Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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"
.claude/skills/reinamaccredy-gitnexus-cli/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 105% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -7% | 0% |
All commands work via npx — no global install required.
bashnpx 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) |
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.
bashnpx 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.
bashnpx 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 |
bashnpx 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 |
bashnpx gitnexus list
Lists all repositories registered in ~/.gitnexus/registry.json. The MCP list_repos tool provides the same information.
gitnexus://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| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 9,700 | 1,521 | -84% | 1 | 1 | 0% | 452 | 927 | +105% | 0 | 0 | — |
case-02 | fail→pass | 46,562 | 28,681 | -38% | 1 | 1 | 0% | 1,091 | 1,033 | -5% | 0 | 0 | — |
case-03 | fail→pass | 39,838 | 3,790 | -90% | 1 | 1 | 0% | 3,002 | 1,338 | -55% | 0 | 0 | — |
case-04 | pass→pass | 4,182 | 2,268 | -46% | 1 | 1 | 0% | 661 | 1,060 | +60% | 0 | 0 | — |
case-05 | pass→pass | 11,105 | 2,308 | -79% | 1 | 1 | 0% | 1,446 | 1,119 | -23% | 0 | 0 | — |
case-06 | fail→pass | 4,622 | 1,406 | -70% | 1 | 1 | 0% | 704 | 924 | +31% | 0 | 0 | — |
case-16 | pass→pass | 4,524 | 2,389 | -47% | 1 | 1 | 0% | 676 | 950 | +41% | 0 | 0 | — |
case-07 | fail→pass | 8,801 | 2,539 | -71% | 1 | 1 | 0% | 1,249 | 1,166 | -7% | 0 | 0 | — |
case-08 | fail→pass | 9,746 | 1,477 | -85% | 1 | 1 | 0% | 1,338 | 959 | -28% | 0 | 0 | — |
case-09 | pass→pass | 7,392 | 2,542 | -66% | 1 | 1 | 0% | 1,052 | 1,045 | -1% | 0 | 0 | — |
case-10 | pass→pass | 11,330 | 1,991 | -82% | 1 | 1 | 0% | 1,586 | 1,107 | -30% | 0 | 0 | — |
case-23 | pass→pass | 15,611 | 9,864 | -37% | 1 | 1 | 0% | 2,623 | 2,115 | -19% | 0 | 0 | — |
case-11 | fail→pass | 17,146 | 2,480 | -86% | 1 | 1 | 0% | 2,129 | 986 | -54% | 0 | 0 | — |
case-12 | pass→pass | 8,873 | 102,467 | +1055% | 1 | 1 | 0% | 1,126 | 1,155 | +3% | 0 | 0 | — |
case-13 | pass→pass | 7,324 | 1,740 | -76% | 1 | 1 | 0% | 1,105 | 981 | -11% | 0 | 0 | — |
case-14 | pass→pass | 7,039 | 2,849 | -60% | 1 | 1 | 0% | 957 | 1,028 | +7% | 0 | 0 | — |
case-15 | pass→pass | 9,121 | 2,227 | -76% | 1 | 1 | 0% | 1,233 | 959 | -22% | 0 | 0 | — |
case-17 | pass→pass | 16,596 | 98,193 | +492% | 1 | 1 | 0% | 1,432 | 1,031 | -28% | 0 | 0 | — |
case-18 | pass→pass | 9,989 | 2,610 | -74% | 1 | 1 | 0% | 1,581 | 1,022 | -35% | 0 | 0 | — |
case-19 | fail→pass | 31,462 | 3,061 | -90% | 1 | 1 | 0% | 4,249 | 1,073 | -75% | 0 | 0 | — |
case-20 | fail→pass | 7,939 | 1,715 | -78% | 1 | 1 | 0% | 1,218 | 946 | -22% | 0 | 0 | — |
case-21 | pass→fail | 13,500 | 11,592 | -14% | 1 | 1 | 0% | 2,270 | 2,311 | +2% | 0 | 0 | — |
case-22 | pass→pass | 15,417 | 9,011 | -42% | 1 | 1 | 0% | 2,224 | 2,289 | +3% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +35 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.