CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-review

Reviews code changes and provides actionable feedback. Use when the user asks to review a PR, diff, commit, or code changes. Triggers on "/review", "review this PR", "review my changes", "code review".

72

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

92%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 content is an excellent instruction-only skill: concrete executable git/gh commands, a clearly sequenced review workflow with explicit pre-flag validation checkpoints, and disciplined focus on what to review and how to communicate findings. The only nit is a slightly redundant opening line and one filler sentence.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — no basic-concept explanations — but has minor trims available: the opener "You are a code reviewer. Your job is to review code changes and provide actionable feedback" duplicates the frontmatter description, and "Use best judgement when processing input" is filler. This fits 'Efficient; minor instances of over-explanation that could be trimmed' rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

The input-handling section gives copy-paste-ready commands for all four cases ("git diff --cached", "git show $ARGUMENTS", "git diff $ARGUMENTS...HEAD", "gh pr diff $ARGUMENTS"), and guidance elsewhere is concrete down to examples like "O(n²) on unbounded data, N+1 queries, blocking I/O on hot paths" — matching 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

The sections are sequenced as a real workflow (determine review target → gather context → what to look for → pre-flag verification → output), with explicit validation steps and feedback loops: "Don't flag something as a bug if you're unsure - investigate first", "Verify the code is *actually* in violation", and the fallback "say 'I'm not sure about X' rather than flagging it". This matches the anchor-5 pattern of clear sequence plus explicit validation with error-recovery loops; this is a read-only review skill, so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

This is a single-file, ~100-line skill with well-organized headers, no bundle files, and no content that clearly belongs in a separate reference file — the structure is easy to navigate with nothing buried. Per the rubric's simple-skill guidance, well-organized sections with no need for external references warrant a 5.

5 / 5

Total

19

/

20

Passed

Description

82%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 with explicit 'what' and 'when' guidance, concrete trigger phrases, and a clear niche. Its main weakness is specificity: the capability statement is limited to two generic actions rather than enumerating what the review actually produces, and a few natural trigger variations are absent.

Suggestions

Replace the generic 'provides actionable feedback' with the concrete outputs of the review, e.g. 'Identifies bugs, security issues, and convention violations in changed code and reports severity', to raise specificity.

Add missing natural trigger variations such as 'pull request' spelled out, 'review this diff', or 'look over my changes' to broaden trigger term coverage.

DimensionReasoningScore

Specificity

"Reviews code changes and provides actionable feedback" names the domain with exactly two fairly generic actions, matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. It does not list several specific actions (e.g., 'identifies bugs, security flaws, convention violations'), so it is not a 4; and it goes beyond a bare domain mention like 'Processes PDF files', so it is not a 2.

3 / 5

Completeness

It explicitly answers both parts: what ("Reviews code changes and provides actionable feedback") and when ("Use when the user asks to review a PR, diff, commit, or code changes. Triggers on '/review', 'review this PR', 'review my changes', 'code review'") with concrete trigger phrases — a direct match to the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Coverage is good and natural: "review a PR", "diff", "commit", "/review", "review this PR", "review my changes", "code review" are phrases users would actually say. A few natural terms are missing (e.g., "pull request" spelled out, "review this diff", "look over my code"), which keeps it at the 'good coverage; a few natural terms missing' anchor rather than the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Reviews code changes... PR, diff, commit" carves out a clear niche with distinct triggers and minimal conflict risk against adjacent skills (e.g., commit-message generation), matching 'Clear niche with distinct triggers; minimal conflict risk'.

5 / 5

Total

17

/

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

Kiz8-Team/open-agents

Path

.agents/skills/code-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.