Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
Using Content Driven Development
Apply a Content Driven Development process to AEM Edge Delivery Services development. Use for all development tasks, including building new blocks, modifying existing blocks, making changes to core decoration functionality, etc.
majiayu000/claude-skill-registry 163
-
mlflow-evaluation
MLflow 3 GenAI evaluation for agent development. Use when (1) writing mlflow.genai.evaluate() code, (2) creating @scorer functions, (3) building evaluation datasets from traces, (4) using built-in scorers (Guidelines, Correctness, Safety, RetrievalGroundedness), (5) analyzing traces for latency/errors/architecture, (6) optimizing agent context/prompts/token usage, (7) debugging evaluation failures. Covers the full eval workflow: trace analysis -> dataset building -> scorer creation -> evaluation execution.
majiayu000/claude-skill-registry 163
-
railway-secrets-management
Railwayプラットフォーム上でのシークレット管理を専門とするスキル。環境変数設定、シークレットローテーション、アクセス制御を体系的に支援し、セキュアで運用しやすいデプロイメント環境を実現します。
Anchors:
• Web Application Security (Andrew Hoffman) / 適用: 脅威モデリングとリスク評価 / 目的: セキュアなシークレット管理設計
• Railway Documentation / 適用: Variables API・Service Variables / 目的: Railway固有機能の理解と活用
• The Twelve-Factor App / 適用: 環境変数による設定管理 / 目的: クラウドネイティブな設定パターン
Trigger:
Use when configuring Railway secrets, rotating credentials, designing access control, managing environment-specific variables, or implementing secure secret management practices on Railway platform.
Keywords: railway secrets, environment variables, secret rotation, railway variables api, service variables, railway security, credential management
majiayu000/claude-skill-registry 163
-
agent-build-engineer
Expert build engineer specializing in build system optimization, compilation strategies, and developer productivity. Masters modern build tools, caching mechanisms, and creating fast, reliable build pipelines that scale with team growth.
majiayu000/claude-skill-registry 163
-
granola-data-handling
Data export, retention, and GDPR compliance for Granola.
Use when managing data exports, configuring retention policies,
or ensuring regulatory compliance.
Trigger with phrases like "granola export", "granola data",
"granola GDPR", "granola retention", "granola compliance".
majiayu000/claude-skill-registry 163
-
k-fencore
Context for FenCore - the pure logic library for WoW addons. Covers utility functions, math helpers, table operations, and environment detection. Load this when working with FenCore or needing utility functions. Triggers: fencore, utility, math, table, logic, pure functions.
majiayu000/claude-skill-registry 163
-
write-unit-test
Generate behavioral unit tests from functional specifications using PreDB/PostDB pattern. Use when user provides specs with PreDB/Workflow/PostDB structure or asks to write tests for a specification before implementation (TDD approach).
majiayu000/claude-skill-registry 163
-
context-management
Proactive context window management via token monitoring, intelligent extraction, and selective rehydration.
Use when approaching token limits or needing to preserve essential context.
Complements /transcripts and PreCompact hook with proactive optimization.
majiayu000/claude-skill-registry 163
-
coding-agents
Spawn and control external coding agents (Claude Code, Codex, OpenCode, Pi) for delegating tasks. Use when (1) user asks to run another coding agent, (2) delegating subtasks to a different AI tool, (3) running multiple agents in parallel on separate issues, (4) spawning an agent in an isolated environment or worktree, (5) user mentions "codex", "opencode", "pi agent", or running "another claude".
majiayu000/claude-skill-registry 163
-
team-coordination
Multi-person projects - shared state, todo claiming, handoffs
majiayu000/claude-skill-registry 163
-
agents-md-improver
Keeps repo-local agent instructions consistent by proposing updates to AGENTS.md when a user corrects the coding agent or asks to change AGENTS.md, CLAUDE.md, .claude/CLAUDE.md, or GEMINI.md.
majiayu000/claude-skill-registry 163
-
ray-train
majiayu000/claude-skill-registry 163
-
gemini
Gemini CLI for one-shot Q&A, summaries, and generation.
majiayu000/claude-skill-registry 163
-
formatting-conditional-types
Formatting rules for TypeScript conditional types. Use when writing complex conditional types to ensure debuggable, maintainable formatting with proper alignment.
majiayu000/claude-skill-registry 163
-
railway-api
Railway.com GraphQL API automation for projects, services, deployments, and environment variables. Use when automating Railway operations, querying project data, managing deployments, setting variables via API, or integrating Railway into workflows.
majiayu000/claude-skill-registry 163
-
harness-runner
Run WaveCap-SDR test harness with automated parameter sweeps and validation. Use when regression testing, validating audio quality across configurations, testing SDR hardware, or benchmarking demodulation performance.
majiayu000/claude-skill-registry 163
-
multi-platform-architect
Multi-Platform AI Ecosystem Architect - Master skill for creating ecosystem components across Claude Code, Codex, Auggie, Kilocode, Goose, Gemini-CLI
majiayu000/claude-skill-registry 163
-
security-compliance-automation
majiayu000/claude-skill-registry 163
-
component-refactoring
Refactor high-complexity React components in Dify frontend. Use when `pnpm analyze-component --json` shows complexity > 50 or lineCount > 300, when the user asks for code splitting, hook extraction, or complexity reduction, or when `pnpm analyze-component` warns to refactor before testing; avoid for simple/well-structured components, third-party wrappers, or when the user explicitly wants testing without refactoring.
majiayu000/claude-skill-registry 163
-
when-releasing-software-use-github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management. Coordinates release-manager, cicd-engineer, tester, and docs-writer agents through hierarchical topology to handle semantic versioning, changelog generation, release notes, deployment validation, and post-release monitoring. Supports multiple release strategies (rolling, blue-green, canary) and automated rollback. Use when creating releases, managing deployments, or coordinating version updates.
majiayu000/claude-skill-registry 163
-
docker-hadolint
Docker & Hadolint - Atoll Tourisme. Use when working with Docker or containers.
majiayu000/claude-skill-registry 163
-
Zero-Day Hunting Methodology
Systematic approach to discovering novel vulnerabilities through code analysis, fuzzing, and attack surface research
majiayu000/claude-skill-registry 163
-
quality-detect-refactor-markers
Finds all REFACTOR markers in codebase, validates associated ADRs exist, identifies stale markers (30+ days old), and detects orphaned markers (no ADR). Use during status checks, before feature completion, or for refactor health audits. Works with Python, TypeScript, and JavaScript files.
majiayu000/claude-skill-registry 163
-
book-market-research
Assess commercial viability of book concepts for Amazon KDP self-publishing. Use when the user has a Book Concept Document and wants to understand market demand, competition, pricing, and positioning before committing to write. Produces a Market Research Report with viability scorecard and Go/No-Go recommendation. Works standalone (commercial analysis only) or after idea-validator (integrated assessment). Nonfiction only.
majiayu000/claude-skill-registry 163