requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/requesting-code-review/SKILL.md

Quality

Content

71%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 a well-structured, actionable playbook for dispatching a review subagent with clear sequencing and triage guidance. Its main weakness is that the single referenced detail file does not exist in the bundle, leaving the progressive-disclosure pointer unresolved.

Suggestions

Include the referenced code-reviewer.md in the bundle (references/ or root) so the signaled template link resolves and progressive disclosure is real.

Add an explicit 're-request review after fixing Critical/Important issues' step to close the feedback loop in the workflow.

Trim the 'Common Rationalizations' table or 'Review early, review often' tagline to reduce motivational padding that assumes Claude needs convincing.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with concrete bash and a tight procedure, but the 'Common Rationalizations' table and 'Review early, review often' add mild motivational padding that could be trimmed, sitting just above the efficient anchor.	4 / 5
Actionability	It gives executable git commands, a named subagent type with explicit template placeholders, and a worked example with real SHAs, but the referenced template file (code-reviewer.md) is absent from the bundle, slightly undercutting copy-paste readiness.	4 / 5
Workflow Clarity	A clear 3-step sequence (get SHAs, dispatch, act on feedback) with a triage checkpoint ordering Critical/Important/Minor and an explicit push-back path; only a minor gap in that no re-review-after-fixing loop is stated.	4 / 5
Progressive Disclosure	Sections are well organized and the template is signaled as a one-level reference, but code-reviewer.md is not present in the bundle (no references/ dir), so the signaled navigation target is a dangling link rather than real progressive disclosure.	3 / 5
	Total	15 / 20 Passed

Description

70%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 gives clear trigger guidance and a recognizable dev-workflow niche, but the 'what' is vague ('verify work meets requirements') rather than naming the concrete action of dispatching a review subagent. It is solid but leaves the core capability underspecified.

Suggestions

State the concrete action up front, e.g. 'Dispatch a code reviewer subagent to verify work meets requirements' so the 'what' is explicit rather than implied by 'verify'.

Add natural synonyms users say, such as 'code review', 'review my code', or 'before opening a PR' to broaden trigger coverage.

Tighten 'completing tasks' to a more specific trigger like 'after completing a task in subagent-driven development' to reduce overlap with generic verification skills.

Dimension	Reasoning	Score
Specificity	Names concrete triggering situations ('completing tasks, implementing major features, before merging') and one action ('verify work meets requirements'), but the action is generic and not comprehensive, matching the anchor for a clear domain with 1-2 actions.	3 / 5
Completeness	It has both a 'when' ('Use when completing tasks...') and a 'what' ('to verify work meets requirements'), but the 'what' is thin and could be more explicit about dispatching a reviewer, so it sits between anchors 3 and 4, closer to 4.	4 / 5
Trigger Term Quality	Phrases like 'completing tasks', 'implementing major features', and 'before merging' are natural things a user would say, but common synonyms like 'code review' or 'before PR' are missing, landing just above the midpoint.	4 / 5
Distinctiveness Conflict Risk	The merge/feature-completion triggers carve a fairly distinct niche, though 'completing tasks' is broad enough to risk minor overlap with general verification skills, so it is mostly distinct with minor overlap.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: obra/superpowers
Path: skills/requesting-code-review/SKILL.md
Commit: b36e082

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.