Skill Creator
majiayu000
6838 published skills · 19,665 GitHub stars across the catalog. View on GitHub ↗
devops-fullstack
DevOps for fullstack - Docker, CI/CD, deployment, monitoring
generate-story-bank
Generate interview-ready stories using HPARL format (Hook, Principles, Action, Results, Learnings). Transforms achievements into compelling narratives for behavioral interviews.
seo-engineer
Principal SEO Engineer for search-optimized web experiences. Use when implementing technical SEO, optimizing Core Web Vitals, creating structured data, building SEO-friendly architectures, or improving organic search visibility. Covers SSR/SSG strategies, meta tags, schema markup, performance optimization, and evidence-based SEO practices.
github-tools
Executes GitHub operations via gh CLI wrapper. Use when managing issues, pull requests, workflows, CI runs, projects, releases, cache, labels, or searching repositories and code.
qdrant-vectordb
Use when working with Qdrant vector database for semantic search and RAG. Covers collection setup, embedding generation, vector upsert/search, HNSW indexing, filtering, and integration with OpenAI embeddings for textbook content retrieval.
commit-message-rules
Gitコミットメッセージの作成ガイドライン。コミット作成時、`git commit`実行時、またはユーザーがコミットメッセージの書き方について質問した際に使用する。日本語でのコミットメッセージ作成ルールを提供。
ln-112-project-core-creator
Creates 3 core project docs (requirements.md, architecture.md, tech_stack.md). L3 Worker invoked by ln-110-project-docs-coordinator. ALWAYS created.
enforce-contract
單元測試與代碼提交前觸發。掃描並驗證方法的 pre-conditions、post-conditions 與 invariants,透過契約式設計減少 AI 幻覺。
google-gemini-api
Integrate Gemini API with correct current SDK (@google/genai v1.27+, NOT deprecated @google/generative-ai).Supports text generation, multimodal (images/video/audio/PDFs), function calling, and thinking mode. 1M input tokens.Use when: integrating Gemini API, implementing multimodal AI, using thinking mode for reasoning, function callingwith parallel execution, streaming responses, deploying to Cloudflare Workers, building chat, or troubleshootingSDK deprecation, context window, model not found, function calling, or multimodal format errors.Keywords: gemini api, @google/genai, gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite,gemini-3-pro-preview, multimodal gemini, thinking mode, google ai, genai sdk, function calling gemini,streaming gemini, gemini vision, gemini video, gemini audio, gemini pdf, system instructions,multi-turn chat, DEPRECATED @google/generative-ai, gemini context window, gemini models 2025,gemini 1m tokens, gemini tool use, parallel function calling, compositional function ca
adr
Create Architecture Decision Records (ADRs) following project standards. Guides template usage, process, and best practices for documenting architecturally significant decisions.
advanced-types
Advanced TypeScript types including generics, conditionals, and mapped types
openai-agents
Use when integrating OpenAI GPT models for conversational AI. Covers chat completions, streaming responses, function calling, system prompts, token management, cost optimization, error handling, and building specialized agent personas for Physical AI tutoring.
coverport-integration
Integrate coverport into Go repositories with Tekton pipelines to enable e2e test coverage collection and upload to Codecov. Use this skill when users ask to integrate coverport, add e2e coverage tracking, or set up coverage instrumentation for Go projects.
pocketbase-migrations
Comprehensive guide for PocketBase migrations (0.20+) using Go-based migration system. Use when creating or modifying PocketBase collections, managing fields, setting up relations, or writing migration files.
context-setter
Generate comprehensive context-setting markdown files for coding tasks by intelligently exploring codebase and structuring work with ROLE, CONSTRAINTS, STYLE, file reading order, and structured tasks. Use proactively when the user is starting a complex dev task requiring multiple steps or file reads.
fastmcp-builder
Build production-ready MCP servers using FastMCP framework with proven patterns for tools, resources, prompts, OAuth authentication, and comprehensive testing. Use this when creating FastMCP-based MCP servers with features like Google OAuth, multiple resource types, testing with FastMCP Client, or complex tool implementations.
github-actions-ci
GitHub Actions CI/CD guide for the dotfiles repository. Use when creating or modifying GitHub Actions workflows, adding CI/CD pipelines, setting up build/test automation, configuring matrix builds, working with artifacts, implementing E2E tests in containers, or troubleshooting workflow issues. Covers workflow patterns, security best practices, caching strategies, and multi-platform testing.
create-architecture
Generate comprehensive system architecture documents from requirements, supporting Frontend, Backend, and Fullstack projects with scale-adaptive depth and Architecture Decision Records. Use when translating requirements (PRD/epic) into technical architecture for new projects or major features.
org-chart-generator
Generate organizational hierarchy charts from CSV, JSON, or nested data. Supports multiple layouts, department coloring, and PNG/SVG/PDF export.
prism-syntax
Use when adding syntax highlighting for custom languages to Prism.js, used by Docusaurus and many documentation sites
create-extension
Creates a new Starlark MCP extension with tools, handlers, and proper structure. Use when the user wants to add a new extension to the starlark-mcp server.
analogjs-development
Develop with Analogjs 2.x file-based routing, markdown content management, and SSR/SSG configuration. Use when creating *.page.ts files, contentFilesResource, routeMeta, and prerender settings.
plan-execute
Two-phase workflow that generates explicit YAML plan before execution, with approval gates and checkpointing. Use for complex multi-file changes, refactoring, bug fixes with dependencies, or any task where mistakes are costly. Achieves 90% first-pass success rate vs ad-hoc changes. Provides audit trail, rollback capability, and explicit approval points. Triggers on "refactor", "multi-step", "plan then execute", "complex changes", "safe refactoring".
confidence-check
5-check quantitative validation ensuring 90% confidence before implementation. Preventswrong-direction work through systematic verification: duplicate check (25%), architecturecompliance (25%), official docs (20%), working OSS (15%), root cause (15%). Thresholds:≥90% proceed, ≥70% clarify, <70% STOP. Proven 25-250x token ROI from SuperClaude.