Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
developing-claude-code-plugins
Use when working on Claude Code plugins (creating, modifying, testing, releasing, or maintaining) - provides streamlined workflows, patterns, and examples for the complete plugin lifecycle
majiayu000/claude-skill-registry 163
-
otp-thinking
This skill should be used when the user asks to "add background processing", "cache this data", "run this async", "handle concurrent requests", "manage state across requests", "process jobs from a queue", "this GenServer is slow", or mentions GenServer, Supervisor, Agent, Task, Registry, DynamicSupervisor, handle_call, handle_cast, supervision trees, fault tolerance, "let it crash", or choosing between Broadway and Oban.
majiayu000/claude-skill-registry 163
-
eval-harness
Frozen evaluation harness that gates self-improvement with benchmarks, regressions, and human approval loops.
majiayu000/claude-skill-registry 163
-
gh-grep
Search real-world code examples across millions of GitHub repositories using grep.app. This skill should be used when looking for implementation patterns, API usage examples, library integration patterns, or production code references. Supports literal code search, regex patterns, and filtering by language/repo/path.
majiayu000/claude-skill-registry 163
-
security-secrets
Review secret detection patterns and scanning workflows. Use for identifying high-signal secrets like AWS keys, GitHub tokens, and DB passwords. Use proactively during all security audits to scan code and history.
Examples:
- user: "Scan for secrets in this repo" → run high-signal rg patterns and gitleaks
- user: "Check for AWS keys" → scan for AKIA patterns and server-side exposure
- user: "Audit my .env files" → ensure secrets are gitignored and not committed
- user: "Verify secret redaction" → check that reported secrets follow 4+4 format
- user: "Scan build artifacts for keys" → search dist/ and build/ for secret patterns
majiayu000/claude-skill-registry 163
-
debate-simulator
majiayu000/claude-skill-registry 163
-
cache-clear
Clear cache entries based on filters (all, expired, pattern).
Delegates to fractary CLI for safe cache operations with dry-run support.
majiayu000/claude-skill-registry 163
-
android-keystore-generation
Generate production and local development keystores for Android release signing
majiayu000/claude-skill-registry 163
-
technical-doc-creator
Create HTML technical documentation with code blocks, API workflows, system architecture diagrams, and syntax highlighting. Use when users request technical documentation, API docs, API references, code examples, or developer documentation.
majiayu000/claude-skill-registry 163
-
mcu-embedded-review
Reviews embedded Rust firmware for RP2350 (Raspberry Pi Pico 2 W) and ESP32-S3 (Heltec) microcontrollers with focus on Embassy async runtime, memory constraints, LED control, CAN attachment protocols, and SLCAN bridging. Use when reviewing MCU firmware changes, debugging LED controller issues, evaluating Embassy async patterns, checking static memory allocation, validating SLCAN implementations, or assessing hardware-specific code for WS2812 LEDs, CAN peripherals, and tool attachments. Covers no_std environments, PIO state machines, RMT peripherals, and USB CDC serial communication.
majiayu000/claude-skill-registry 163
-
unity-csharp-editing-akiojin-unity-mcp-server
majiayu000/claude-skill-registry 163
-
pr-workflow
This skill should be used when user asks to "create a PR", "make a pull request", "open PR for this branch", "submit changes as PR", "push and create PR", or runs /create-pr or /pr-creator commands.
majiayu000/claude-skill-registry 163
-
Git Workflow with Conventional Commits
Automated Git workflow including staging, committing with Conventional Commits format, PR creation, and merging. Use when committing changes, creating PRs, or managing Git branches.
majiayu000/claude-skill-registry 163
-
safe-edit
Automatically backs up files, saves diffs, uses agents/skills, and ensures modular code (<200 lines) before any implementation. Use this skill for ALL code changes to ensure safe, reversible, and clean implementations.
majiayu000/claude-skill-registry 163
-
agent-debugger
Expert debugger specializing in complex issue diagnosis, root cause analysis, and systematic problem-solving. Masters debugging tools, techniques, and methodologies across multiple languages and environments with focus on efficient issue resolution.
majiayu000/claude-skill-registry 163
-
forensic-surgeon
Deep forensic debugging that never stops until root cause is found or visibility limit is proven. Use when user wants to understand exactly why something is broken, not work around it. Activates on "why is this happening", "dig deeper", "don't work around it", "I want to understand", "find the root cause", "this seems suspicious", or when a problem suggests deeper breakage.
majiayu000/claude-skill-registry 163
-
link-validation
Universal link validation using lychee for Claude Code sessions. Runs at session end to detect broken links and path policy violations.
majiayu000/claude-skill-registry 163
-
qlty-check
Code quality checks, formatting, and metrics via qlty CLI
majiayu000/claude-skill-registry 163
-
ordercli
Foodora-only CLI for checking past orders and active order status (Deliveroo WIP).
majiayu000/claude-skill-registry 163
-
tmf-mcp-builder
Build TM Forum (TMF) MCP servers from TMF OpenAPI specs (TMF6xx/7xx YAML). Use when you are given a TMF OpenAPI file and asked to (1) implement an MCP server exposing TMF operations as tools, (2) generate a mock TMF API server + client + MCP layer, or (3) standardize tool naming, create/update inputs, $ref/allOf handling, and /hub event-subscription patterns for TMF APIs.
majiayu000/claude-skill-registry 163
-
multi-repository-orchestrator
Coordinate development workflows across multiple Git repositories with synchronized branching, batch commits, cross-repo operations, and monorepo-like workflows for microservices and multi-package projects.
majiayu000/claude-skill-registry 163
-
prompt-engineer
Use this skill when creating, improving, or optimizing prompts for Claude. Applies Anthropic's best practices for prompt engineering including clarity, structure, consistency, hallucination reduction, and security. Useful when users request help with writing prompts, improving existing prompts, reducing errors, increasing consistency, or implementing specific techniques like chain-of-thought, multishot prompting, or XML structuring.
majiayu000/claude-skill-registry 163
-
qcc-debug
Use for debugging, troubleshooting, and diagnosing issues in qcc_plus project
majiayu000/claude-skill-registry 163
-
doc-prd
Create Product Requirements Documents (PRD) following SDD methodology - Layer 2 artifact defining product features and user needs
majiayu000/claude-skill-registry 163