Skill Creator
majiayu000
6838 published skills · 19,665 GitHub stars across the catalog. View on GitHub ↗
rollback
Rollback AI agent to a previous version. Use when reverting a deployment, undoing changes, or recovering from failed deploys.
kubernetes-health
Comprehensive Kubernetes cluster health diagnostics using dynamic API discovery. Use when checking cluster health, troubleshooting K8s issues, or running health assessments.
openai-assistants
Build stateful chatbots with OpenAI Assistants API v2 - Code Interpreter, File Search (10k files), Function Calling. ⚠️ Deprecated (sunset August 26, 2026); use openai-responses for new projects.Use when: maintaining legacy chatbots, implementing RAG with vector stores, or troubleshooting "thread has active run", vector store delays, polling timeouts, or file upload errors.
build-run-local
Run local builds with proper environment setup. Use when building code locally to verify changes before pushing.
metaphor-to-protocol-translation
Translate metaphorical descriptions into executable protocols.
css-styling
Write modern, maintainable CSS using best practices for layouts, responsive design, animations, and CSS architecture. Use when styling websites, fixing CSS issues, or implementing designs.
workflow-optimizer
Workflow navigation assistant that recommends next steps and optimizes documentation sequence through the SDD workflow
seo-mastery-jp
包括的なSEO最適化スキル(日本語版)。Googleの公式ガイドラインに基づく技術SEO、コンテンツSEO、構造化データ、Core Web Vitals、E-E-A-T対策を網羅し、実践的なコード生成とサイト監査ワークフローを提供
race-strategy-builder
Generates race-day pacing and fueling strategies with contingency plans. Use when user has an upcoming race, asks for race preparation advice, or wants a printable race-day plan with segment pacing and fueling schedule.
data-engineering
ETL pipelines, Apache Spark, data warehousing, and big data processing. Use for building data pipelines, processing large datasets, or data infrastructure.
wp-security-review
WordPress security audit and vulnerability analysis. Use when reviewing WordPress code for security issues, auditing themes/plugins for vulnerabilities, checking authentication/authorization, analyzing input validation, or detecting security anti-patterns, or when user mentions "security review", "security audit", "vulnerability", "XSS", "SQL injection", "CSRF", "nonce", "sanitize", "escape", "validate", "authentication", "authorization", "permissions", "capabilities", "hacked", or "malware".
task-mover
[Task Mgmt] A Skill that syncs task status in Docs/Task/{StepName}_Task.md by moving tasks between sections (Backlog, Worker1, Worker2, Worker3, Review, Done) with priority-aware management for multi-agent parallel development. AI agent MUST invoke this skill AUTOMATICALLY when (1) starting work on a task - move to assigned Worker, (2) AI completing work - move to Review (NOT Done). CRITICAL - AI CANNOT move to Done or Backlog. Only User/Reviewer can move tasks to Done or Backlog. (user)
java-maven-gradle
Master Maven and Gradle - build configuration, dependencies, plugins, CI/CD
ha-emby-issue-selector
Use when starting work to select the next issue - queries GitHub project board, applies priority logic, and routes to the appropriate workflow (bug-triage or issue-executor).
requirements-clarity-scoring
When gathering requirements during discovery phase to measure answer quality and decide when to proceed.
winget-release
GistGetのWinGetパッケージリリースを支援。(1) 新バージョンのリリース、(2) WinGetマニフェスト作成・更新、(3) winget-pkgsへのPR作成。「WinGetにリリース」「winget-pkgsにPR」「マニフェスト作成」などのキーワードで使用。
vercel-kv
Integrate Redis-compatible Vercel KV for caching, session management, and rate limiting in Next.js applications. Powered by Upstash with strong consistency and TTL support.Use when implementing cache strategies, storing temporary data with expiration, building rate limiters, or troubleshooting missing environment variables, serialization errors, or rate limit issues.
solver-control
Solver kill-switch and progress monitoring for schedule generation. Use when aborting runaway solvers, monitoring long-running schedule generation, or integrating abort checks into solver loops.
product-self-knowledge
Authoritative reference for Anthropic products. Use when users ask about product capabilities, access, installation, pricing, limits, or features. Provides source-backed answers to prevent hallucinations about Claude.ai, Claude Code, and Claude API.
phase-cleanup
Refactor and finalize code after parallel phases complete, addressing technical debt. Use in cleanup phase to polish code before merge.
test-scenario-framework
Define and run end-to-end test scenarios for medical residency scheduling. Use when validating complex scheduling logic, testing edge cases, verifying ACGME compliance under stress, or running regression scenarios. Includes 20+ pre-built scenarios covering N-1 failures, multi-swap operations, holiday conflicts, and moonlighting.
propose-implementation-plan
Create an implementation plan with atomic commits that build toward a complete feature
doc-validation-framework
Expert methodology for systematically validating the quality, accuracy, and freshness of any technical document. Use when user requests document validation, checklist generation, documentation quality assurance, or needs to verify claims in technical documentation. Generates comprehensive validation checklists with 80-150 items organized by domain and criticality.
home-assistant
This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.