メニュー
Use when the user needs to run OntoIndex CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Universo-specific complement to the OntoIndex code-intelligence tool. Use alongside the generated `.claude/skills/ontoindex/*` skills when querying the code graph in this monorepo. Adds the three things those generated skills do NOT cover — the namespace-collision caveat (this is code intelligence over source, NOT OWL/RDF/SPARQL), this repo's pnpm wrapper and golden queries, and the SQL-first edge-quality limitation.
Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug"
Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How does X work?", "What calls this function?", "Show me the auth flow"
Use when the user asks about OntoIndex itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What OntoIndex tools are available?", "How do I use OntoIndex?"
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?"
Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file"
| name | ontoindex-cli |
| description | Use when the user needs to run OntoIndex CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki" |
All commands work via npx — no global install required.
npx ontoindex analyze
Run from the project root. This parses all source files, builds the knowledge graph, writes it to .ontoindex/, and generates CLAUDE.md / AGENTS.md context files.
| Flag | Effect |
|---|---|
--force | Force full re-index even if up to date |
--embeddings | Enable embedding generation for semantic search (off by default) |
When to run: First time in a project, after major code changes, or when ontoindex://repo/{name}/context reports the index is stale. In Claude Code, a PostToolUse hook runs analyze automatically after git commit and git merge, preserving embeddings if previously generated.
npx ontoindex status
Shows whether the current repo has a OntoIndex index, when it was last updated, and symbol/relationship counts. Use this to check if re-indexing is needed.
npx ontoindex clean
Deletes the .ontoindex/ directory and unregisters the repo from the global registry. Use before re-indexing if the index is corrupt or after removing OntoIndex from a project.
| Flag | Effect |
|---|---|
--force | Skip confirmation prompt |
--all | Clean all indexed repos, not just the current one |
npx ontoindex wiki
Generates repository documentation from the knowledge graph using an LLM. Requires an API key (saved to ~/.ontoindex/config.json on first use).
| Flag | Effect |
|---|---|
--force | Force full regeneration |
--model <model> | LLM model (default: minimax/minimax-m2.5) |
--base-url <url> | LLM API base URL |
--api-key <key> | LLM API key |
--concurrency <n> | Parallel LLM calls (default: 3) |
--gist | Publish wiki as a public GitHub Gist |
npx ontoindex list
Lists all repositories registered in ~/.ontoindex/registry.json. The MCP list_repos tool provides the same information.
ontoindex://repo/{name}/context to verify the index loadedexploring, debugging, impact-analysis, refactoring) for your task--embeddings (it's off by default) or set OPENAI_API_KEY for faster API-based embedding