gitnexus-review

Review code changes with GitNexus from a GitHub PR URL or number, a branch/ref or commit range, or local staged, unstaged, and untracked changes. Use when the user asks for a code review, merge-risk assessment, regression hunt, missing-test analysis, or a verdict on whether a PR, branch, commit range, or local diff is safe.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

70%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 well-sequenced, actionable review workflow with strong validation checkpoints and feedback loops, weakened by a missing referenced bundle (ci-personas/) and a verbose, repo-specific schema-fingerprint digression that bloats the context and would be better placed in a reference file.

Suggestions

Ship the referenced ci-personas/*.md lane files in a bundle directory alongside SKILL.md, or remove the claim that they ship with this skill — the current reference does not resolve.

Move the GitNexus-internal SCHEMA_FINGERPRINT / NODE_SCHEMA_QUERIES digression (lines ~122-133) into a separate reference file and keep only the general principle (verify schema/version constants were bumped) inline.

Tighten the repeated 'in GitNexus itself, for example' elaborations into a single short illustration or relocate them to a references/ file to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The prose mostly assumes Claude's competence (no explaining what a PR or git diff is), but the multi-paragraph GitNexus-internal SCHEMA_FINGERPRINT digression and repeated 'in GitNexus itself, for example' elaborations are unnecessary over-explanation that could be trimmed or moved to a reference, fitting the 3 anchor.	3 / 5
Actionability	Quotes concrete, executable commands and tool calls — 'gh pr view', 'git merge-base <base> <head>', 'node .gitnexus/run.cjs analyze --index-only', and MCP calls like detect_changes with scope/base_ref/worktree and impact with includeTests — with only minor gaps in the exact argument shapes for explain/pdg_query.	4 / 5
Workflow Clarity	The numbered workflow (steps 1-8) is a clear sequence with explicit validation checkpoints and feedback loops — re-running the exact CI check against head for stale baselines, rebuilding the --pdg index when missing, and the bounded two-pass critic repair — plus an explicit 'never switch or reset the user's current worktree' safety guard.	5 / 5
Progressive Disclosure	The body has clear section structure but references a 'ci-personas/' bundle directory that does not exist alongside SKILL.md, and inlines content that belongs in separate files (the six lane persona definitions and the schema-fingerprint deep-dive), matching the 3 anchor of structure present but content that should be separate is inline.	3 / 5
	Total	15 / 20 Passed

Description

95%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, third-person description that concretely names the tool, the supported review surfaces, and a rich set of natural 'Use when...' triggers. The only minor gap is that it expresses one action (review) across many input forms rather than several distinct actions.

Dimension	Reasoning	Score
Specificity	Quotes 'Review code changes with GitNexus from a GitHub PR URL or number, a branch/ref or commit range, or local staged, unstaged, and untracked changes' — it lists several concrete input surfaces comprehensively, but the action itself is a single verb (review) parametrized by input type rather than multiple distinct actions, so it sits just below the 5 anchor.	4 / 5
Completeness	It explicitly answers both 'what' (review code changes via GitNexus across enumerated surfaces) and 'when' (a concrete 'Use when...' clause with multiple trigger phrases), matching the 5 anchor.	5 / 5
Trigger Term Quality	Quotes 'Use when the user asks for a code review, merge-risk assessment, regression hunt, missing-test analysis, or a verdict on whether a PR, branch, commit range, or local diff is safe' — these are natural phrasings a user would actually say, with effective synonym coverage (merge-risk + safe-to-merge, code review, missing tests).	5 / 5
Distinctiveness Conflict Risk	Tool-anchored ('GitNexus') with specific review surfaces and distinct trigger phrases, giving it a clear niche and minimal overlap with generic review skills.	5 / 5
	Total	19 / 20 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: abhigyanpatwari/GitNexus
Path: .claude/skills/gitnexus-review/SKILL.md
Commit: c6b2416

Reviewed: 2 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.