Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
elixir-root-cause-only
MANDATORY systematic debugging - trace to root cause before proposing fixes. NO random changes, NO symptom fixes, NO "try this". Use when debugging ANY error or issue.
majiayu000/claude-skill-registry 163
-
dead-code-detector
Identify unused code, imports, variables, and functions for safe removal.
majiayu000/claude-skill-registry 163
-
hybrid-search-implementation
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
majiayu000/claude-skill-registry 163
-
go-modules
Go modules and dependency management
majiayu000/claude-skill-registry 163
-
figma-to-page
Generates React code for a full page based on pasted Figma 'Inspect' details. Uses the page scaffolder.
majiayu000/claude-skill-registry 163
-
autonomous-skill
Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Claude Code headless mode with auto-continuation. Trigger phrases: "autonomous", "long-running task", "multi-session", "自主执行", "长时任务", "autonomous skill".
majiayu000/claude-skill-registry 163
-
modules-readme-updater
Update the README.md file to list all available journal modules under the Features section. Use when adding, removing, or reorganizing modules and keeping documentation in sync.
majiayu000/claude-skill-registry 163
-
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
majiayu000/claude-skill-registry 163
-
parallel-subagent-driven-development
Use when executing decomposed plans with parallel batches - dispatches up to 2 fresh subagents per batch with code review between batches, enabling fast parallel iteration with quality gates
majiayu000/claude-skill-registry 163
-
error-recovery
Consistent error patterns, validation approaches, and recovery strategies. Use when implementing input validation, designing error responses, handling failures gracefully, or establishing logging practices. Covers operational vs programmer errors, user-facing vs internal errors, and recovery mechanisms.
majiayu000/claude-skill-registry 163
-
execution
Implement approved plans into production-ready code. Use when user wants to build, implement, code, or execute an approved plan. Activates when user says 'let's build', 'implement this', 'start coding', or 'execute the plan'.
majiayu000/claude-skill-registry 163
-
unity-editor
Remote control Unity Editor via CLI using unityctl. Use when working with Unity projects to enter/exit play mode, compile scripts, view console 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.
majiayu000/claude-skill-registry 163
-
docker-build-push-action
GitHub ActionsでのDockerビルド/プッシュを設計・実装するスキル。
レジストリ認証、キャッシュ戦略、マルチプラットフォーム対応を整理する。
Anchors:
• docker/build-push-action / 適用: ビルドとプッシュ / 目的: 自動化
• BuildKit / 適用: キャッシュ最適化 / 目的: ビルド高速化
• Registry Authentication / 適用: 認証設計 / 目的: 安全な配布
Trigger:
Use when configuring GitHub Actions for Docker build and push, managing registry auth, or optimizing BuildKit cache.
docker build push action, buildx, registry auth, github actions docker
majiayu000/claude-skill-registry 163
-
autonomous-ci
Ensures Claude verifies both local tests AND remote CI before claiming completion. Use BEFORE any completion claims, commits, or pull requests. Mandatory verification with evidence.
majiayu000/claude-skill-registry 163
-
mcp-server-builder
Build Model Context Protocol (MCP) servers with best practices. Generate production-ready MCP servers in Python or TypeScript with tools, resources, and prompts.
majiayu000/claude-skill-registry 163
-
deployment-verifier
Enforce comprehensive deployment verification after deploying code, scripts, or configurations. Use after any deployment, build, or installation operation. Prevents deployment verification failures (FP-9).
majiayu000/claude-skill-registry 163
-
exercise-designer
Designs deliberate practice exercises applying evidence-based learning strategies like retrieval practice, spaced repetition, and interleaving. Activate when educators need varied exercise types (fill-in-blank, debug-this, build-from-scratch, extend-code, AI-collaborative) targeting learning objectives with appropriate difficulty progression. Creates exercise sets that apply cognitive science principles to maximize retention and skill development. Use when designing practice activities for Python concepts, creating homework assignments, generating problem sets, or evaluating exercise quality.
majiayu000/claude-skill-registry 163
-
hook-generator
Creates and configures Claude Code hooks for event-driven automation. Activates when user wants to automate tasks, create event handlers, add formatting/logging/notifications, or ensure deterministic behaviors. Updates settings.json safely with hook configurations. Use when user mentions "create hook", "automate", "on save", "pre/post tool", "notification", "formatting hook", or wants always-on behaviors.
majiayu000/claude-skill-registry 163
-
gpu-parallel-scheduling
GPU-safe parallel processing patterns for KINTSUGI to prevent OOM crashes and ensure Jupyter-compatible progress output
majiayu000/claude-skill-registry 163
-
code-searcher
Delegates codebase searches to a lightweight agent. Use when searching for existing implementations, classes, or functions without loading search results into context.
majiayu000/claude-skill-registry 163
-
two-agent-harness
This skill sets up a complete two-agent development system based on the "Effective Harnesses for Long-Running Agents" research. It creates initializer-agent (for project planning) and coding-agent (for incremental implementation), along with enforcement hooks and progress tracking infrastructure. Use when users ask to "set up two-agent system", "install agent harness", "configure Opus delegation", or want to implement the two-agent architecture pattern.
majiayu000/claude-skill-registry 163
-
payload-collections
Use when designing, creating, or modifying Payload CMS collections in db.sb - covers field patterns, relationships, hooks, access control, and how collections map to Nouns in the business-as-code system
majiayu000/claude-skill-registry 163
-
google-workspace
Manage Google Calendar and Gmail through Python code execution. Trigger keywords include calendar, gmail, meeting, email, schedule, event.
majiayu000/claude-skill-registry 163
-
channel-name-parsing
Multi-format channel name parsing for KINTSUGI CHANNELNAMES.txt files
majiayu000/claude-skill-registry 163