Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 404 files from 1 741 authors, of which 61 763 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Knowledge of the Vercel deployment pipeline, hybrid build scripts, and environment configuration.
Code quality standards, linting rules, and CI/CD principles.
Deep dive into the Docusaurus configuration, plugins, and custom fields.
Analyzes prose for grammar errors, style inconsistencies, clarity issues, and readability problems. Provides specific suggestions for improvement while preserving the author's unique voice. Use when the user needs help polishing their writing, improving clarity, or maintaining consistent style.
Best practices and patterns for Next.js App Router, Server Actions, and Routing in this project.
Analyzes narrative plot points, timelines, and story events to identify inconsistencies, plot holes, continuity errors, and pacing issues. Use when the user needs help ensuring their story remains logically consistent and well-paced.
Overview of the project's tech stack, directory structure, and architectural patterns.
Details on the Retrieval Augmented Generation pipeline, Ingestion, and Vector Search.
Assists authors in researching topics, verifying facts, and ensuring accuracy in their writing. Particularly useful for historical fiction, non-fiction, science fiction, and any genre requiring real-world accuracy. Use when the user needs help with research or fact-checking.
Domain knowledge for Physical AI, ROS 2, and Humanoid Robotics.
The Design System, Theme, and UX rules for the Physical AI Hub.
Use AI to merge individual page HTML files into a unified chapter document. Creates continuous document format for improved reading experience and semantic consistency.
Use AI to recreate PDF page as semantic HTML. Consumes three inputs (PNG image, parsed text, ASCII preview) for complete contextual understanding and accurate generation.
Use AI to compare rendered HTML to original PDF page. AI makes contextual judgment about visual accuracy with explainable reasoning. BLOCKING quality gate - stops pipeline if score below 85%.
Use AI to create ASCII text-based preview of PDF page layout. Transforms visual and extracted data into structured ASCII representation for HTML generation.
Check if code is readable by non-developers - clear names, plain English comments, no jargon
Automatically draft commit messages by analyzing git status and staged changes
Create a thoughtful, supportive commit message from your staged changes.
Standardize formatting and apply consistent style to the deliverable. Use after generation to ensure the output matches the user's formatting standards and conventions.
Create the deliverable (code, documentation, tests, content) following the user's standards and best practices. Use after validation passes to actually build the work product.
Validate HTML5 structure and basic syntax. BLOCKING quality gate - stops pipeline if validation fails. Ensures deterministic output quality.
Extract rich data from PDF pages including text spans with metadata, rendered PNG images, and page mapping. Creates persistent artifacts for downstream processing.
Generate comprehensive quality report with metrics and verification. Produces final CHAPTER_XX_VERIFICATION.md and quality_metrics.json for deployment approval.
Verify the final deliverable meets all quality criteria before delivery. Use as the final validation step to ensure the output meets the user's quality standards across all 6 dimensions.
Validate that input meets prerequisites based on the user's saved standards for the project type. Use at the start of any quality pipeline to ensure the user has provided sufficient requirements.
Extract all chapters from an EPUB file into separate markdown files. Use when the user wants to split an EPUB into individual chapter files, extract EPUB chapters, or convert an ebook to separate markdown documents.
System diagnostics using GASP (General AI Specialized Process monitor). Use when user asks about Linux system performance, requests system checks, mentions GASP, asks to diagnose hosts, or says things like "check my system" or "what's wrong with [hostname]". Can actively fetch GASP metrics from hosts via HTTP or interpret provided JSON output.
> misunderstanding requirements, using wrong patterns, forgetting conventions, receiving correction from user, unexpected behavior, or any error situation
Write token-efficient documentation for LLM context. Use when creating CLAUDE.md, README, technical docs, agent instructions, or any documentation consumed by AI assistants.
Clerk for forced surrenders, threats, procedural irregularities, and lack of informed consent; use for Coercion_Duress queue.
Clerk for Crown fiduciary breaches, fund mismanagement, conflicts of interest, and failure to protect reserve lands; use for Fiduciary_Duty_Negligence queue.
Clerk for Chief/Council authority, assertions of title, self-government, and resistance to federal imposition; use for Governance_Sovereignty queue.
Clerk for reserve reduction, trespass, survey errors, and railway takings; use when processing the Land_Reduction_Trespass queue.
Edits and compiles very large Markdown research reports using surgical patches, structure JSON, and legal‑grade citation rules.
Orchestrates Pukaist agents, enforces plan-first workflow, runs integrity tests, and delegates tasks; use for coordination or system audits.
Operates and debugs the local stack (API/worker/frontend); focuses on observability, logs, and safe automation.
Synthesizes provided sources neutrally; separates quotes from paraphrase and avoids ungrounded claims.
Builds and refactors code safely; prefers small diffs, clear validation steps, and testable outcomes.
Clerk for water licenses, irrigation, riparian rights, and fishing restrictions affecting Pukaist/Nlaka'pamux; use for Water_Rights_Fishing queue.
Master Cohere v2 Chat API with Python, specializing in entity extraction using JSON Schema mode for structured outputs. Use when extracting entities from text, building data extraction pipelines, implementing NER systems, or requiring validated JSON responses from LLMs.
Master SurrealDB 2.3.x with Python for multi-model database operations including CRUD, graph relationships, vector search, and real-time queries. Use when working with SurrealDB databases, implementing graph traversal, semantic search with embeddings, or building RAG applications.
Explore and understand the Empathy Ledger codebase architecture, data flows, database schema, services, and how components connect. Use when you need to understand where things are, how data flows, or how different parts of the system relate to each other.
This skill provides comprehensive guidance for reviewing code, features, and content for cultural sensitivity and Indigenous data sovereignty compliance.
AI-powered data analysis for Empathy Ledger. Use when working with themes, quotes, story suggestions, transcript analysis, storyteller connections, or any feature requiring extracted insights. Ensures consistent analysis patterns across the platform.
Design Component skill for Empathy Ledger. Use for storyteller cards, story cards, profile displays, and any UI component requiring cultural sensitivity. Provides data mapping, AI enrichment patterns, and design system guidelines.
Invoke this skill when: - Starting work on any Empathy Ledger feature - Need quick reference to project patterns
This skill provides comprehensive guidance for implementing and reviewing GDPR-compliant features in Empathy Ledger.
Zero-friction local development server management for Empathy Ledger using PM2
Navigate Supabase database tables, relationships, and query patterns. Use when you need to understand how tables connect, write queries, or find the right data source.
Documents and explains the CookMode V2 codebase as it exists. Use this when the user needs factual information about the current implementation, architecture, file locations, or how components work. DOES NOT suggest improvements unless explicitly asked.
Manages Supabase database schema, migrations, and queries for CookMode V2. Use this when the user needs to create/modify tables, write migrations, update RLS policies, or troubleshoot database issues.
Helps add, edit, validate, and manage recipe data in recipes.js. Use this when the user wants to create new recipes, modify existing ones, fix recipe formatting, or validate recipe structure.
AI-friendly architecture patterns for TypeScript projects including Domain-Driven Design, Clean Architecture, Hexagonal Architecture, and Page Object Model testing patterns
Battle-tested code review practices optimizing for codebase health and team velocity
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
Intelligent routing layer that analyzes requests and directs them to the most appropriate Skills, Agents, or Commands
Write effective JSDoc comments for TypeScript code. Provides guidance on documentation format, strategic placement, best practices, and when to document versus when to keep code self-documenting. Helps maintain code clarity and IDE support.
**AI-friendly comprehensive testing guidance for Vitest with practical patterns and behavior-driven development.**
Expert guidance for Google Kubernetes Engine (GKE) operations including cluster management, workload deployment, scaling, monitoring, troubleshooting, and optimization. Use when working with GKE clusters, Kubernetes deployments on GCP, container orchestration, or when users need help with kubectl commands, GKE networking, autoscaling, workload identity, or GKE-specific features like Autopilot, Binary Authorization, or Config Sync.
Write Python code following FiftyOne's official conventions. Use when contributing to FiftyOne, developing plugins, or writing code that integrates with FiftyOne's codebase.
Claude Skills — questions
Answers built from the skills we actually parsed.