Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
zapier-workflows
Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to "run" any process. Also handles Perplexity-based research and Google Sheets data tracking.
majiayu000/claude-skill-registry 163
-
field-playbooks
Use when operationalizing regional/field events with consistent playbooks and follow-up motions.
majiayu000/claude-skill-registry 163
-
lookalike-customer-finder
Input your best customers and find 100+ companies that match the profile. Uses firmographic data, tech stack, growth signals, and similarity scoring to identify ideal prospects. Use when building target account lists or expanding to new markets.
majiayu000/claude-skill-registry 163
-
github-pr-utils
Utility scripts for GitHub pull request management. Includes tools for fetching bot-generated review comments (linters, security scanners, dependabot), replying to review threads programmatically, listing merged pull requests with filtering, resolving conversations, and automating PR review workflows. Useful for batch processing comments, CI/CD integration, quality metrics tracking, release notes generation, and automated responses to bot reviewers.
majiayu000/claude-skill-registry 163
-
component-refactor-planner
指定されたコンポーネントのリファクタリングを設計する。
majiayu000/claude-skill-registry 163
-
propagate-req-keys
Homeostatic actuator that tags code, tests, and commits with REQ-* keys for traceability. Adds "# Implements:" tags to code and "# Validates:" tags to tests. Use when code or tests are missing requirement tags.
majiayu000/claude-skill-registry 163
-
matlab
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
majiayu000/claude-skill-registry 163
-
pytorch-lightning
Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
majiayu000/claude-skill-registry 163
-
markdown-quality
Use when creating or editing any markdown file (.md) - ensures consistent formatting and zero linting violations through mandatory validation
majiayu000/claude-skill-registry 163
-
sentry-sdk-patterns
Execute best practices for using Sentry SDK in TypeScript and Python.
Use when implementing error handling patterns, structuring Sentry code,
or optimizing SDK usage.
Trigger with phrases like "sentry best practices", "sentry patterns",
"sentry sdk usage", "sentry code structure".
majiayu000/claude-skill-registry 163
-
jomonsho-repo-map
Jomonsho の主要ファイル・層・入口の早見表。
majiayu000/claude-skill-registry 163
-
copilot-customization
GitHub Copilotカスタマイゼーションファイル（プロンプト、エージェント、インストラクション、スキル）の作成ガイド。.prompt.md、.agent.md、.instructions.md、SKILL.mdファイルをVS Codeのベストプラクティスに従って作成する際に使用してください。
majiayu000/claude-skill-registry 163
-
babel-config-builder
Generate Babel configuration files for JavaScript/TypeScript transpilation with presets and plugins. Triggers on "create babel config", "generate babel configuration", "babel setup", "transpilation config".
majiayu000/claude-skill-registry 163
-
moai-platform-convex
Convex real-time backend specialist covering TypeScript-first reactive patterns, optimistic updates, and server functions. Use when building real-time collaborative apps.
majiayu000/claude-skill-registry 163
-
xcode-file-manager
Add Swift files to the AIQ Xcode project. Use when creating new Swift files (views, view models, services, models, tests) that need to be added to the Xcode project and build targets.
majiayu000/claude-skill-registry 163
-
install-skill-tracker
This skill installs a complete Claude Code skill tracking system using hooks to automatically log skill usage, execution duration, token usage, and user prompts for later analysis. Use this skill when setting up activity tracking in a Claude Code project to identify patterns, monitor costs, and discover opportunities for new skills.
majiayu000/claude-skill-registry 163
-
nix-devenv
Expert at creating Nix flakes with flake-parts for development environments. Invoked when users want to set up devShells, configure nix-direnv, create flake.nix files, or build reproducible development environments. Specializes in Python, Node.js, and Rust projects using the flake-parts modular architecture.
majiayu000/claude-skill-registry 163
-
prompt-testing-evaluation
プロンプトのテスト、評価、反復改善を専門とするスキル。A/Bテスト、評価メトリクス、自動化されたプロンプト品質保証により、本番環境で信頼性の高いプロンプトを実現します。
Anchors:
• Test-Driven Development: By Example (Kent Beck) / 適用: Red-Green-Refactorサイクル / 目的: 反復的な品質改善
• LLM-as-a-Judge pattern / 適用: 自動評価とスコアリング / 目的: スケーラブルな品質評価
• A/B Testing for AI Systems / 適用: プロンプト比較実験設計 / 目的: データドリブンな改善
Trigger:
Use when testing prompts, evaluating prompt quality, running A/B tests on prompts, implementing automated prompt evaluation, or establishing continuous prompt improvement cycles.
Keywords: prompt testing, A/B testing, evaluation metrics, LLM-as-a-judge, prompt quality, automated evaluation, regression testing
majiayu000/claude-skill-registry 163
-
when-optimizing-agent-learning-use-reasoningbank-intelligence
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement
majiayu000/claude-skill-registry 163
-
expert-routing
majiayu000/claude-skill-registry 163
-
proof-packet-generation
Generate cryptographic proof packets for verification.
majiayu000/claude-skill-registry 163
-
stack-analyzer
Analyze project stack and recommend skills. Auto-detects frameworks, activates generic ai-dev-kit skills, and optionally scaffolds project-specific skills in the target repo.
majiayu000/claude-skill-registry 163
-
mockery-generate
统一使用 mockery + go:generate 为 Golang 接口生成 Mock，禁止手写 mock 结构体；在实现或编写单测时需要为接口创建 mock 时启用本 Skill。
majiayu000/claude-skill-registry 163
-
ring:pre-dev-subtask-creation
Gate 8: Zero-context implementation steps - 2-5 minute atomic subtasks with
complete code, exact commands, TDD pattern. Large Track only.
majiayu000/claude-skill-registry 163