docs-indexing-strategy
How to organize and index documentation for humans and AI: taxonomy, metadata, cross-linking, freshness reviews, and automated index generation
Find the perfect capability for your agent.
How to organize and index documentation for humans and AI: taxonomy, metadata, cross-linking, freshness reviews, and automated index generation
Repo navigation and “where do I start?” guide for OpenEvent-AI. Use when an agent/dev is lost, needs an overview of the project or a subsystem, or needs pointers to the most important docs, entrypoints, scripts, and tests without rescanning the entire codebase.
Classify dual-nature entities (hotels, churches, schools of arts, halls, lodges) in historical newspaper text as building-only, business/organisation-only, or both (polyhierarchical) based on contextual linguistic analysis. Use when analysing entity mentions from the Blue Mountains Historical Society Zotero library to determine appropriate Getty AAT facet assignments (Built Environment vs Agents).
This skill should be used when choosing between implementation approaches, making architectural decisions, selecting libraries or patterns, debugging complex issues, refactoring code, or making any significant decision where past context might be relevant. Search local-recall memories BEFORE proposing solutions.
Reference and maintain project technology stack documentation including frameworks, languages, databases, testing tools, deployment infrastructure, and third-party services. Use this skill when needing to understand what technologies and frameworks are used in the project, when making architectural decisions about adding new dependencies, when documenting the tech stack for team members, or when ensuring consistency across technology choices. Use when working with configuration files (package.json, requirements.txt, Gemfile, Cargo.toml), when setting up new services or integrations, when choosing between multiple library options, or when onboarding new developers who need to understand the project's technical foundation. Reference this when making decisions about ORM choices, testing frameworks, CSS frameworks, frontend libraries, or deployment platforms.
EU AI Act Article 73 compliance specialist for serious incident detection, classification, 15-day reporting timeline tracking, remediation workflow, and regulatory notification. AI-assisted automation with human judgment for serious incidents.
Fetch the latest, docs-grounded API details and best practices for a library/framework using Context7 MCP tools `resolve-library-id` and `get-library-docs`. Use when a user asks for “最新用法/最新寫法/最佳實務/latest usage/current best practice/latest API” of a package, or asks how to implement a feature with a library and wants the newest docs-based guidance.
Repo navigation and “where do I start?” guide for OpenEvent-AI. Use when an agent/dev is lost, needs an overview of the project or a subsystem, or needs pointers to the most important docs, entrypoints, scripts, and tests without rescanning the entire codebase.
Analyze argument structure, identify logical gaps, suggest evidence needs, generate counterarguments, apply claim-evidence-warrant framework. Use when strengthening arguments, analyzing persuasive writing, checking logical validity, or when user asks to improve reasoning or logic.
Tag Zotero items with timestamp tags after generating bibliographies. Uses secure macOS Keychain storage for credentials. Claude Code only.
This skill should be used when the user asks questions about their Plex media library, such as "what movies can I watch on Plex", "find romantic movies under 100 minutes", "show me Tom Cruise films from the 90s", "how many unwatched episodes of Always Sunny do I have", "give me a British comedy show I haven't watched", or "shows with episodes under 30 minutes that I've started". Use whenever user mentions Plex in combination with movies, TV shows, or media queries.
This skill should be used when the user asks questions like "how does build.zig work", "how to add dependencies in Zig", "explain Zig build system", "how to cross-compile in Zig", "what are Zig build modes", "how to create build steps", or generally asks about Zig's build system and package management.
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).
Capture solved problems as categorized documentation with YAML frontmatter for fast lookup
Skill for writing and updating codebase documentation. Use when creating or editing markdown documentation files in the docs/ directory, README files, or any documentation-related content. Also activates when maintaining the documentation index.
Systematically gather source material for blog articles. GitHub history, session transcripts, code examples, screenshots. Use at RESEARCH stage of blog pipeline.
You are planning to simplify and improve a folder and its contents. The goal is to restructure the folder so that it is more understandable, maintainable and debuggable.
Automatically review documents against checklists and best practices. Use when creating or reviewing ADRs, Design Docs, meeting notes, technical proposals, or RFCs. Detects anti-patterns, vague expressions, and missing elements.