CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-review

Review code changes for correctness, regressions, and unintended scope. Use when reviewing a pull request, branch, commit, patch, or local diff, including when invoked with /code-review.

67

Quality

84%

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

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.

A well-structured, senior-maintainer-grade review procedure that is sequenced, gated, and free of padding. The main headroom is deduplicating the out-of-scope-change guidance and adding a model finding to make the report format fully concrete.

Suggestions

Merge the duplicated guidance about 'changes whose connection to the stated goal is unclear' (checklist bullet and closing paragraph) into one place to tighten conciseness.

Add one example of a well-formed finding showing the severity, trigger conditions, and line reference format in action to lift actionability.

Make the verification loop explicit — e.g., a step confirming every changed file was accounted for before reporting — to add a clear validation checkpoint to the workflow.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence with no concept explanations, but 'changes whose connection to the stated goal is unclear' is stated twice (in the checklist and again in the closing paragraph), a minor trim opportunity that keeps it below anchor 5.

4 / 5

Actionability

Concrete guidance throughout — a numbered scope procedure, an explicit 'Check for:' checklist, and a 4-part per-finding format — but no worked example of a well-formed finding, which for an instruction-only skill is the gap between anchor 4 and 5.

4 / 5

Workflow Clarity

Three clearly sequenced phases (establish scope, review, report) with explicit gates such as 'If the intended behavior is unclear, state the assumption used for the review' and 'If no actionable findings remain, say so explicitly'; error-recovery feedback loops are implicit rather than spelled out, so it sits at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The body is under 50 lines, references no external files, and is organized into well-signaled '##' sections, so under the simple-skill exception for a self-contained skill it earns the top score.

5 / 5

Total

17

/

20

Passed

Description

83%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 tight, third-person description that pairs a specific capability statement with an explicit 'Use when' clause covering the full range of diff artifacts. It is close to exemplary, with only minor gaps in synonym coverage and slight overlap risk with adjacent git skills.

Suggestions

Add common synonyms users actually say, such as 'PR' or 'review my changes', to broaden trigger coverage toward anchor 5.

Sharpen distinctiveness from adjacent git/PR skills (e.g., commit-message generation) by stating the outcome, such as 'produce prioritized, actionable review findings'.

DimensionReasoningScore

Specificity

'Review code changes for correctness, regressions, and unintended scope' enumerates three concrete review targets, giving specific coverage with only minor gaps; it stops short of anchor 5 because there is a single action verb rather than multiple distinct capabilities.

4 / 5

Completeness

It explicitly answers both what ('Review code changes for correctness, regressions, and unintended scope') and when ('Use when reviewing a pull request, branch, commit, patch, or local diff, including when invoked with /code-review') with concrete trigger phrases, matching the anchor 5 example exactly; not below because neither part is vague or implied.

5 / 5

Trigger Term Quality

'pull request, branch, commit, patch, local diff, /code-review' gives good natural keyword coverage, but common synonyms such as 'PR' and 'diff review' are missing, so it falls just short of comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The niche (reviewing diffs/PRs for defects) is mostly distinct with clear triggers, but phrases like 'review a commit' carry minor overlap risk with adjacent git-workflow skills, keeping it below anchor 5.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

microsoft/vscode

Path

.github/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.