Search Skills
Find the perfect capability for your agent.
web-search
Web research and literature search capabilities for external resources. LOAD THIS SKILL WHEN: User says "搜尋", "search", "找資料", "查詢", "檢索", "web search", "網路搜尋" | needs external documentation | research task | API reference lookup | technology comparison | wants latest information. CAPABILITIES: Technical docs (MDN, GitHub, Stack Overflow), academic papers (PubMed integration), API documentation, real-time web data via fetch_webpage, structured search results.
obsidian-vault
Vault structure, file naming, frontmatter, and linking conventions. Use when: "vault structure", "file naming", "frontmatter", "wiki links", "obsidian conventions".
latex-compilation
Use when LaTeX documents fail to compile, have undefined references, duplicate labels, or citation errors
open-source-librarian
Research external libraries with evidence-backed responses and GitHub permalinks. Use when investigating library APIs, implementation patterns, or historical context for open source dependencies.
docs-seeker
Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration. Use when user needs: (1) Latest documentation for libraries/frameworks, (2) Documentation in llms.txt format, (3) GitHub repository analysis, (4) Documentation without direct llms.txt support, (5) Multiple documentation sources in parallel
repo-knowledge-lookup
knowledgeca がプロジェクト内一次情報と外部公式ドキュメントに当たって回答する手順。
external-reference-research
Specialized agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search. Use proactively when unfamiliar libraries or frameworks are involved, working with external dependencies, or needing examples from open-source projects to understand best practices and real-world implementations.
issue-creation
Skill for creating and triaging issues in the Corrupt Video File Inspector project
wechat-article-fetcher
WeChat official account article fetcher with intelligent ranking based on research interests (AI Agent, System Design, GitHub Open Source). Supports fetching from specific accounts or all followed accounts with date filtering and Obsidian integration.
search
Search the web, library documentation, and GitHub repositories using Tavily, Context7, and GitHub Grep MCPs. Use when: (1) Looking up documentation for libraries or frameworks, (2) Searching for code examples or tutorials, (3) Finding API references or specifications, (4) Researching best practices or solutions, (5) Looking up error messages or troubleshooting guides, (6) Finding library installation instructions, (7) Searching for real-world code patterns in GitHub repositories, or (8) When you need current web information or documentation. Triggers: search, look up, find documentation, search web, lookup, find examples, search for, how to, tutorial, API reference, documentation for, error message, troubleshoot, best practices, find code examples, GitHub search.
docs-seeker
Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy
glossary-creation
プロジェクト用語集（docs/glossary.md）を作成・更新する。 「用語集を作って」「用語を整理して」「用語の定義を統一」「glossaryを更新」 「このプロジェクトの用語を定義」「専門用語をまとめて」などの依頼時に発火。 docs群から用語を抽出し、定義・関連用語・使用例・実装箇所を整理して出力。
generating-spec
Write the specification for implementing a feature, bug correction, or enhancement. Used to specify a current or new feature, bug correction, or enhancement.
memory-updater
Update and maintain Memory Bank files (activeContext, progress, decisionLog). LOAD THIS SKILL WHEN: Task completed | session ending | User says "記錄進度", "更新 memory" | before git commit | context needs saving. FILES: activeContext.md (current focus), progress.md (done/doing/next), decisionLog.md (decisions).
research-gather
Systematically gather source material for blog articles. GitHub history, session transcripts, code examples, screenshots. Use at RESEARCH stage of blog pipeline.
