Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
codebase-index
Quickly index and understand a codebase's architecture. Use at session start to get up to speed fast. Finds entry points, API routes, classes, models, configs, and patterns.
majiayu000/claude-skill-registry 163
-
trust-reliability
Use when creating animations that build user confidence, establish credibility, and communicate dependability.
majiayu000/claude-skill-registry 163
-
devflow-file-standards
File naming conventions, directory structure, and YAML frontmatter standards for CC-DevFlow. Consolidates shared conventions from all agents.
majiayu000/claude-skill-registry 163
-
lightning-invoice-decoder
Use when implementing BOLT11 Lightning invoice decoding - provides complete patterns for decoding invoice amounts, validating invoice format, and extracting satoshi values from Lightning invoices
majiayu000/claude-skill-registry 163
-
refactor-simplify-branching
[Code Quality] Simplifies complex conditionals: deep nesting, long if-else chains, switch sprawl. Use when control flow is hard to follow or has high cyclomatic complexity.
majiayu000/claude-skill-registry 163
-
github-actions-debugging
GitHub Actionsワークフロー実行時のデバッグとトラブルシューティング。
Anchors:
• Continuous Delivery (Jez Humble) / 適用: パイプライン失敗の診断 / 目的: フィードバックループ短縮
• Site Reliability Engineering (Google) / 適用: ログベース障害分析 / 目的: 体系的エラー診断
Trigger:
Use when debugging failed GitHub Actions workflows, analyzing workflow logs, enabling debug logging, troubleshooting permission/secret/cache/timeout issues, or diagnosing runner environment problems.
Keywords: github actions, workflow error, failed job, ACTIONS_STEP_DEBUG, ACTIONS_RUNNER_DEBUG, permission denied, cache miss, timeout, runner diagnostics
majiayu000/claude-skill-registry 163
-
code-review-assistant
Perform structured, actionable code reviews for Python code with clear findings and suggestions.
majiayu000/claude-skill-registry 163
-
Global Performance
Your approach to handling global performance. Use this skill when working on files where global performance comes into play.
majiayu000/claude-skill-registry 163
-
lcp-git-commit
When asked to commit, write clear git commit messages (50/72, present tense, subsystem prefixes like go-lcpd:).
majiayu000/claude-skill-registry 163
-
web-developer-persistent-context
Advanced persistent context management system for web development work that never loses context between Claude Desktop sessions. Automatically tracks, saves, and restores all work context, session history, decisions, and progress across multiple sessions and projects.
majiayu000/claude-skill-registry 163
-
sonos-control
Control Sonos speakers through MCP tools - search and play music, manage queue and playlists, adjust volume. Use when users request music playback, mention artists/songs/albums, want to control Sonos speakers, manage playlists, or ask about what's playing.
majiayu000/claude-skill-registry 163
-
Gen Alpha Output Style
This skill provides the Gen Alpha/brainrot output style transformation rules and vocabulary. It is automatically loaded by the SessionStart hook to transform all Claude responses into Gen Alpha internet slang. Contains comprehensive glossary, transformation patterns, and examples.
majiayu000/claude-skill-registry 163
-
machine-learning
Supervised/unsupervised learning, model selection, evaluation, and scikit-learn. Use for building classification, regression, or clustering models.
majiayu000/claude-skill-registry 163
-
Global Security
Your approach to handling global security. Use this skill when working on files where global security comes into play.
majiayu000/claude-skill-registry 163
-
warp-grep
Parallel code search with Warp-Grep MCP. Use for codebase discovery, understanding how things work, data flow analysis, or when the user asks "how does X work" about the codebase.
majiayu000/claude-skill-registry 163
-
precommit
Running precommit checks and build validation. ALWAYS use after ANY code changes.
majiayu000/claude-skill-registry 163
-
prototype-planning
Define what to build at what fidelity to learn what you need without over-investing. Use before starting any prototype.
majiayu000/claude-skill-registry 163
-
error-handling-standardizer
Creates consistent error handling with custom error classes, HTTP status mapping, structured logging, safe client messages, and error taxonomy. Use when standardizing "error handling", "logging", "error responses", or "exception management".
majiayu000/claude-skill-registry 163
-
frontend-bugfix
Use this skill when debugging frontend test failures (React/TypeScript, Vitest, etc.), fixing bugs in React/TypeScript code, or following TDD methodology for frontend bug fixes. This skill provides the complete bugfix workflow knowledge including error classification, confidence scoring, and TDD best practices.
majiayu000/claude-skill-registry 163
-
Medical Records
All things needed for interacting with medical records
majiayu000/claude-skill-registry 163
-
fda-database
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
majiayu000/claude-skill-registry 163
-
security-scanner
Automatically scan code for security vulnerabilities when user asks if code is secure or shows potentially unsafe code. Performs focused security checks on specific code, functions, or patterns. Invoke when user asks "is this secure?", "security issue?", mentions XSS, SQL injection, or shows security-sensitive code.
majiayu000/claude-skill-registry 163
-
scanpy
Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use anndata.
majiayu000/claude-skill-registry 163
-
command-best-practices
コマンド設計のベストプラクティス（単一責任/合成可能性/冪等性/DRY/保守性）を整理し、設計レビューと改善方針を支援するスキル。
原則の適用判断、チェックリスト運用、検証手順を一貫して整理する。
Anchors:
• The Pragmatic Programmer (Andrew Hunt, David Thomas) / 適用: 設計原則の実務適用 / 目的: 実装品質の安定化
Trigger:
Use when reviewing command design best practices, refactoring command structure, or validating maintainability and composability.
command best practices, single responsibility, composability, idempotency, DRY, maintainable commands
majiayu000/claude-skill-registry 163