Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 389,706 indexed, measured the same four ways as everything else here.
A project-initialization command that creates or completes a Context Engineering directory structure for AI-assisted collaboration. The description is in Chinese and gives no further implementation details.
Clean up and maintain the entire wiki system automatically. Syncs vault pages with projectwiki/ (projectwiki is truth). Reads every vault page, fixes formatting, fills gaps, strengthens cross-references. Fully autonomous — run periodically to keep everything healthy.
Use when working with Notion (pages, databases, blocks, comments, search, file uploads) from the shell — full notion-cli command reference and workspace snapshot cache usage. Prefer this CLI over Notion MCP tools.
Personal conversation distillation system. Records, analyzes, and distills your AI conversations to automatically discover and generate personalized skills from your real behavior patterns. Contains three sub-commands: - /self-distill record: Script directly parses JSONL to archive the current conversation — zero…
Use when the user wants to set up, switch between, or manage aenv namespaces — named bundles of CLAUDE.md, skills, MCP entries, and other AI-coding-harness config — in a project OR globally across $HOME. Triggers include aenv … mentioned directly, "switch namespace/profile", "activate/deactivate", "create/snapshot a…
Runs the vibe-check static analyzer on Claude skills, agents, and CLAUDE.md files, then fixes the findings and trims token cost. Use when the user wants to lint, score, review, fix, or improve a skill or agent file, asks why a skill scores badly, or wants to audit skills they installed.
Learn from conversation history to improve Claude Code performance. Analyzes logs for communication patterns, model understanding, assumptions, efficiency, and extracts actionable lessons.
Reviews code changes for quality, security, and correctness. Use when the user says "review this", "check my PR", "look over these changes", "is this safe", or "what do you think of this code". Covers: logic errors, security issues, style violations, missing tests, and architectural concerns.
PostgreSQL database documentation - SQL queries, database design, administration, performance tuning, and advanced features. Use when working with PostgreSQL databases, writing SQL, or managing database systems.
Migrate a bloated monolithic memory.md (or any large knowledge file) into a slim INDEX + per-topic files pattern. Cuts session-start token cost by 93% by lazy-loading topic content only when relevant. Use when an agent's memory.md has grown above 10KB, when a CLAUDE.md is bloating session context, when a multi-agent…
Imports an existing Claude.ai project folder, Cowork project, or any folder of past Claude work into the user's Obsidian vault as structured PARA notes. Use this skill when the user runs /migrate-claude-project [path], says "import my Claude project", "migrate this folder into my vault", "seed my vault from old Claude…
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
Review code quality with all 18 dimensions. Analyzes diff, gathers deep context, checks Known Gotchas, presents findings grouped by severity. If a PR exists, posts inline comments on GitHub. Use when the user says "code review", "review this PR", "review PR", "review", "pre-review", "check quality", or before opening…
Operate an LLM-maintained personal knowledge base (an "LLM Wiki") — a persistent, interlinked markdown wiki that the LLM builds and maintains from raw sources, used for study, research, and reading notes. Use this whenever the user wants to ingest sources into their knowledge base — one at a time or in a batch via…
Fast project health check. Structure completeness, namespace purity, file staleness, hook functionality, decisions format, memory adoption, dream history, setup quality — all from local files. Works with or without git. No agents, no external fetches, 15-30 seconds. For deep analysis with feature adoption and session…
Use when writing code in an app that does semantic search, RAG, or ingests documents into a vector database on the platform — running nearest-neighbor queries, listing/adding/removing documents, or feeding retrieved chunks into an LLM. Covers VectorDatabaseQuery(), ListDocumentsInVectorDatabase()…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: