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. 86 696 files from 2 113 authors, of which 68 413 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.
CC-DevFlow workflow router and agent recommender. Use when starting requirements, running flow commands, or asking about devflow processes.
Real-time Constitution compliance checker for devflow documents. Blocks partial implementations and hardcoded secrets during file editing.
Quick reference guide to CC-DevFlow Constitution v2.0.0 with links to full text. Covers all 10 Articles and Phase -1 Gates.
File naming conventions, directory structure, and YAML frontmatter standards for CC-DevFlow. Consolidates shared conventions from all agents.
Enforces TDD order in TASKS.md - Tests MUST be marked complete before Implementation tasks. Blocks violations in real-time.
文件头三行契约注释。触发：create file、新建文件、编写代码。
注意力刷新协议。在关键时刻强制读取核心文档，防止目标遗忘。被 flow-dev, flow-ralph 等命令引用。
在 /flow-init 阶段强制触发，用于捕捉需求的原始意图、探索方案、记录决策。确保后续流程有明确的北极星可追溯。
4-phase systematic debugging for flow-fix. NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.
Decide how to complete a development branch: merge, PR, squash, or cleanup.
Handle code review feedback with technical rigor. Don't blindly agree - verify before implementing.
Enforces TDD Iron Law in flow-dev. NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST.
目录级 CLAUDE.md 生成。触发：mkdir、create directory、目录结构变更。
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Remote control Unity Editor via CLI using unityctl. Use when working with Unity projects to launch/stop editor, enter/exit play mode, compile scripts, view logs, load scenes, run tests, capture screenshots, or execute C# code for debugging. Activate when user mentions Unity, play mode, compilation, or needs to interact with a running Unity Editor.
> Pedantic backend pre-commit and atomic commit Skill for Django/Optimo-style repos. Enforces local AGENTS.md / CLAUDE.md, pre-commit hooks, .security/* helpers, and Monty’s backend engineering taste – with no AI signatures in commit messages.
> Pedantic Diversio backend dev workflow Skill that enforces ClickUp-linked branch/PR naming, PR hygiene, safe Django migrations, and downtime-safe schema changes for Django4Lyfe-style backends.
> Create a structured plan directory with Ralph Wiggum Loop integration for backend Django projects. Generates PLAN.md (task index), task files, and RALPH-PROMPT.md (the actual prompt for ralph-loop). Use for rigorous, iterative implementation requiring quality gates and verification.
> Generate comprehensive API endpoint documentation from Bruno (.bru) files by mapping requests to a Django4Lyfe/Diversio-style backend implementation (Django REST Framework or Django Ninja), including auth/permissions, multi-tenant filtering, request/response schemas, and line-numbered code references. Use for single endpoints, directory scans of .bru files, or when writing docs to a specific output path.
> Generates weekly code-review digest docs from PR review comments for any GitHub repository. If present, follows project-specific docs/review-digests/AGENTS.md guidelines. Use this to turn a date-bounded set of PR reviews into a structured markdown “newsletter” that captures themes, repeated issues, and concrete takeaways.
> MixPanel analytics tracking implementation and review Skill for Django4Lyfe optimo_analytics module. Implements new events following established patterns and reviews implementations for PII protection, schema design, and code quality.
> Hyper-pedantic code review skill that emulates Monty's Django4Lyfe backend engineering philosophy and review style. Use this when reviewing or refactoring Python/Django code in this backend repo and you want a strict, correctness-first, multi-tenant-safe, deeply nitpicky review.
> Create or update a structured plan directory with a master PLAN.md index and numbered task files (001-*.md). Each task file includes goal, dependencies, scope, checklist, tests, and completion criteria. Use when scaffolding a repeatable project plan in markdown, especially when the user wants a master index plus per-task files with checkboxes that are checked off as work completes.
> Generates comprehensive, reviewer-friendly PR descriptions with visual diagrams, summary tables, collapsible sections, and structured test plans. Optimized for readability without sacrificing detail.
> Process code review findings interactively - fix or skip issues from monty-code-review output. Presents issues in severity order, applies fixes, runs quality checks, and updates review documents with status markers.
Expert guidance for Prisma ORM v7 (7.0+). Use when working with Prisma schema files, migrations, Prisma Client queries, database setup, or when the user mentions Prisma, schema.prisma, @prisma/client, database models, or ORM. Covers ESM modules, driver adapters, prisma.config.ts, Rust-free client, and migration from v6.
Generates RBS-inline type annotations directly in Ruby source files as comments. Triggers when adding inline type signatures, annotating Ruby methods with rbs-inline syntax, or generating type comments without existing inline annotations.
Generates RBS type signatures from Ruby source files. Triggers when creating type definitions, adding types to Ruby code, or generating .rbs files for classes/modules without existing RBS signatures.
Generates Sorbet inline type signatures using sig blocks directly in Ruby source files. Triggers when adding Sorbet types, annotating Ruby methods with sig syntax, or generating type signatures for Sorbet-typed projects.
Generates Sorbet type signatures in separate RBI files from Ruby source files. Triggers when creating type definitions, adding types to Ruby code, or generating .rbi files for classes/modules without existing Sorbet signatures.
Transform rough ideas into detailed designs through structured dialogue. Use before implementation to refine requirements.
Execute implementation plans with batch processing and review checkpoints. Use when given a plan document.
Dispatch multiple agents to work on independent problems concurrently. Use when facing 3+ independent failures or tasks.
Request and process code reviews with proper context. Use after completing significant implementation work.
Execute plans using fresh subagent per task with code review between tasks. Use for high-quality iterative implementation.
Four-phase root cause investigation before attempting fixes. Use when debugging bugs, test failures, or unexpected behavior.
Enforce RED-GREEN-REFACTOR cycle. Use when implementing features, fixing bugs, or writing any production code.
Auto-escalate reasoning depth for complex problems. Use proactively when encountering architecture, debugging, or unfamiliar code.
Create detailed implementation plans with granular tasks. Use before implementing features or complex changes.
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, and hybrid search for distributed AI systems.
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
Implement persistent memory patterns for AI agents using AgentDB - session memory, long-term storage, pattern learning, and context management for stateful agents, chat systems, and intelligent assistants
Train AI agents using AgentDB's 9 reinforcement learning algorithms including Q-Learning, DQN, PPO, and Actor-Critic. Build self-learning agents, implement RL training loops with experience replay, and deploy optimized models to production.
Build semantic vector search systems with AgentDB for intelligent document retrieval, RAG applications, and knowledge bases using embedding-based similarity matching
Optimize AgentDB vector search performance using quantization for 4-32x memory reduction, HNSW indexing for 150x faster search, caching, and batch operations for scaling to millions of vectors.
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
Creates sophisticated workflow cascades coordinating multiple micro-skills with sequential pipelines, parallel execution, conditional branching, and Codex sandbox iteration. Enhanced with multi-model routing (Gemini/Codex), ruv-swarm coordination, memory persistence, and audit-pipeline patterns for production workflows.
Loop 3 of the Three-Loop Integrated Development System. CI/CD automation with intelligent failure recovery, root cause analysis, and comprehensive quality validation. Receives implementation from Loop 2, feeds failure patterns back to Loop 1. Achieves 100% test success through automated repair and theater validation. v2.0.0 with explicit agent SOPs.
Comprehensive PR review using multi-agent swarm with specialized reviewers for security, performance, style, tests, and documentation. Provides detailed feedback with auto-fix suggestions and merge readiness assessment.
Complete feature development lifecycle from research to deployment. Uses Gemini Search for best practices, architecture design, Codex prototyping, comprehensive testing, and documentation generation. Full 12-stage workflow.
Validates that code actually works through sandbox testing, execution verification, and systematic debugging. Use this skill after code generation or modification to ensure functionality is genuine rather than assumed. The skill creates isolated test environments, executes code with realistic inputs, identifies bugs through systematic analysis, and applies best practices to fix issues without breaking existing functionality. This ensures code delivers its intended behavior reliably.
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.
Automate internationalization and localization workflows for web applications with translation, key generation, and library setup
Advanced intent interpretation system that analyzes user requests using cognitive science principles and extrapolates logical volition. Use when user requests are ambiguous, when deeper understanding would improve response quality, or when helping users clarify what they truly need. Applies probabilistic intent mapping, first principles decomposition, and Socratic clarification to transform vague requests into well-understood goals.
Use Claude Code's interactive question tool to gather comprehensive requirements through structured multi-select questions
Rapidly creates atomic, focused skills optimized with evidence-based prompting, specialist agents, and systematic testing. Each micro-skill does one thing exceptionally well using self-consistency, program-of-thought, and plan-and-solve patterns. Enhanced with agent-creator principles and functionality-audit validation. Perfect for building composable workflow components.
Implement machine learning solutions including model architectures, training pipelines, optimization strategies, and performance improvements. This skill spawns a specialist ML implementation agent...
Claude Skills — questions
Answers built from the skills we actually parsed.