AGENT SKILL

gitnexus-cli

Use when the user needs to run GitNexus 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"

License 许可
MIT
最近更新
2026-07-08
Stars
★ 2
Forks
0

01 前言 Front Matter

name
gitnexus-cli
description
Use when the user needs to run GitNexus 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"

03 SKILL.md 正文

GitNexus CLI Commands

All commands work via npx — no global install required.

Commands

analyze — Build or refresh the index

npx gitnexus analyze

Run from the project root. This parses all source files, builds the knowledge graph, writes it to .gitnexus/, 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)
--drop-embeddings Drop existing embeddings on rebuild. By default, an analyze without --embeddings preserves them.

When to run: First time in a project, after major code changes, or when gitnexus://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.

status — Check index freshness

npx gitnexus status

Shows whether the current repo has a GitNexus index, when it was last updated, and symbol/relationship counts. Use this to check if re-indexing is needed.

clean — Delete the index

npx gitnexus clean

Deletes the .gitnexus/ directory and unregisters the repo from the global registry. Use before re-indexing if the index is corrupt or after removing GitNexus from a project.

Flag Effect
--force Skip confirmation prompt
--all Clean all indexed repos, not just the current one

wiki — Generate documentation from the graph

npx gitnexus wiki

Generates repository documentation from the knowledge graph using an LLM. Requires an API key (saved to ~/.gitnexus/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

list — Show all indexed repos

npx gitnexus list

Lists all repositories registered in ~/.gitnexus/registry.json. The MCP list_repos tool provides the same information.

After Indexing

  1. Read gitnexus://repo/{name}/context to verify the index loaded
  2. Use the other GitNexus skills (exploring, debugging, impact-analysis, refactoring) for your task

Troubleshooting

  • "Not inside a git repository": Run from a directory inside a git repo
  • Index is stale after re-analyzing: Restart Claude Code to reload the MCP server
  • Embeddings slow: Omit --embeddings (it's off by default) or set OPENAI_API_KEY for faster API-based embedding

04 同仓库更多 Skills

milky-way-66
milky-way-66/ai-spector

ai-spector

暂无简介

★ 2
milky-way-66
milky-way-66/ai-spector

ai-spector

Core AI Spector skill: setup, upgrade, adopt, check, docops CLI, work sessions (resume/route/pause), course link, and onboarding help. Use when the user says help, I'm stuck, where am I, or what's next about project setup; project init/setup, upgrade, adopting existing docs, workspace check, Writer contract bootstrap (docops init/migrate), resuming or managing active work sessions, or learning via the course. Do not use when the user clearly wants generation, graph ops, or contract review/comments — use the matching skill instead.

★ 2
milky-way-66
milky-way-66/ai-spector

ai-spector-graph

Traceability graph operations: analyze data-source, index refresh, graph validate, impact, visualize, semantic search (CocoIndex), natural language graph lookup, doc summaries, and layer sync audit (design drift since baseline). Use when the user asks to analyze sources, refresh or validate the graph, see impact, visualize traceability, find docs by concept, or check doc drift since baseline. Do not use for writing SRS, basic design, HTML prototype, or formal document sign-off.

★ 2
milky-way-66
milky-way-66/ai-spector

ai-spector-generate

All document generation: SRS, basic design, detail design, HTML prototype; incremental feature/section changes (resolve-task); and template pack import. Use for "generate SRS/basic design/detail design", "write chapter N", "add feature", "update section", "I want to add…", "HTML prototype", Capability-gated for Writer cloud UI only — local adapter (`.ai-spector/engine.json`) uses MCP/CLI work sessions even when `capabilities.generate` is false.

★ 2
milky-way-66
milky-way-66/ai-spector

ai-spector-contract

Writer contract operations: document sign-off (review_approve), comment resolution (doc threads C-NNN and prototype batches B-NNN), translation sync, and language status. Use for review queue, approve doc by logical path (srs/01-overview), pending client review, resolve C-NNN threads, B-NNN prototype batches, resolve translations, or check language status. NOT for graph, generate, or setup — use the matching skill instead.

★ 2
milky-way-66
milky-way-66/ai-spector

ai-spector

Core AI Spector skill: setup, upgrade, adopt, check, docops CLI, work sessions (resume/route/pause), course link, and onboarding help. Use when the user says help, I'm stuck, where am I, or what's next about project setup; project init/setup, upgrade, adopting existing docs, workspace check, Writer contract bootstrap (docops init/migrate), resuming or managing active work sessions, or learning via the course. Do not use when the user clearly wants generation, graph ops, or contract review/comments — use the matching skill instead.

★ 2