Review change

Skill jsuvic/agent-profile/fixtures/code-review-enabled/expected/.claude/skills/review-change

Use to review a proposed change for correctness, security-sensitive behavior, readability, tests, performance when relevant, architecture and contract impact, and generated-file drift.From its SKILL.md

Install

npx -y skills add jsuvic/agent-profile --skill review-change

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.9 KB, 353 tokens by cl100k_base, as published. Nobody here has run it

Review Change

Use these rules when reviewing a pull request or proposed change.

Review Focus

Correctness and edge cases.
Security, including input validation and secret handling.
Performance hotspots and obvious complexity regressions.
Unnecessary complexity or premature abstraction.
Consistency with existing project style.
Missing or weakened tests.
Weak typing or unjustified any.
Accessibility-affecting behavior in user-facing changes.
Error handling and observability gaps.
Dependency risk and license concerns.
Spec compliance.

Severity Labels

Blocker: must fix before merge (correctness, security, contract break).
High: must fix before merge unless explicitly deferred.
Medium: should fix before merge or open a tracked follow-up.
Low: nit or polish; safe to defer.

Output Format

Summary: one paragraph of intent and overall verdict.
Spec Compliance: cite the spec and any deviation.
Findings: grouped by severity, each with file, function, and concrete suggestion.
Tests: list coverage gaps and whether tests were run.
Safety Review: secrets, production access, dependency installs, network access.
Final recommendation: approve, request changes, or block with reason.

Review Discipline

Skip nitpicks the autoformatter or linter already handles.
Do not propose broad rewrites; keep suggestions actionable.
Reference the specific file, function, or component in every finding.

Safety

Review only; do not rewrite or apply patches unless the user asks.
Do not upload source code or read or print secrets.
Do not install dependencies, contact production systems, or broaden permissions.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most review quality skills give in 353 tokens

Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07

Ask questions one at a timein 81 of 1048, across 64 files
Provide a recommended answer for each questionin 73 of 1048, across 50 files
Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
Interview the user relentlessly about the planin 38 of 1048, across 13 files
Order findings by severityin 31 of 1048
Resolve each branch of the decision treein 27 of 1048, across 5 files
Run a grilling sessionin 26 of 1048, across 5 files
Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
Create documentation files lazilyin 24 of 1048, across 5 files
Assign severity to every findingin 24 of 1048

Said here and by no other author read

Check security, input validation, and secret handling
Check performance hotspots and complexity regressions
Check for unnecessary complexity or premature abstraction
Check typing for weak types or unjustified any
Check accessibility in user-facing changes
Check error handling and observability gaps

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.