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"

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and token-efficient CLI reference with excellent command/flag organization. The only gap is missing explicit validation checkpoints for the destructive clean and batch analyze workflows, which caps workflow clarity.

Suggestions

Add an explicit verification checkpoint after `analyze` (e.g. run `node .gitnexus/run.cjs status` or read `gitnexus://repo/{name}/context`) before declaring the index ready, framed as a validate-then-proceed gate.

Add a validate→fix→retry loop for the stale-index case in Troubleshooting beyond "restart Claude Code", so a failed re-index has a recovery path.

For `clean` (destructive), make the confirmation/validation step explicit in the body rather than only surfacing it via the `--force` flag table.

Dimension	Reasoning	Score
Conciseness	Lean command/flag-table layout with no basic-concept padding; even the dense npm 11.x troubleshooting note conveys edge-case detail Claude would not already know, so tokens earn their place.	3 / 3
Actionability	Every command ships a copy-paste bash block plus explicit flag tables with concrete defaults (e.g. `--model` default `minimax/minimax-m2.5`, `--concurrency` default 3), matching the fully-executable anchor.	3 / 3
Workflow Clarity	Commands are clearly grouped with "When to run" and "After Indexing" sections, but the destructive `clean` and batch `analyze` operations lack an explicit validate/verify checkpoint gate, which the rubric caps at 2.	2 / 3
Progressive Disclosure	A single well-organized file with clear section structure and no nested references; external pointers (the MCP context resource, GitHub issue) are one level deep and clearly signaled, appropriate for a CLI reference.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person, concrete actions, explicit "Use when" trigger, and tool-specific triggers that avoid conflict with generic skills. It hits the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete subcommand actions — "analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos" — matching the score-3 anchor for several specific concrete actions, not merely naming a domain.	3 / 3
Completeness	Explicitly answers both what (the CLI command set) and when ("Use when the user needs to run GitNexus CLI commands..."), satisfying the score-3 anchor with explicit triggers.	3 / 3
Trigger Term Quality	Provides natural user phrases as examples ("Index this repo", "Reanalyze the codebase", "Generate a wiki") that a user would plausibly say, giving good coverage rather than jargon-only triggers.	3 / 3
Distinctiveness Conflict Risk	The named tool "GitNexus CLI" with tool-specific subcommand triggers carves a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mindfold-ai/Trellis
Path: .claude/skills/gitnexus/gitnexus-cli/SKILL.md
Commit: 12e279a

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.