Claude Code Skills & SKILL.md Standard

Selection brief

# Linear Dark UI Standard (linear-dark-ui)
Enforces extreme restraint, deep zinc/obsidian surfaces, subtle 1px border glows, and crisp monospace details. Completely eliminates generic white cards and cheesy gradients.

## Use when
- Build or refine a restrained dark interface.

## Required inputs
- Frontend repository
- Page content and target viewports

## Prerequisites
- Access to project source files and a browser for visual review.

## Expected outputs
- Dark UI with reusable surface and typography tokens

Source: https://agenttaste.dev/skills/linear-dark-ui#instructions
Full SKILL.md: https://agenttaste.dev/skills/linear-dark-ui/SKILL.md

Selection brief

# Marc Lou Conversion Engine (marclou-conversion-landing)
Forces your agent to design landing pages that actually sell. Focuses on founder-led credibility, above-the-fold pain relief, wall of love, and zero corporate fluff.

## Use when
- Write or restructure a product landing page for conversion.

## Required inputs
- Product, target audience and offer
- Existing landing page or draft

## Prerequisites
- Product facts and evidence for any conversion claims.

## Expected outputs
- Revised hero, proof and call-to-action copy

Source: https://agenttaste.dev/skills/marclou-conversion-landing#instructions
Full SKILL.md: https://agenttaste.dev/skills/marclou-conversion-landing/SKILL.md

Selection brief

# Anti-Generic UI Guardrails (anti-generic-components)
AI models love generating the same three feature cards with generic Lucide icons. This skill intercepts those patterns and forces asymmetric layouts, visual diffs, and live code previews.

## Use when
- Review generated UI for repetitive layouts and visual clichés.

## Required inputs
- UI source or screenshots
- Product content and design constraints

## Prerequisites
- Access to the UI implementation.

## Expected outputs
- Specific component and composition changes

Source: https://agenttaste.dev/skills/anti-generic-components#instructions
Full SKILL.md: https://agenttaste.dev/skills/anti-generic-components/SKILL.md

Selection brief

# Stripe Fluid Micro-Interactions (stripe-micro-interactions)
Injects precision interaction standards: spring transitions, hover glows calculated via CSS variables, and layout stability.

## Use when
- Implement subtle hover, focus and transition behavior.

## Required inputs
- Interactive components
- Motion and accessibility constraints

## Prerequisites
- Frontend project and a browser to verify keyboard and pointer interactions.

## Expected outputs
- CSS interactions with reduced-motion support

Source: https://agenttaste.dev/skills/stripe-micro-interactions#instructions
Full SKILL.md: https://agenttaste.dev/skills/stripe-micro-interactions/SKILL.md

Selection brief

# Product Hunt Launch Preparation (ph-launch-ready)
Reverse-engineered from 30+ Product Hunt daily winners. Teaches your agent how to write viral maker comments, craft 60-character taglines, and structure launch galleries.

## Use when
- Prepare Product Hunt launch copy and a launch-day sequence.

## Required inputs
- Product, audience and differentiators
- Launch date and verified proof

## Prerequisites
- Check current Product Hunt submission rules and launch timing.

## Expected outputs
- Tagline, maker comment and launch checklist

Source: https://agenttaste.dev/skills/ph-launch-ready#instructions
Full SKILL.md: https://agenttaste.dev/skills/ph-launch-ready/SKILL.md

Selection brief

# Claude Code Clean Architecture (claude-code-clean-arch)
Prevents autonomous coding agents from dumping 800-line spaghetti files and mixing database calls directly into React components.

## Use when
- Separate UI, business logic and persistence boundaries.

## Required inputs
- Repository structure
- Feature requirements and data flow

## Prerequisites
- Access to repository and its engineering instructions.

## Expected outputs
- Architecture boundaries and modular implementation

Source: https://agenttaste.dev/skills/claude-code-clean-arch#instructions
Full SKILL.md: https://agenttaste.dev/skills/claude-code-clean-arch/SKILL.md

Selection brief

# Stitch Design System (Minimalist Taste) (stitch-design-taste)
Translates high-end human craft into strict algorithmic rules for AI agents. Combines 60/40 golden-ratio grid splits, subtle breathing animations, and hardware-accelerated SVG filter effects.

## Use when
- Define a semantic design system for a new or existing interface.

## Required inputs
- Product brief
- Design references and existing tokens

## Prerequisites
- Read the project design constraints before applying the instructions.

## Expected outputs
- Semantic typography, spacing and color rules

Source: https://agenttaste.dev/skills/stitch-design-taste#instructions
Full SKILL.md: https://agenttaste.dev/skills/stitch-design-taste/SKILL.md

Selection brief

# Silicon Valley High-Density Dashboard (b2b-saas-dashboard)
Teaches coding agents to produce high-density, professional enterprise dashboards inspired by Datadog, PostHog, and Stripe. No oversized empty padding or juvenile charts.

## Use when
- Build a dashboard with dense tables and KPI panels.

## Required inputs
- Metrics, table schema and workflows
- Target viewport constraints

## Prerequisites
- Use supplied data and metric definitions.

## Expected outputs
- Dashboard layout with readable metrics and reusable data components

Source: https://agenttaste.dev/skills/b2b-saas-dashboard#instructions
Full SKILL.md: https://agenttaste.dev/skills/b2b-saas-dashboard/SKILL.md

Selection brief

# iOS-Fluid Mobile Web App Standard (ios-fluid-mobile-web)
Eliminates annoying mobile web glitches: fixes address-bar jumpiness with dvh units, integrates touch-friendly bottom sheets, and respects home indicator safe areas.

## Use when
- Implement a mobile web interface with safe-area-aware navigation.

## Required inputs
- Mobile UI source
- Target browsers and device requirements

## Prerequisites
- Mobile browser or emulator for viewport and touch validation.

## Expected outputs
- Responsive mobile layout and sheet interactions

Source: https://agenttaste.dev/skills/ios-fluid-mobile-web#instructions
Full SKILL.md: https://agenttaste.dev/skills/ios-fluid-mobile-web/SKILL.md

Selection brief

# GEO & LLM Citation Engine (seo-geo-citation-ready)
Enforces 2026 Generative Engine Optimization standards so AI engines (Perplexity, ChatGPT, Claude) cite your project directly in their answers.

## Use when
- Add structured data and agent discovery to a public site.

## Required inputs
- Public URL and site source
- Verified facts and page types

## Prerequisites
- Use traceable sources for statistics and validate structured data.

## Expected outputs
- Schema markup and machine-readable discovery files

Source: https://agenttaste.dev/skills/seo-geo-citation-ready#instructions
Full SKILL.md: https://agenttaste.dev/skills/seo-geo-citation-ready/SKILL.md

Selection brief

# Cursor Rules Strict TypeScript Architect (cursor-rules-architect)
Prevents Cursor from taking lazy shortcuts: forbids type assertions (as any), enforces readonly properties on domain models, and checks for unused imports.

## Use when
- Enforce TypeScript and server-boundary rules across a project.

## Required inputs
- TypeScript repository
- Framework and validation requirements

## Prerequisites
- Access to the compiler and relevant project checks.

## Expected outputs
- Reusable components and explicit input validation

Source: https://agenttaste.dev/skills/cursor-rules-architect#instructions
Full SKILL.md: https://agenttaste.dev/skills/cursor-rules-architect/SKILL.md

Selection brief

# Show HN Technical Launch Copy (hacker-news-show-hn)
Hacker News hates marketing fluff and buzzwords. This skill guides your agent to write technical, humble, and architecture-focused Show HN copy that engineers actually respect.

## Use when
- Draft a technical Show HN introduction and project README.

## Required inputs
- Working product URL
- Technical details and verifiable benchmarks

## Prerequisites
- Follow current Hacker News rules and use supported claims.

## Expected outputs
- Show HN copy and concise technical documentation

Source: https://agenttaste.dev/skills/hacker-news-show-hn#instructions
Full SKILL.md: https://agenttaste.dev/skills/hacker-news-show-hn/SKILL.md

Selection brief

# Humanizer: Anti-AI Writing Filter (humanizer-anti-ai-slop)
Based on Wikipedia's WikiProject AI Cleanup. Systematically strips bloated AI clichés: "delves into", "testament to", "crucial reminder", rule-of-three sentences, and empty promotional adjectives.

## Use when
- Edit a draft to remove inflated or repetitive AI-style wording.

## Required inputs
- Original draft
- Audience, tone and facts to preserve

## Prerequisites
- Source text and factual references when claims need verification.

## Expected outputs
- Clearer draft with the original meaning preserved

Source: https://agenttaste.dev/skills/humanizer-anti-ai-slop#instructions
Full SKILL.md: https://agenttaste.dev/skills/humanizer-anti-ai-slop/SKILL.md

Selection brief

# Figma-to-Code 1:1 Precision Engine (figma-to-production-code)
Enforces strict translation rules when converting Figma frames into React components. Reuses project design tokens, extracts real vector SVGs, and prevents arbitrary hardcoded hex codes.

## Use when
- Implement a provided Figma frame using project design tokens.

## Required inputs
- Figma node or design export
- Frontend repository and reusable tokens

## Prerequisites
- Figma file access or a complete design export.

## Expected outputs
- Responsive components mapped to the supplied design

Source: https://agenttaste.dev/skills/figma-to-production-code#instructions
Full SKILL.md: https://agenttaste.dev/skills/figma-to-production-code/SKILL.md

Selection brief

# Waffo Pancake Global Checkout Architecture (waffo-pancake-checkout)
Step-by-step rules for integrating Merchant-of-Record payments via @waffo/pancake-ts. Includes cryptographic webhook signature verification, idempotent ledger records, and refund handling.

## Use when
- Integrate Waffo Pancake checkout and verified payment webhooks.

## Required inputs
- Server code and fulfillment requirements
- Merchant configuration and test environment

## Prerequisites
- Current @waffo/pancake-ts documentation.
- Server-side signing credentials and provider test access.

## Expected outputs
- Server-only checkout and idempotent webhook handling

Source: https://agenttaste.dev/skills/waffo-pancake-checkout#instructions
Full SKILL.md: https://agenttaste.dev/skills/waffo-pancake-checkout/SKILL.md

Selection brief

# Reverse-Engineer Website Cloner (pixel-perfect-site-clone)
Teaches autonomous agents how to rebuild any reference website with forensic precision: extracts computed CSS styles, downloads layered assets, and builds responsive components section-by-section.

## Use when
- Rebuild an authorized reference interface with reusable components.

## Required inputs
- Reference URL or screenshots
- Target framework and viewports

## Prerequisites
- Access to the reference UI and permission to reuse relevant assets.

## Expected outputs
- Responsive implementation using inspected tokens and assets

Source: https://agenttaste.dev/skills/pixel-perfect-site-clone#instructions
Full SKILL.md: https://agenttaste.dev/skills/pixel-perfect-site-clone/SKILL.md

Selection brief

# Competitor Growth & GTM Teardown (competitor-growth-teardown)
Reverse-engineers how top AI startups acquire their first 10,000 customers. Analyzes landing page evolution via Wayback Machine, maps viral social propagation chains, and benchmarks freemium margins.

## Use when
- Investigate competitor positioning, pricing and acquisition channels.

## Required inputs
- Competitor URLs
- Product category and target market

## Prerequisites
- Web access; separate observed facts from unverified estimates.

## Expected outputs
- Source-backed comparison and growth hypotheses

Source: https://agenttaste.dev/skills/competitor-growth-teardown#instructions
Full SKILL.md: https://agenttaste.dev/skills/competitor-growth-teardown/SKILL.md

Selection brief

# DevRel & Docs-as-Marketing Engine (devrel-docs-as-growth)
Engineers hate traditional marketing — documentation is your highest-converting acquisition funnel. This skill teaches AI agents to structure quickstarts, interactive API playgrounds, and copy-paste recipes that drive immediate adoption.

## Use when
- Improve developer quickstarts and API onboarding documentation.

## Required inputs
- API or SDK documentation
- Working example and target developer audience

## Prerequisites
- Verified API behavior and test credentials for runnable examples.

## Expected outputs
- Runnable quickstart and clearer developer onboarding copy

Source: https://agenttaste.dev/skills/devrel-docs-as-growth#instructions
Full SKILL.md: https://agenttaste.dev/skills/devrel-docs-as-growth/SKILL.md

Selection brief

# Frontend design (anthropic-frontend-design)
Anthropic’s frontend design skill covers typography, composition, visual identity and implementation decisions for new or existing interfaces.

## Use when
- Build a website, landing page or application interface.
- Reshape an existing UI around a specific visual identity.

## Required inputs
- Product brief and audience
- Repository, framework and design constraints

## Prerequisites
- Access to the project source files.
- Read the upstream skill and its license terms.

## Expected outputs
- Implemented interface
- Coherent typography, layout and interaction choices

Source: https://github.com/anthropics/skills/blob/683bc88e56f3e09ba94f7055977f3d3aa499f202/skills/frontend-design/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/anthropic-frontend-design/SKILL.md

Selection brief

# Web interface guidelines (vercel-web-design-guidelines)
This upstream skill fetches the current Web Interface Guidelines and reviews the requested files for accessibility, interaction and usability issues.

## Use when
- Audit an existing UI or review frontend changes.
- Check accessibility and interaction behavior.

## Required inputs
- Files or a file pattern to review

## Prerequisites
- Access to project files.
- Web access to fetch the upstream guidelines.

## Expected outputs
- Findings with file and line references

Source: https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/skills/web-design-guidelines/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/vercel-web-design-guidelines/SKILL.md

Selection brief

# React best practices (vercel-react-best-practices)
Vercel Engineering’s React performance skill includes a companion rule collection. Install the package so the referenced rules remain available.

## Use when
- Write, review or refactor React or Next.js code.
- Investigate unnecessary rendering or slow data loading.

## Required inputs
- React or Next.js repository
- Performance symptoms or implementation task

## Prerequisites
- React or Next.js project.
- Install the complete upstream skill directory, including its rules.

## Expected outputs
- Prioritized performance changes
- Validation against the relevant rules

Source: https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/skills/react-best-practices/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/vercel-react-best-practices/SKILL.md

Selection brief

# SEO audit (marketing-seo-audit)
A public marketing skill for investigating crawlability, indexation, page metadata and search performance. Findings should be tied to the inspected site and available data.

## Use when
- Investigate indexing issues, ranking losses or organic traffic changes.
- Review a site’s SEO before a launch.

## Required inputs
- Website URL and target market
- Search Console or analytics data when available

## Prerequisites
- Web access to inspect the site.
- Read linked reference files and product marketing context.

## Expected outputs
- Sourced SEO findings
- Prioritized fixes and validation steps

Source: https://github.com/coreyhaines31/marketingskills/blob/1efedbc5148b54b2f0f6c6c9fe0be62e151c7fff/skills/seo-audit/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-seo-audit/SKILL.md

Selection brief

# AI search optimization (marketing-ai-seo)
The public ai-seo skill covers answer engine optimization and content visibility in AI-generated search answers. It does not guarantee citations or search rankings.

## Use when
- Review content for AI search or answer engine visibility.

## Required inputs
- Website or content URL
- Target questions and audience

## Prerequisites
- Web access and the relevant content.
- Access to visibility tools when quantitative measurement is requested.

## Expected outputs
- Content and citation improvements
- A visibility measurement plan

Source: https://github.com/coreyhaines31/marketingskills/blob/1efedbc5148b54b2f0f6c6c9fe0be62e151c7fff/skills/ai-seo/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-ai-seo/SKILL.md

Selection brief

# SERP keyword clustering (seo-keyword-clustering)
The Claude SEO plugin’s seo-cluster skill groups keyword opportunities using SERP evidence and plans pillar pages, supporting content and internal links.

## Use when
- Turn a seed keyword or keyword list into a content architecture.
- Investigate overlapping search intent and keyword cannibalization.

## Required inputs
- Seed keyword or URL
- Target language and market

## Prerequisites
- Claude Code with the full Claude SEO plugin and its companion scripts.
- Live web search or a configured SERP data provider.
- Search volume and difficulty require a data provider; do not invent metrics.

## Expected outputs
- Keyword clusters
- Pillar and supporting page plan

Source: https://github.com/AgriciDaniel/claude-seo/blob/4b99de2f7de7e7d5247042e5fb5b4ea9368ef734/skills/seo-cluster/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/seo-keyword-clustering/SKILL.md

Selection brief

# Live keyword research (dataforseo-keyword-research)
The Claude SEO DataForSEO extension exposes live keyword and competitor data through its MCP server. Provider credentials and paid API usage are required.

## Use when
- Validate keyword demand and competition with live metrics.
- Research competitor keywords for a specific location and language.

## Required inputs
- Seed keywords or competitor domain
- Location and language
- Approved API usage budget

## Prerequisites
- Claude Code and the complete Claude SEO plugin.
- DataForSEO extension and connected MCP server.
- DataForSEO credentials and sufficient API balance.

## Expected outputs
- Keyword metrics with sources
- SERP and competitor evidence

Source: https://github.com/AgriciDaniel/claude-seo/blob/4b99de2f7de7e7d5247042e5fb5b4ea9368ef734/extensions/dataforseo/skills/seo-dataforseo/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/dataforseo-keyword-research/SKILL.md

Selection brief

# Stripe integration best practices (stripe-best-practices)
Stripe’s own agent skill guides API selection, test environments, subscriptions, tax, Connect and payment integration practices.

## Use when
- Implement or review a Stripe checkout or subscription integration.
- Choose between Stripe APIs for a defined payment workflow.

## Required inputs
- Payment use case and existing code
- Stripe integration and account configuration

## Prerequisites
- Current Stripe documentation and project code.
- Test credentials for any integration tests; keep secrets server-side.

## Expected outputs
- Integration decisions tied to Stripe documentation
- Implementation and test-mode validation

Source: https://github.com/stripe/ai/blob/08d371a9fbe098ecc943713a70a669ef05cfa6d6/skills/stripe-best-practices/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/stripe-best-practices/SKILL.md

Selection brief

# Stripe API and SDK upgrades (stripe-api-upgrades)
Stripe’s upgrade-stripe skill reviews current versions, the target API, webhook endpoints and SDK changes before implementing a migration.

## Use when
- Upgrade a Stripe SDK or API version.
- Review webhook behavior before a payment migration.

## Required inputs
- Current API and SDK versions
- Target version and integration files

## Prerequisites
- Current official migration documentation.
- A test environment for verifying payment and webhook behavior.

## Expected outputs
- Documented upgrade plan
- Validated integration and webhook changes

Source: https://github.com/stripe/ai/blob/08d371a9fbe098ecc943713a70a669ef05cfa6d6/skills/upgrade-stripe/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/stripe-api-upgrades/SKILL.md

Selection brief

# Web app testing with Playwright (anthropic-webapp-testing)
Anthropic’s webapp-testing toolkit uses Python Playwright and includes a server-lifecycle helper, examples and browser-log workflows for testing local applications.

## Use when
- Verify a local web app’s interactions or reproduce a frontend bug.

## Required inputs
- Local application URL or startup commands
- User journeys and expected behavior

## Prerequisites
- Python with Playwright and its browser binaries installed.
- A locally runnable application; install the entire skill directory to retain scripts and examples.

## Expected outputs
- Browser test scripts
- Screenshots, logs and observed test results

Source: https://github.com/anthropics/skills/blob/dbd4588f9e1033efb41dad4bef2f7947c8993d44/skills/webapp-testing/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/anthropic-webapp-testing/SKILL.md

Selection brief

# MCP server builder (anthropic-mcp-builder)
Anthropic’s MCP development guide covers protocol research, Python or TypeScript implementation, tool design, testing and task-based evaluations, with companion references and scripts.

## Use when
- Expose an external API or service through an MCP server.

## Required inputs
- Service API documentation and allowed operations
- Target MCP client, language and authentication requirements

## Prerequisites
- Python or Node.js development environment and the appropriate MCP SDK.
- Access to current protocol documentation; use test credentials for authenticated integrations.

## Expected outputs
- MCP server implementation
- Tool tests and evaluation questions

Source: https://github.com/anthropics/skills/blob/dbd4588f9e1033efb41dad4bef2f7947c8993d44/skills/mcp-builder/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/anthropic-mcp-builder/SKILL.md

Selection brief

# Skill authoring and evaluation (anthropic-skill-creator)
Anthropic’s skill-creator workflow iterates on skill instructions, trigger descriptions and evaluations. The bundled evaluation workflow uses Claude tooling; install the scripts and reference material together.

## Use when
- Create a reusable agent skill or evaluate an existing skill.

## Required inputs
- Task definition and representative prompts
- Existing skill, expected outputs and evaluation criteria

## Prerequisites
- Claude Code plus Python and the bundled evaluation scripts for the documented evaluation workflow.
- Model calls used by evaluations may incur usage charges.

## Expected outputs
- Versioned SKILL.md package
- Evaluation results and revised trigger description

Source: https://github.com/anthropics/skills/blob/dbd4588f9e1033efb41dad4bef2f7947c8993d44/skills/skill-creator/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/anthropic-skill-creator/SKILL.md

Selection brief

# React composition patterns (vercel-composition-patterns)
Vercel’s composition guide covers compound components, state ownership, context and React 19 APIs. Its companion rule files provide concrete component architecture examples.

## Use when
- Refactor a component API with many boolean props.
- Design a reusable React component library.

## Required inputs
- React components and their consumers
- Required variants, state ownership and composition constraints

## Prerequisites
- React project source and access to all affected consumers.
- Install the complete upstream rule directory.

## Expected outputs
- Composable component APIs
- Refactored consumers and relevant checks

Source: https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/skills/composition-patterns/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/vercel-composition-patterns/SKILL.md

Selection brief

# React Native performance practices (vercel-react-native-skills)
Vercel’s React Native collection organizes performance and implementation rules for Expo and React Native, including list virtualization, animation, navigation and monorepo dependencies.

## Use when
- Build or review a React Native or Expo app.
- Investigate slow scrolling, rendering or mobile animations.

## Required inputs
- React Native repository and target devices
- Performance symptoms or implementation task

## Prerequisites
- React Native or Expo development environment.
- A simulator or physical device for runtime checks; retain the companion rules.

## Expected outputs
- Prioritized mobile implementation changes
- Device validation checklist

Source: https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/skills/react-native-skills/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/vercel-react-native-skills/SKILL.md

Selection brief

# Postgres performance and security (supabase-postgres-best-practices)
Supabase’s Postgres guide supplies rules and SQL examples for query performance, connections, security, schema design and locking. It applies to Postgres beyond Supabase-hosted projects.

## Use when
- Write or review Postgres queries, migrations or security policies.
- Diagnose slow queries or connection exhaustion.

## Required inputs
- Schema, queries and query plans
- Postgres version and workload constraints

## Prerequisites
- A Postgres project and representative queries or schema.
- A test database for executing changes; keep the referenced rule collection.

## Expected outputs
- SQL or schema recommendations
- Relevant performance and access-control checks

Source: https://github.com/supabase/agent-skills/blob/c9be0e931b7930f7d02126d04774d904c381e7d7/skills/supabase-postgres-best-practices/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/supabase-postgres-best-practices/SKILL.md

Selection brief

# Cloudflare Agents SDK (cloudflare-agents-sdk)
Cloudflare’s Agents SDK skill routes implementation work to current official documentation and companion references for agent lifecycle, durable state, callable methods, scheduling and chat.

## Use when
- Build or review an application using Cloudflare’s agents package.

## Required inputs
- Workers repository and installed agents version
- State, scheduling and communication requirements

## Prerequisites
- Cloudflare Workers project with the agents package and current generated types.
- Network access for documentation; Cloudflare account access is required for deployment.

## Expected outputs
- Agent implementation and bindings
- Runtime and integration validation plan

Source: https://github.com/cloudflare/skills/blob/86505e44f87d801aa1864a3c4109e9a8ae5c409f/skills/agents-sdk/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/cloudflare-agents-sdk/SKILL.md

Selection brief

# Cloudflare Durable Objects (cloudflare-durable-objects)
Cloudflare’s Durable Objects guide covers stateful coordination, authorization, stub creation, storage, alarms and tests, with current platform documentation as the API authority.

## Use when
- Implement chat rooms, coordinated sessions or other stateful Workers features.

## Required inputs
- Workers repository and coordination requirements
- Storage, identity and concurrency constraints

## Prerequisites
- Workers project with Durable Object bindings and migration configuration.
- Local runtime or a permitted Cloudflare test environment for verification.

## Expected outputs
- Durable Object implementation and configuration
- Storage, authorization and lifecycle tests

Source: https://github.com/cloudflare/skills/blob/86505e44f87d801aa1864a3c4109e9a8ae5c409f/skills/durable-objects/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/cloudflare-durable-objects/SKILL.md

Selection brief

# Wrangler CLI workflows (cloudflare-wrangler)
Cloudflare’s Wrangler skill inspects existing Wrangler configuration, retrieves current command documentation and distinguishes local resources from remote changes before applying operations.

## Use when
- Run or debug Wrangler in an existing configured project.

## Required inputs
- wrangler.jsonc, wrangler.json or wrangler.toml
- Installed CLI version and target environment

## Prerequisites
- An existing Wrangler-configured project and its local CLI dependency.
- Cloudflare credentials and explicit target selection for remote operations; new cf-based projects use Cloudflare’s separate cf-cli skill.

## Expected outputs
- Verified CLI commands or configuration changes
- Validation of the intended Worker and resources

Source: https://github.com/cloudflare/skills/blob/86505e44f87d801aa1864a3c4109e9a8ae5c409f/skills/wrangler/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/cloudflare-wrangler/SKILL.md

Selection brief

# Workers production practices (cloudflare-workers-best-practices)
Cloudflare’s Workers guide checks production code and configuration against installed versions, generated types and current documentation, including secrets, logs, streaming and runtime anti-patterns.

## Use when
- Write or review a Cloudflare Worker before deployment.

## Required inputs
- Worker source and configuration
- Runtime versions and production requirements

## Prerequisites
- Workers repository with its installed toolchain and generated binding types.
- Network access to current Cloudflare documentation.

## Expected outputs
- Specific code and configuration changes
- Type, build and runtime checks

Source: https://github.com/cloudflare/skills/blob/86505e44f87d801aa1864a3c4109e9a8ae5c409f/skills/workers-best-practices/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/cloudflare-workers-best-practices/SKILL.md

Selection brief

# Web performance diagnosis (cloudflare-web-performance)
Cloudflare’s web-perf skill combines browser traces, network requests and source inspection to diagnose performance issues. It distinguishes collected measurements from unavailable tooling and does not guarantee a performance score.

## Use when
- Investigate slow loading, interaction delays or layout shifts.

## Required inputs
- Website URL and relevant project source
- Target device, symptoms and available browser tools

## Prerequisites
- Browser performance tooling such as Chrome DevTools MCP for trace measurements.
- Source access is needed for implementation changes; field data requires a separate data source.

## Expected outputs
- Measured findings and prioritized fixes
- Trace, network or source evidence with limitations

Source: https://github.com/cloudflare/skills/blob/86505e44f87d801aa1864a3c4109e9a8ae5c409f/skills/web-perf/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/cloudflare-web-performance/SKILL.md

Selection brief

# Expo Router navigation (expo-router-navigation)
Expo’s routing skill covers route organization, dynamic segments, native stacks and tabs, headers, link previews and modal presentation, with SDK-specific reference files.

## Use when
- Implement or restructure navigation in an Expo Router app.

## Required inputs
- Expo repository and SDK version
- Route map and navigation behavior

## Prerequisites
- Expo Router project and an appropriate simulator or device.
- Keep companion references and check API support against the installed SDK.

## Expected outputs
- Route structure and navigation components
- Navigation and deep-link checks

Source: https://github.com/expo/skills/blob/7ddc1f5796996e5c7efe2fc3fa9168eb24e8dac1/plugins/expo/skills/expo-router/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/expo-router-navigation/SKILL.md

Selection brief

# Expo data fetching and offline states (expo-data-fetching)
Expo’s networking guide covers fetch, React Query, SWR and router data loaders, including request debugging, caching and explicit screen states.

## Use when
- Implement or debug network requests in an Expo application.

## Required inputs
- Expo screen or data layer
- API contract, authentication and caching requirements

## Prerequisites
- Expo application and an accessible API or test fixture.
- Check library and router-loader availability for the project’s installed versions.

## Expected outputs
- Data-fetching implementation
- Explicit screen states and request validation

Source: https://github.com/expo/skills/blob/7ddc1f5796996e5c7efe2fc3fa9168eb24e8dac1/plugins/expo/skills/expo-data-fetching/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/expo-data-fetching/SKILL.md

Selection brief

# Expo SDK upgrades (expo-sdk-upgrades)
Expo’s upgrade skill follows the current SDK migration process, dependency checks and native changes, with references for React, navigation, media packages and the New Architecture.

## Use when
- Upgrade an Expo SDK or investigate upgrade-related build failures.

## Required inputs
- Current SDK, dependency versions and native configuration
- Target SDK and observed build errors

## Prerequisites
- Expo repository, package manager and a reproducible development build.
- Native toolchains or EAS access are needed for the corresponding build checks.

## Expected outputs
- Updated dependencies and migration changes
- Post-upgrade build and device checks

Source: https://github.com/expo/skills/blob/7ddc1f5796996e5c7efe2fc3fa9168eb24e8dac1/plugins/expo/skills/expo-upgrade/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/expo-sdk-upgrades/SKILL.md

Selection brief

# Expo EAS CI/CD workflows (expo-eas-workflows)
Expo’s EAS workflow skill covers workflow files, expressions and validation against current service documentation. The instructions are free; executing jobs uses EAS services and may incur charges.

## Use when
- Create or review CI/CD automation for an Expo project.

## Required inputs
- Expo project and eas.json
- Build, submission or deployment pipeline requirements

## Prerequisites
- Expo account, EAS configuration and the documented CLI tooling.
- EAS plan limits and usage charges apply; store submission also requires the relevant developer accounts.

## Expected outputs
- .eas/workflows YAML configuration
- Validation results and operational prerequisites

Source: https://github.com/expo/skills/blob/7ddc1f5796996e5c7efe2fc3fa9168eb24e8dac1/plugins/expo/skills/eas-workflows/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/expo-eas-workflows/SKILL.md

Selection brief

# Expo native screen design (expo-native-screen-design)
Expo’s native UI skill covers screen structure, styling, colors, icons, media and visual effects. Its routing, native controls and animation work are delegated to the corresponding Expo skills.

## Use when
- Build or refine screens in an Expo app.

## Required inputs
- Screen content and interaction requirements
- Expo SDK version and target platforms

## Prerequisites
- Expo project and simulator or physical device.
- Install expo-ui for native controls, expo-router for navigation and expo-animation when motion is needed.

## Expected outputs
- Native screen implementation
- Platform and responsive verification steps

Source: https://github.com/expo/skills/blob/7ddc1f5796996e5c7efe2fc3fa9168eb24e8dac1/plugins/expo/skills/expo-native-ui/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/expo-native-screen-design/SKILL.md

Selection brief

# Expo native controls with @expo/ui (expo-native-controls)
Expo’s UI skill documents Host-wrapped native controls, grouped forms, sheets, pickers and platform-specific trees. It also distinguishes short native grouped lists from virtualized large-data lists.

## Use when
- Implement native controls or replace community UI components in an Expo app.

## Required inputs
- Expo SDK version and current UI components
- Target iOS and Android behavior

## Prerequisites
- A compatible @expo/ui package and Expo SDK; the pinned guide’s universal layer requires SDK 56 or later.
- Install the full skill directory to retain its component-discovery script.

## Expected outputs
- @expo/ui component implementation
- Platform checks and migration notes

Source: https://github.com/expo/skills/blob/7ddc1f5796996e5c7efe2fc3fa9168eb24e8dac1/plugins/expo/skills/expo-ui/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/expo-native-controls/SKILL.md

Selection brief

# Expo animation and gestures (expo-native-animation)
Expo’s animation skill, developed with Emil Kowalski, sequences motion decisions around UI-thread execution, interruption, velocity and device performance, with reference material and examples.

## Use when
- Build native animations or diagnose stuttering motion in an Expo app.

## Required inputs
- Interaction and animation requirements
- Installed animation libraries and supported devices

## Prerequisites
- Expo or React Native project with compatible Reanimated and Gesture Handler versions.
- A release build on a representative device for meaningful performance verification.

## Expected outputs
- Animation or gesture implementation
- Reduced-motion behavior and device validation

Source: https://github.com/expo/skills/blob/7ddc1f5796996e5c7efe2fc3fa9168eb24e8dac1/plugins/expo/skills/expo-animation/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/expo-native-animation/SKILL.md

Selection brief

# Landing page and form CRO (marketing-page-cro)
Corey Haines’s CRO skill reviews homepages, pricing pages and lead forms, then separates quick fixes from larger experiments using the product context and available conversion evidence.

## Use when
- Review a marketing page or form that is losing visitors before conversion.

## Required inputs
- Page URL or copy
- Audience, offer, primary action and available funnel data

## Prerequisites
- Access to the page and accurate product facts.
- Conversion data improves diagnosis; improvement claims require actual measurement.

## Expected outputs
- Prioritized page or form changes
- Experiment hypotheses and validation steps

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/cro/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-page-cro/SKILL.md

Selection brief

# Signup flow optimization (marketing-signup-optimization)
Corey Haines’s signup skill reviews single- and multi-step registration, mobile form behavior, trust signals, validation and the transition into the product.

## Use when
- Investigate signup abandonment or improve trial registration.

## Required inputs
- Signup flow and account requirements
- Known drop-off data and target audience

## Prerequisites
- Access to the current signup experience and its technical constraints.
- A permitted test account for any authenticated walkthrough.

## Expected outputs
- Revised signup flow recommendations
- Field, error-state and completion checks

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/signup/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-signup-optimization/SKILL.md

Selection brief

# Onboarding and activation (marketing-onboarding-activation)
Corey Haines’s onboarding skill defines meaningful activation, reviews first-run steps and empty states, and plans interventions for users who stall before receiving value.

## Use when
- Users sign up but do not complete setup or reach the product’s core value.

## Required inputs
- Product workflow and activation definition
- First-session experience and available usage data

## Prerequisites
- Product access and a clear description of a successful first use.
- Representative user evidence for validating activation assumptions.

## Expected outputs
- Onboarding flow and checklist
- Activation metrics and improvement hypotheses

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/onboarding/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-onboarding-activation/SKILL.md

Selection brief

# Product and landing page copywriting (marketing-copywriting)
Corey Haines’s copywriting skill builds marketing-page copy from audience context, voice and evidence. It covers page structure, alternatives and CTA language without requiring a full rewrite for every request.

## Use when
- Write or rewrite a homepage, product page or pricing page.

## Required inputs
- Product brief, audience and offer
- Existing copy, voice examples and supportable claims

## Prerequisites
- Accurate product details and access to any source material used for claims.
- Provide the existing voice and requested edit scope when preserving copy.

## Expected outputs
- Page copy with headline and CTA options
- Rationale and evidence requirements

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/copywriting/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-copywriting/SKILL.md

Selection brief

# Marketing copy editing (marketing-copy-editing)
Corey Haines’s editing workflow reviews marketing copy for clarity, specificity, unsupported claims and generic phrasing, including focused edits and content refreshes.

## Use when
- Polish an existing page or update outdated marketing copy.

## Required inputs
- Existing draft and desired voice
- Edit scope and evidence for factual claims

## Prerequisites
- The original text and the intended audience.
- Source evidence for statistics, testimonials or comparative statements.

## Expected outputs
- Edited copy
- Explanation of material wording or claim changes

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/copy-editing/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-copy-editing/SKILL.md

Selection brief

# SaaS pricing and packaging (marketing-pricing-strategy)
Corey Haines’s pricing skill separates packaging, price metric and price point, then uses customer context, costs and willingness-to-pay research to form testable pricing decisions.

## Use when
- Set initial prices or review an existing pricing structure.

## Required inputs
- Product, audience, current plans and costs
- Customer research and pricing performance when available

## Prerequisites
- Actual product economics and current offer details.
- Customer evidence is needed before treating suggested prices as validated demand.

## Expected outputs
- Packaging and pricing options with tradeoffs
- Research and validation plan

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/pricing/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-pricing-strategy/SKILL.md

Selection brief

# Analytics and event tracking (marketing-analytics-tracking)
Corey Haines’s analytics skill works backward from business decisions to event design, implementation and data-quality checks, including consistent observation windows for conversion rates.

## Use when
- Implement tracking or diagnose missing and inconsistent conversion events.

## Required inputs
- Business questions and funnel definitions
- Current analytics stack, event data and privacy constraints

## Prerequisites
- Access to relevant code and analytics configuration.
- Authorized tool access is required to verify events inside an analytics account.

## Expected outputs
- Event specification and implementation guidance
- Validation and reconciliation checklist

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/analytics/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-analytics-tracking/SKILL.md

Selection brief

# Competitor and alternatives pages (marketing-competitor-alternatives)
Corey Haines’s competitor-page skill distinguishes alternatives lists, direct comparisons and competitor-versus-competitor pages, with centralized evidence and explicit strengths and weaknesses.

## Use when
- Build a comparison page for explicitly named competing products.

## Required inputs
- Your product and named competitors
- Target buyers, verified pricing and feature sources

## Prerequisites
- Current public sources for every material comparison.
- Disclose your relationship to the product; do not invent competitor weaknesses.

## Expected outputs
- Comparison page draft or page plan
- Source-backed competitor data

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/competitors/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-competitor-alternatives/SKILL.md

Selection brief

# Programmatic SEO planning (marketing-programmatic-seo)
Corey Haines’s programmatic SEO skill evaluates keyword patterns, data requirements, templates, internal linking and launch checks before scaling a page system.

## Use when
- Assess an opportunity for a useful data-driven directory or template-page system.

## Required inputs
- Product, audience and conversion objective
- Candidate keyword patterns and available unique data

## Prerequisites
- A reliable dataset and evidence of distinct user intent.
- Search-volume or competition figures require real data sources.

## Expected outputs
- Programmatic page strategy and template plan
- Rollout quality checks and measurement

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/programmatic-seo/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-programmatic-seo/SKILL.md

Selection brief

# Structured data and JSON-LD (marketing-schema-markup)
Corey Haines’s schema skill covers organization, article, product and breadcrumb markup, with validation and current search-feature eligibility checks before making rich-result claims.

## Use when
- Add or repair structured data on an existing website.

## Required inputs
- Page content and current markup
- Relevant entity facts and intended search feature

## Prerequisites
- Access to page HTML or source and verified entity facts.
- Check current Google documentation; markup does not guarantee enhanced search results.

## Expected outputs
- JSON-LD matching visible content
- Validation findings and eligibility limitations

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/schema/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-schema-markup/SKILL.md

Selection brief

# Product launch strategy (marketing-product-launch)
Corey Haines’s launch skill covers readiness gates, phased launches, announcements and post-launch follow-through, including a Product Hunt preparation framework.

## Use when
- Prepare a product launch, feature release or public announcement.

## Required inputs
- Product facts, target audience and release scope
- Timeline, available channels and support capacity

## Prerequisites
- A verifiable product state, pricing and support plan.
- External publishing or outreach needs the appropriate authorization; no ranking outcome is guaranteed.

## Expected outputs
- Launch checklist and channel plan
- Announcement ideas and post-launch actions

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/launch/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-product-launch/SKILL.md

Selection brief

# Keyword-led content strategy (marketing-content-strategy)
Corey Haines’s content-strategy skill combines keyword research, customer questions, topic clusters and resource constraints to plan searchable and shareable content.

## Use when
- Choose what content to create and connect search intent to useful pages.

## Required inputs
- Product, audience and content objective
- Customer questions, existing content and available keyword evidence

## Prerequisites
- Product context and customer or search evidence.
- Live search volume and difficulty need a connected data provider; the skill itself supplies no metrics.

## Expected outputs
- Priority topics and content pillars
- Topic cluster map and production plan

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/content-strategy/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-content-strategy/SKILL.md

Selection brief

# A/B test design and analysis (marketing-ab-testing)
Corey Haines’s experimentation skill covers hypothesis design, variants, sample size, traffic allocation and analysis, plus maintaining an experiment backlog.

## Use when
- Compare product or marketing variants with a defined outcome.

## Required inputs
- Baseline rate, traffic and proposed change
- Minimum effect of interest, constraints and test tooling

## Prerequisites
- Reliable event data and enough eligible traffic for the planned design.
- Low sample counts are not proof of a conversion uplift.

## Expected outputs
- Experiment specification and measurement plan
- Analysis criteria and result interpretation

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/ab-testing/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-ab-testing/SKILL.md

Selection brief

# Lifecycle email sequences (marketing-email-sequences)
Corey Haines’s email-sequence skill covers audience segments, timing, sequence structure and individual email copy, with companion templates and measurement guidance.

## Use when
- Draft or improve an opted-in lifecycle email program.

## Required inputs
- Product, audience segment and lifecycle stage
- Trigger events, offer details and brand voice

## Prerequisites
- Accurate product details and an authorized, appropriately consented audience.
- Sending requires a separately configured email platform; this skill does not send messages.

## Expected outputs
- Sequence map with timing and triggers
- Email drafts, CTAs and success metrics

Source: https://github.com/coreyhaines31/marketingskills/blob/e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b/skills/emails/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/marketing-email-sequences/SKILL.md

Selection brief

# Superpowers brainstorming (superpowers-brainstorming)
Jesse Vincent’s Superpowers brainstorming workflow uses focused questions and design discussion to turn an uncertain request into an agreed direction before implementation.

## Use when
- Explore a feature or substantial change whose requirements are still uncertain.

## Required inputs
- Initial idea and intended users
- Repository context, constraints and success criteria

## Prerequisites
- Access to the relevant project and a user who can settle product decisions.
- Install the complete skill directory; the optional visual companion uses a local Node.js server.

## Expected outputs
- Clarified requirements and design decisions
- An agreed design ready for implementation planning

Source: https://github.com/obra/superpowers/blob/bb92a77741419a4ab5f06e711a283343f1ada0c3/skills/brainstorming/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/superpowers-brainstorming/SKILL.md

## Popularity evidence
- 302,164 GitHub repo stars — obra/superpowers; checked 2026-10-20. Source: https://github.com/obra/superpowers/stargazers
- 398,168 skill installs (all time) — obra/superpowers / brainstorming · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/obra/superpowers/brainstorming
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Superpowers systematic debugging (superpowers-systematic-debugging)
Superpowers’ debugging discipline separates root-cause investigation, pattern analysis, hypothesis testing and implementation, with companion debugging techniques in the original directory.

## Use when
- Diagnose a failing test, build, integration or production behavior.

## Required inputs
- Failure symptoms and reproduction steps
- Relevant code, logs and execution environment

## Prerequisites
- A reproducible failure or access to an environment that exhibits it.
- Retain the companion debugging references; do not share credentials in captured logs.

## Expected outputs
- Evidence-backed root cause
- Targeted fix and regression verification

Source: https://github.com/obra/superpowers/blob/bb92a77741419a4ab5f06e711a283343f1ada0c3/skills/systematic-debugging/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/superpowers-systematic-debugging/SKILL.md

## Popularity evidence
- 302,164 GitHub repo stars — obra/superpowers; checked 2026-10-20. Source: https://github.com/obra/superpowers/stargazers
- 300,287 skill installs (all time) — obra/superpowers / systematic-debugging · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/obra/superpowers/systematic-debugging
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Superpowers implementation plans (superpowers-writing-plans)
Superpowers’ planning skill writes a handoff for an engineer who has not seen the project, specifying interfaces, files, test commands and task boundaries from an already agreed design.

## Use when
- Plan a multi-step implementation after requirements have been agreed.

## Required inputs
- Approved specification or design
- Repository structure and existing test commands

## Prerequisites
- An agreed specification and access to the codebase.
- Install the corresponding Superpowers execution skills separately for the documented execution handoff.

## Expected outputs
- Versioned implementation plan
- Task-level acceptance and verification steps

Source: https://github.com/obra/superpowers/blob/bb92a77741419a4ab5f06e711a283343f1ada0c3/skills/writing-plans/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/superpowers-writing-plans/SKILL.md

## Popularity evidence
- 302,164 GitHub repo stars — obra/superpowers; checked 2026-10-20. Source: https://github.com/obra/superpowers/stargazers
- 278,266 skill installs (all time) — obra/superpowers / writing-plans · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/obra/superpowers/writing-plans
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Superpowers test-driven development (superpowers-test-driven-development)
Superpowers’ TDD skill follows a red-green-refactor cycle, explicitly checking that a new test fails for the intended reason before implementing the behavior.

## Use when
- Implement a feature or bug fix with a test-first workflow.

## Required inputs
- Behavior to implement and expected result
- Project source and a runnable test suite

## Prerequisites
- A working test runner and a testable interface for the requested behavior.
- Keep the bundled testing guidance with SKILL.md.

## Expected outputs
- Behavior-focused regression tests
- Implementation with observed red and green results

Source: https://github.com/obra/superpowers/blob/bb92a77741419a4ab5f06e711a283343f1ada0c3/skills/test-driven-development/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/superpowers-test-driven-development/SKILL.md

## Popularity evidence
- 302,164 GitHub repo stars — obra/superpowers; checked 2026-10-20. Source: https://github.com/obra/superpowers/stargazers
- 254,722 skill installs (all time) — obra/superpowers / test-driven-development · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/obra/superpowers/test-driven-development
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Superpowers completion verification (superpowers-verification)
Superpowers’ verification skill checks which command proves a claim, runs it, reads its full result and reports the result with its actual limits before declaring work complete.

## Use when
- Verify a proposed completion, fix, build or test claim.

## Required inputs
- Change or claim to verify
- Relevant acceptance criteria and validation commands

## Prerequisites
- Ability to run the commands that demonstrate the claimed behavior.
- A passing check only supports the behavior that check actually covers.

## Expected outputs
- Recorded verification results
- Accurate completion status and remaining limitations

Source: https://github.com/obra/superpowers/blob/bb92a77741419a4ab5f06e711a283343f1ada0c3/skills/verification-before-completion/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/superpowers-verification/SKILL.md

## Popularity evidence
- 302,164 GitHub repo stars — obra/superpowers; checked 2026-10-20. Source: https://github.com/obra/superpowers/stargazers
- 246,086 skill installs (all time) — obra/superpowers / verification-before-completion · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/obra/superpowers/verification-before-completion
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Matt Pocock decision interview (matt-pocock-grilling)
Matt Pocock’s grilling skill models an idea as a tree of dependent decisions, asks the currently answerable questions and revisits the remaining branches as the user responds.

## Use when
- Stress-test an implementation plan, design or product decision.

## Required inputs
- Plan or idea to examine
- Known constraints and decision owners

## Prerequisites
- A user available to make the decisions.
- The documented environment-research workflow uses an agent client with subagent dispatch.

## Expected outputs
- Resolved decision tree
- Shared understanding of the proposed work

Source: https://github.com/mattpocock/skills/blob/5beb35b040e3de97e54fa9e386d7e42d15c295c2/skills/productivity/grilling/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/matt-pocock-grilling/SKILL.md

## Popularity evidence
- 297,596 GitHub repo stars — mattpocock/skills; checked 2026-10-20. Source: https://github.com/mattpocock/skills/stargazers
- 948,515 skill installs (all time) — mattpocock/skills / grilling · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/mattpocock/skills/grilling
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Matt Pocock deep module design (matt-pocock-codebase-design)
Matt Pocock’s codebase-design reference defines modules, interfaces, test seams and adapters, then uses depth, leverage and locality to evaluate architecture and testability.

## Use when
- Design a module interface or assess a refactor’s effect on testability.

## Required inputs
- Current module and its consumers
- Behavior, dependency variation and test constraints

## Prerequisites
- Project source and representative consumers.
- Keep DEEPENING.md and DESIGN-IT-TWICE.md; the optional alternative-design exercise needs subagent support.

## Expected outputs
- Proposed interfaces and test seams
- Architecture tradeoffs grounded in callers

Source: https://github.com/mattpocock/skills/blob/5beb35b040e3de97e54fa9e386d7e42d15c295c2/skills/engineering/codebase-design/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/matt-pocock-codebase-design/SKILL.md

## Popularity evidence
- 297,596 GitHub repo stars — mattpocock/skills; checked 2026-10-20. Source: https://github.com/mattpocock/skills/stargazers
- 825,720 skill installs (all time) — mattpocock/skills / codebase-design · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/mattpocock/skills/codebase-design
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Matt Pocock behavioral TDD (matt-pocock-tdd)
Matt Pocock’s TDD reference emphasizes tests through agreed public interfaces, useful assertions, narrow mocking and one behavior slice at a time.

## Use when
- Implement a feature or fix while protecting behavior through public interfaces.

## Required inputs
- Expected behavior and public interfaces
- Project test tools and source

## Prerequisites
- A runnable test suite and agreement on which public interfaces to test.
- Install Matt Pocock’s codebase-design skill for its referenced interface and seam vocabulary.

## Expected outputs
- Behavioral tests at agreed seams
- Incremental implementation and verification

Source: https://github.com/mattpocock/skills/blob/5beb35b040e3de97e54fa9e386d7e42d15c295c2/skills/engineering/tdd/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/matt-pocock-tdd/SKILL.md

## Popularity evidence
- 297,596 GitHub repo stars — mattpocock/skills; checked 2026-10-20. Source: https://github.com/mattpocock/skills/stargazers
- 1,114,501 skill installs (all time) — mattpocock/skills / tdd · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/mattpocock/skills/tdd
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Matt Pocock domain modeling (matt-pocock-domain-modeling)
Matt Pocock’s domain-modeling skill challenges ambiguous terminology and captures domain concepts in GLOSSARY.md and scoped architecture decision records.

## Use when
- Clarify inconsistent business terms or document an evolving domain model.

## Required inputs
- Product domain and existing terminology
- Repository glossary and architecture decisions

## Prerequisites
- Access to the repository and domain knowledge from the decision owner.
- Existing glossary maps and ADRs determine where scoped decisions belong.

## Expected outputs
- Updated domain glossary
- Recorded decisions and edge-case scenarios

Source: https://github.com/mattpocock/skills/blob/5beb35b040e3de97e54fa9e386d7e42d15c295c2/skills/engineering/domain-modeling/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/matt-pocock-domain-modeling/SKILL.md

## Popularity evidence
- 297,596 GitHub repo stars — mattpocock/skills; checked 2026-10-20. Source: https://github.com/mattpocock/skills/stargazers
- 850,687 skill installs (all time) — mattpocock/skills / domain-modeling · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/mattpocock/skills/domain-modeling
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Matt Pocock bug diagnosis (matt-pocock-bug-diagnosis)
Matt Pocock’s diagnosis loop begins with a fast red-capable reproduction, then minimizes it, ranks hypotheses, instruments specific predictions and verifies the final fix.

## Use when
- Investigate a difficult bug or performance regression.

## Required inputs
- Exact reported symptom
- Code, environment and permitted diagnostic tools

## Prerequisites
- Access to an environment or fixture that can reproduce the reported symptom.
- Redact secrets in commands, logs and captured artifacts; retain companion diagnostic scripts.

## Expected outputs
- Minimal reproduction and root cause
- Fix, regression evidence and diagnostic cleanup

Source: https://github.com/mattpocock/skills/blob/5beb35b040e3de97e54fa9e386d7e42d15c295c2/skills/engineering/diagnosing-bugs/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/matt-pocock-bug-diagnosis/SKILL.md

## Popularity evidence
- 297,596 GitHub repo stars — mattpocock/skills; checked 2026-10-20. Source: https://github.com/mattpocock/skills/stargazers
- 810,548 skill installs (all time) — mattpocock/skills / diagnosing-bugs · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/mattpocock/skills/diagnosing-bugs
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Addy Osmani code quality review (addy-osmani-code-review)
Addy Osmani’s code-review skill evaluates a change across five quality dimensions and reports actionable findings in the context of the project’s conventions.

## Use when
- Review a diff, pull request or completed implementation.

## Required inputs
- Diff or commit range
- Project standards and intended behavior

## Prerequisites
- The complete diff and enough surrounding source to understand its effects.
- Repository standards and product requirements remain the review context.

## Expected outputs
- Prioritized review findings
- Quality assessment with relevant verification

Source: https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/skills/code-review-and-quality/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/addy-osmani-code-review/SKILL.md

## Popularity evidence
- 108,660 GitHub repo stars — addyosmani/agent-skills; checked 2026-10-20. Source: https://github.com/addyosmani/agent-skills/stargazers
- 67,892 skill installs (all time) — addyosmani/agent-skills / code-review-and-quality · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/addyosmani/agent-skills/code-review-and-quality
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Addy Osmani application hardening (addy-osmani-security-hardening)
Addy Osmani’s security skill covers web application trust boundaries, authentication, authorization, data handling, dependency findings and external integrations.

## Use when
- Implement or review web features that handle untrusted data or user sessions.

## Required inputs
- Relevant source and data flows
- Threat context and dependency findings

## Prerequisites
- Authorized access to the application source and a permitted test environment.
- A skill-based review does not establish compliance or replace a security assessment.

## Expected outputs
- Concrete hardening changes or findings
- Validation of affected security behavior

Source: https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/skills/security-and-hardening/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/addy-osmani-security-hardening/SKILL.md

## Popularity evidence
- 108,660 GitHub repo stars — addyosmani/agent-skills; checked 2026-10-20. Source: https://github.com/addyosmani/agent-skills/stargazers
- 64,634 skill installs (all time) — addyosmani/agent-skills / security-and-hardening · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/addyosmani/agent-skills/security-and-hardening
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Addy Osmani frontend engineering (addy-osmani-frontend-engineering)
Addy Osmani’s frontend skill connects component architecture, state handling, accessibility, responsive layouts and visual polish with the project’s existing design conventions.

## Use when
- Build or refine production-facing frontend components.

## Required inputs
- UI task and audience needs
- Project source, design tokens and supported viewports

## Prerequisites
- Frontend repository and existing design-system conventions.
- A browser and relevant accessibility checks are required to validate rendered behavior.

## Expected outputs
- Implemented responsive components
- Interaction and accessibility validation

Source: https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/skills/frontend-ui-engineering/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/addy-osmani-frontend-engineering/SKILL.md

## Popularity evidence
- 108,660 GitHub repo stars — addyosmani/agent-skills; checked 2026-10-20. Source: https://github.com/addyosmani/agent-skills/stargazers
- 62,218 skill installs (all time) — addyosmani/agent-skills / frontend-ui-engineering · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/addyosmani/agent-skills/frontend-ui-engineering
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Addy Osmani performance optimization (addy-osmani-performance)
Addy Osmani’s performance guide spans frontend delivery, server execution and database queries, with profiling and measured evidence before prioritizing a fix.

## Use when
- Investigate measured slowness or a known performance requirement.

## Required inputs
- Workload and performance symptoms
- Source, profiles and target performance budget

## Prerequisites
- A reproducible workload and access to the relevant profiling tools.
- Field performance data needs its own measurement source; this skill provides no live metrics.

## Expected outputs
- Evidence-backed optimization changes
- Comparable before-and-after measurements

Source: https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/skills/performance-optimization/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/addy-osmani-performance/SKILL.md

## Popularity evidence
- 108,660 GitHub repo stars — addyosmani/agent-skills; checked 2026-10-20. Source: https://github.com/addyosmani/agent-skills/stargazers
- 60,118 skill installs (all time) — addyosmani/agent-skills / performance-optimization · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/addyosmani/agent-skills/performance-optimization
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Addy Osmani documentation and ADRs (addy-osmani-documentation-adrs)
Addy Osmani’s documentation skill records architecture choices, public API changes and operational context so future maintainers can understand the reasoning behind the code.

## Use when
- Record an architectural choice or document a changed public interface.

## Required inputs
- Decision and relevant implementation
- Alternatives, constraints and existing documentation

## Prerequisites
- Accurate project facts and access to the documentation location.
- Use the repository’s existing documentation format and ownership conventions.

## Expected outputs
- Decision record or updated documentation
- Clear context, consequences and references

Source: https://github.com/addyosmani/agent-skills/blob/aeac41d4d005999432bb7312f7ff06383a91d59d/skills/documentation-and-adrs/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/addy-osmani-documentation-adrs/SKILL.md

## Popularity evidence
- 108,660 GitHub repo stars — addyosmani/agent-skills; checked 2026-10-20. Source: https://github.com/addyosmani/agent-skills/stargazers
- 58,973 skill installs (all time) — addyosmani/agent-skills / documentation-and-adrs · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/addyosmani/agent-skills/documentation-and-adrs
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Emil Kowalski design engineering (emil-design-engineering)
Emil Kowalski’s design-engineering skill describes his approach to UI polish, component design, animation decisions and the interaction details that make software feel considered.

## Use when
- Refine a working interface or discuss concrete design-engineering decisions.

## Required inputs
- Specific interface task or question
- Screenshots, source and interaction constraints

## Prerequisites
- A concrete question or interface task; invoking the skill without one only starts a conversation.
- Source and browser access are needed to implement and verify changes.

## Expected outputs
- Design-engineering recommendations
- Relevant component or interaction changes

Source: https://github.com/emilkowalski/skills/blob/2d228630ba1446365f614a108cb8252f1feda202/skills/emil-design-eng/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/emil-design-engineering/SKILL.md

## Popularity evidence
- 47,710 GitHub repo stars — emilkowalski/skills; checked 2026-10-20. Source: https://github.com/emilkowalski/skills/stargazers
- 367,700 skill installs (all time) — emilkowalski/skills / emil-design-eng · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/emilkowalski/skills/emil-design-eng
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Emil Kowalski animation review (emil-animation-review)
Emil Kowalski’s focused animation-review skill evaluates motion craft and performance, reporting specific issues rather than reviewing unrelated application code.

## Use when
- Review an animation implementation or motion-related diff.

## Required inputs
- Animation code and rendered behavior
- Interaction intent and supported devices

## Prerequisites
- Animation source and a runnable example or recording.
- Explicitly invoke this review skill; meaningful performance claims require device or browser measurements.

## Expected outputs
- Concrete motion review findings
- Specific fixes and validation criteria

Source: https://github.com/emilkowalski/skills/blob/2d228630ba1446365f614a108cb8252f1feda202/skills/review-animations/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/emil-animation-review/SKILL.md

## Popularity evidence
- 47,710 GitHub repo stars — emilkowalski/skills; checked 2026-10-20. Source: https://github.com/emilkowalski/skills/stargazers
- 238,628 skill installs (all time) — emilkowalski/skills / review-animations · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/emilkowalski/skills/review-animations
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Emil Kowalski animation vocabulary (emil-animation-vocabulary)
Emil Kowalski’s animation-vocabulary skill is a reverse glossary for naming motion effects so a developer or designer can describe the intended interaction more precisely.

## Use when
- Name a motion effect from a description or example.

## Required inputs
- Description, reference or recording of the motion

## Prerequisites
- A specific motion description or reference.
- This is a naming reference, not an animation implementation or performance test.

## Expected outputs
- Matching animation terms
- Brief definitions and distinctions

Source: https://github.com/emilkowalski/skills/blob/2d228630ba1446365f614a108cb8252f1feda202/skills/animation-vocabulary/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/emil-animation-vocabulary/SKILL.md

## Popularity evidence
- 47,710 GitHub repo stars — emilkowalski/skills; checked 2026-10-20. Source: https://github.com/emilkowalski/skills/stargazers
- 222,546 skill installs (all time) — emilkowalski/skills / animation-vocabulary · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/emilkowalski/skills/animation-vocabulary
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# UI Skills baseline interface review (ibelick-baseline-ui)
Ibelick’s baseline-ui skill applies opinionated React and Tailwind interface constraints, preferring existing accessible primitives and consistent interaction patterns.

## Use when
- Clean up a React/Tailwind interface or review a targeted UI file.

## Required inputs
- UI source and existing component conventions
- Scope of the requested polish pass

## Prerequisites
- A compatible frontend stack and project source.
- The guide prefers Tailwind, cn utilities, accessible primitives and motion/react when JavaScript motion is needed.

## Expected outputs
- Quoted UI violations and rationale
- Targeted implementation suggestions

Source: https://github.com/ibelick/ui-skills/blob/747a47fdb6b405e5cbf268f7c410123930455157/skills/baseline-ui/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/ibelick-baseline-ui/SKILL.md

## Popularity evidence
- 9,877 GitHub repo stars — ibelick/ui-skills; checked 2026-10-20. Source: https://github.com/ibelick/ui-skills/stargazers
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# UI Skills accessibility fixes (ibelick-accessibility)
Ibelick’s accessibility skill gives targeted HTML and interaction review rules for controls, forms, dialogs and other focus-sensitive interfaces.

## Use when
- Review or fix accessibility in an interactive frontend component.

## Required inputs
- Rendered control and source
- Expected keyboard and assistive-technology behavior

## Prerequisites
- Access to the rendered UI and relevant source.
- Use browser, keyboard and assistive-technology checks where appropriate; the skill alone is not a conformance certification.

## Expected outputs
- Specific accessibility findings
- Targeted fixes and interaction checks

Source: https://github.com/ibelick/ui-skills/blob/747a47fdb6b405e5cbf268f7c410123930455157/skills/fixing-accessibility/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/ibelick-accessibility/SKILL.md

## Popularity evidence
- 9,877 GitHub repo stars — ibelick/ui-skills; checked 2026-10-20. Source: https://github.com/ibelick/ui-skills/stargazers
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# UI Skills motion performance (ibelick-motion-performance)
Ibelick’s motion-performance skill reviews CSS and JavaScript animation for layout thrashing, scroll-linked work, filters and measurement patterns within the existing stack.

## Use when
- Investigate a stuttering animation or review motion-related source.

## Required inputs
- Animation code and performance symptoms
- Target device and available profiling evidence

## Prerequisites
- A runnable animation and its source.
- Browser or device profiling is required to confirm improvements; no library migration is implied.

## Expected outputs
- Concrete motion-performance findings
- Targeted fixes and follow-up measurements

Source: https://github.com/ibelick/ui-skills/blob/747a47fdb6b405e5cbf268f7c410123930455157/skills/fixing-motion-performance/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/ibelick-motion-performance/SKILL.md

## Popularity evidence
- 9,877 GitHub repo stars — ibelick/ui-skills; checked 2026-10-20. Source: https://github.com/ibelick/ui-skills/stargazers
Adoption counts are not user ratings or guarantees of quality.

Selection brief

# Vercel agent-browser automation (vercel-agent-browser)
Vercel’s agent-browser skill is a discovery entry for the browser automation CLI. Its current stub loads the actual usage guide from the installed CLI so the workflow matches that version.

## Use when
- Automate or inspect a website in an authorized browser workflow.

## Required inputs
- Target URL and authorized task
- Browser session and any required application access

## Prerequisites
- Node.js 24 or later, the agent-browser CLI and its browser binaries.
- The pinned SKILL.md is a discovery stub: run agent-browser skills get core to load the actual workflow; follow upstream setup before use.

## Expected outputs
- Browser task results
- Relevant screenshots or observed interaction evidence

Source: https://github.com/vercel-labs/agent-browser/blob/5ee8691339a5a002e4d7454eec95250253bc7419/skills/agent-browser/SKILL.md
Full SKILL.md: https://agenttaste.dev/skills/vercel-agent-browser/SKILL.md

## Popularity evidence
- 44,278 GitHub repo stars — vercel-labs/agent-browser; checked 2026-10-20. Source: https://github.com/vercel-labs/agent-browser/stargazers
- 1,179,586 skill installs (all time) — vercel-labs/agent-browser / agent-browser · skills.sh · all time; checked 2026-10-20. Source: https://skills.sh/vercel-labs/agent-browser/agent-browser
- 7,102,587 npm package downloads — agent-browser · 2026-09-19 – 2026-10-18; checked 2026-10-20. Source: https://api.npmjs.org/downloads/point/2026-09-19:2026-10-18/agent-browser
Adoption counts are not user ratings or guarantees of quality.