CtrlK
BlogDocsLog inGet started
Tessl Logo

code-reviewer

Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.

80

1.54x
Quality

70%

Does it follow best practices?

Impact

99%

1.54x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/code-reviewer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

The body is a strong, efficient, actionable workflow: a clearly sequenced five-step process with concrete git/gh commands, a validation checkpoint, a structured feedback format, and cleanup. The only meaningful gaps are the absence of an example review output and of guidance for handling preflight failures.

DimensionReasoningScore

Conciseness

Efficient and well-sectioned with concrete commands throughout; only minor over-explanation remains (the opening line 'This skill guides the agent in conducting professional and thorough code reviews' and tone platitudes like 'Be constructive, professional, and friendly' could be trimmed). It is not a 5 because a few sentences restate what Claude already knows about reviewing.

4 / 5

Actionability

Provides concrete executable commands ('gh pr checkout <PR_NUMBER>', 'npm run preflight', 'git status', 'git diff', 'git diff --staged') plus a concrete findings taxonomy (Critical/Improvements/Nitpicks) and an explicit Approved/Request Changes decision. Falls short of 5 because the feedback output format is described but never exemplified.

4 / 5

Workflow Clarity

A clear five-phase numbered workflow with an explicit preflight validation checkpoint and a cleanup step for PR checkout. Not a destructive/batch operation so no cap applies; it misses 5 only because there is no error-recovery loop (what to do when preflight fails is left implicit).

4 / 5

Progressive Disclosure

A single-file skill (~58 lines) with no bundle files and no content that belongs in separate references; sections are well-organized and navigable, satisfying the simple-skill exception for well-organized single-file content.

5 / 5

Total

17

/

20

Passed

Description

61%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.

The description clearly communicates what the skill does and its two review modes with mostly distinct triggers, but it lacks an explicit 'Use when...' clause and relies on a single generic action verb, capping both completeness and specificity. Adding explicit trigger phrasing and concrete action verbs would lift it substantially.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to review code, review my changes, or review a PR (by number or URL)'.

Replace the generic 'review code' with concrete actions, e.g. 'Analyzes git diffs, reviews local staged/unstaged changes and remote Pull Requests, categorizes findings by severity, and recommends Approve or Request Changes'.

Include common trigger variations users actually say — 'PR', 'code review', 'diff' — to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain (code review) and its scope ('local changes (staged or working tree)' and 'remote Pull Requests (by ID or URL)'), but the only action is the generic 'review code' — matching the anchor for naming a domain with 1-2 concrete actions but not comprehensive coverage.

3 / 5

Completeness

The 'what' is clear (reviews local and remote changes; focuses on correctness, maintainability, and project standards), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural phrases users would say — 'review code', 'local changes', 'staged', 'working tree', 'Pull Requests' — but misses common variations like 'PR', 'code review', and 'diff', fitting 'good keyword coverage; a few natural terms missing' rather than comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

The staged/working-tree and PR-by-ID/URL scoping carves a mostly distinct niche with minor overlap risk against general linting or CI-type skills; it does not reach 5 because 'review code' alone is broad.

4 / 5

Total

14

/

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
google-gemini/gemini-cli
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.