CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

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

A highly actionable CLI reference: every command is executable, flags and defaults are documented, and a verification step plus troubleshooting section give the workflow checkpoints. The main cost is token weight — version-specific fallback detail and densely packed paragraphs could be trimmed or moved to reference files.

Suggestions

Trim the npm 11.x blockquote: keep one fallback (e.g., `bunx gitnexus@latest analyze`) in the body and move the full list of alternative install commands and issue link to a troubleshooting reference file.

Split the long watch paragraph into short bullets (behavior, rejected flags, remote-sync distinction) and cut detail not needed at decision time, such as MCP five-second refresh throttling.

Move the complete wiki provider/model flag table and the storage/retention API semantics into a references file, keeping only the two or three most common flags inline in SKILL.md.

DimensionReasoningScore

Conciseness

The body is dense and tool-specific rather than padded with concepts Claude already knows, but several sections could be tightened: the npm 11.x blockquote stacking four fallback commands with an issue link, the runner auto-selection parenthetical, and the watch paragraph that crams flag rejection lists, remote-sync semantics, and MCP refresh throttling into one block. This matches the 3 anchor ('mostly efficient but could be tightened') better than the 4 anchor, since the version-specific troubleshooting detail is time-sensitive material that adds notable token weight.

3 / 5

Actionability

Every command is copy-paste ready (`node .gitnexus/run.cjs analyze|status|clean|wiki|list`), flags are tabulated with defaults, and troubleshooting gives concrete fixes (e.g., "install once with `npm i -g gitnexus`"). This matches the 5 anchor: fully executable commands covering the common cases, exceeding the 4 anchor which allows minor gaps.

5 / 5

Workflow Clarity

The sequence is clear with an explicit validation checkpoint ("Read `gitnexus://repo/{name}/context` to verify the index loaded") and a troubleshooting section providing error recovery. It sits between the 4 and 5 anchors: recovery loops exist but are implied rather than fully spelled out (e.g., what to do when verification fails is not linked back to a re-run or clean step), so it is not the 5 anchor's complete feedback loops.

4 / 5

Progressive Disclosure

No bundle files exist, and the body has good structure — clear command sections, flag tables, storage, and troubleshooting — so navigation is easy. It does not reach 5 because reference-grade material (the full wiki provider/model flag table and the storage/retention API semantics paragraphs) is inlined rather than split out, matching the 4 anchor's 'most content appropriately placed; minor organization gaps'.

4 / 5

Total

16

/

20

Passed

Description

92%Weight 40%Scale 1-5

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: it names a distinct tool, enumerates all of its concrete capabilities, and provides an explicit 'Use when' clause with natural example trigger phrases. The only weakness is modest coverage of synonymous phrasings users might naturally use.

DimensionReasoningScore

Specificity

Enumerates five concrete actions — "analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos" — which comprehensively covers every command documented in the skill body. It exceeds the 4 anchor ('minor gaps in coverage') because no documented capability is missing.

5 / 5

Completeness

Explicitly answers both what (running GitNexus CLI commands: analyze, status, clean, wiki, list) and when ("Use when the user needs to run GitNexus CLI commands…" with concrete example trigger phrases). This matches the 5 anchor's requirement of concrete trigger phrases for both what and when; the 4 anchor applies only when the when-clause lacks specificity.

5 / 5

Trigger Term Quality

Includes natural example phrases users would say ("Index this repo", "Reanalyze the codebase", "Generate a wiki") plus command-level keywords (analyze, status, clean, wiki, list). It falls just below the 5 anchor because common variations such as "reindex", "update the index", or "refresh the codebase" are not covered.

4 / 5

Distinctiveness Conflict Risk

"GitNexus" names a specific tool and all triggers are scoped to its commands ("analyze/index a repo", "generate a wiki", "list indexed repos"), giving it a clear niche with minimal risk of firing for unrelated skills. It is well above the 4 anchor's 'minor overlap risk with closely related skills'.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

abhigyanpatwari/GitNexus

Path

gitnexus-claude-plugin/skills/gitnexus-cli/SKILL.md

Reviewed

Table of Contents

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.