CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

An exceptionally actionable, well-sequenced review workflow with concrete commands, per-case parameters, and explicit validation and failure-handling loops throughout. Its weaknesses are token-heavy inlined repo-specific detail and a dangling reference to a 'ci-personas/' directory that is absent from the bundle.

Suggestions

Move the GitNexus schema-fingerprint/parser-compatibility detail (workflow step 8, roughly 25 lines of repo-specific constants and file paths) into a reference file and keep a one-line pointer in the workflow so the main body stays an overview.

The 'ci-personas/' directory cited in 'Swarm lanes' does not exist in this skill bundle; either ship the six lane files with the skill or reword the section so the reference is not dangling.

Tighten repeated governance statements — e.g., the fail-open critic rationale is explained twice, and 'the lanes structure the work; they never gate it' repeats the same point made for the critic — to reduce token cost without losing the rule.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — no explanations of concepts Claude already knows — but the ~30-line schema-fingerprint/parser-compatibility paragraph in workflow step 8 and repeated governance statements (the fail-open critic rationale, 'never gate' phrasing) could be trimmed. It is above the 3 anchor (little is truly unnecessary) but short of 'every token earns its place'.

4 / 5

Actionability

Fully executable throughout: exact commands ('git merge-base <base> <head>', 'node .gitnexus/run.cjs analyze --index-only --pdg'), per-case tool parameters (scope/base_ref for detect_changes, includeTests for impact), and a copy-paste output template — matching the 5 anchor's 'specific examples cover the common cases'.

5 / 5

Workflow Clarity

An 8-step numbered workflow with explicit validation checkpoints and feedback loops: stale-index refresh, re-running committed baselines/fingerprints against the head, and the bounded critic loop ('repair the draft and re-dispatch the critic once; if defects remain... note the unresolved objections and proceed') with an inline fallback when subagents are unavailable — matching the 5 anchor.

5 / 5

Progressive Disclosure

Sections are well-organized, but the referenced 'ci-personas/' bundle directory is not present in the skill bundle, and repo-specific detail (the GitNexus schema-fingerprint and parser-compatibility material in step 8) is inlined in the main body where it belongs in a separate reference file — matching the 3 anchor ('content that should be separate is inline; references present but not clearly signaled') rather than 4.

3 / 5

Total

17

/

20

Passed

Description

91%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: third-person, explicit 'Use when' triggers, and comprehensive natural trigger terms for the code-review niche. Its only weaknesses are a single-verb capability list and minor overlap risk with generic code-review skills on the bare 'code review' trigger.

DimensionReasoningScore

Specificity

Enumerates concrete capabilities across target surfaces ('GitHub PR URL or number, a branch/ref or commit range, or local staged, unstaged, and untracked changes'), but the action set is essentially one verb — review — with input variants, so it falls just short of the comprehensive multi-action coverage of the 5 anchor.

4 / 5

Completeness

Both 'what' ('Review code changes with GitNexus from...') and 'when' ('Use when the user asks for a code review...') are explicitly stated with concrete trigger phrases, exactly matching the 5 anchor.

5 / 5

Trigger Term Quality

'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' comprehensively covers the natural phrases a user would say for this niche, matching the 5 anchor rather than 4 where natural terms would be missing.

5 / 5

Distinctiveness Conflict Risk

The GitNexus framing and enumerated target surfaces give it a clear niche, but the bare 'code review' trigger overlaps generic code-review skills, so it fits the 4 anchor (minor overlap with closely related skills) rather than 5.

4 / 5

Total

18

/

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-review/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.