CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

67

Quality

80%

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

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.

The body is a lean, well-structured instruction skill with concrete git/gh commands and a clear review workflow including a confidence checkpoint. It is held at 4 across dimensions by minor padding, some descriptive rather than executable guidance, and the absence of bundle files that would otherwise demonstrate one-level-deep progressive disclosure.

Suggestions

Trim soft-justification lines like 'Treat this as a first-class review concern, not an afterthought' to tighten conciseness toward the 5 anchor.

Consider splitting the enumerated input-handling and output rules into a small reference file so SKILL.md stays an overview and progressive disclosure can reach 5, while signaling the reference explicitly.

Add an explicit post-review verification step (e.g., re-run the diff to confirm flagged lines) to push workflow_clarity from 4 to 5.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence (no explanation of git/PR concepts), with only minor instances of over-explanation such as 'Treat this as a first-class review concern, not an afterthought' that could be trimmed; it does not reach 5 because a few lines are mildly padded.

4 / 5

Actionability

Provides concrete copy-paste commands for each input type ('git diff', 'git show $ARGUMENTS', 'gh pr diff $ARGUMENTS') and enumerated handling, with minor gaps since the 'What to Look For' section is descriptive guidance rather than executable steps; not a 5 because some guidance remains abstract.

4 / 5

Workflow Clarity

A clear sequence is present (determine target -> gather context -> look for issues -> before-you-flag checkpoint -> output) with a self-check in 'Before You Flag Something' and a context-gathering feedback step; minor validation gaps keep it at 4 rather than 5.

4 / 5

Progressive Disclosure

No bundle files exist, so this scores on body structure: the content is a single well-organized SKILL.md with clear section headers and no nested references, fitting the 'good structure' anchor; it is over the ~50-line simple-skill threshold so it does not reach 5.

4 / 5

Total

16

/

20

Passed

Description

86%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 is strong, explicitly covering both what the skill does and when to trigger it with a comprehensive set of natural trigger phrases. Its only weakness is specificity, as the action vocabulary is limited to reviewing and providing feedback rather than enumerating concrete review actions.

Suggestions

Expand the 'what' with concrete actions (e.g., 'identifies bugs, flags security issues, checks conventions, and recommends fixes') to lift specificity from a list of review types to a list of review actions.

DimensionReasoningScore

Specificity

Names the domain ('code changes') and 1-2 concrete actions ('Reviews code changes and provides actionable feedback'), matching the anchor that lists domain plus a couple of actions without comprehensive coverage; it does not rise to 4 because the only actions are review and feedback.

3 / 5

Completeness

Clearly states what it does ('Reviews code changes and provides actionable feedback') and when to use it ('Use when the user asks to review a PR... Triggers on...') with concrete trigger phrases, matching the anchor that explicitly answers both what and when.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural phrases users would actually say ('/review', 'review this PR', 'review my changes', 'code review', 'review a PR, diff, commit'), including synonyms and multiple surface forms; nothing significant is missing for this domain.

5 / 5

Distinctiveness Conflict Risk

Mostly distinct with a clear code-review niche and specific triggers; minor overlap risk with closely related review-oriented skills keeps it just below the 5 anchor.

4 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Kiz8-Team/open-agents
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.