requesting-code-review

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill presents a clear, well-sequenced review workflow with concrete git commands and a triage-based feedback loop, but actionability and progressive disclosure are weakened by the missing code-reviewer.md template, and the example plus Integration section add redundancy.

Suggestions

Ship the referenced code-reviewer.md template file (or inline its prompt) so the dispatch step is actually copy-paste ready rather than depending on a file absent from the bundle.

Trim the narrative example and collapse "Integration with Workflows" into "When to Request" to remove the redundancy between those sections.

Add an explicit re-review step after fixes (e.g. re-dispatch the reviewer on the new HEAD_SHA) so the feedback loop is validate -> fix -> retry rather than a single pass.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with concrete commands, but the narrative example ("You: Let me request code review before proceeding.") and the "Integration with Workflows" section largely rephrase "When to Request", so it could be tightened, matching score-2 rather than the fully lean score-3 anchor.	2 / 3
Actionability	It gives executable git commands and named placeholders, but the core action (filling the template at code-reviewer.md) depends on a referenced file that is not present in the bundle, leaving a key detail missing per the score-2 anchor.	2 / 3
Workflow Clarity	The three numbered steps (get SHAs, dispatch reviewer, act on feedback) are clearly sequenced with a triage checkpoint system (Critical=fix now, Important=fix before proceeding, Minor=note) and a push-back feedback path, matching the score-3 clear-sequence-with-checkpoints anchor.	3 / 3
Progressive Disclosure	The body correctly signals a one-level-deep reference to [code-reviewer.md](code-reviewer.md), but that file does not exist in the bundle, so the split is broken and navigation fails, capping this at score-2 rather than the well-split score-3 anchor.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 leads with explicit "Use when" triggers and states a purpose, which satisfies completeness, but the capability statement is vague and the triggers are generic dev milestones that omit the word "review" and could overlap with other skills.

Suggestions

Add concrete capability verbs, e.g. "Dispatch a code-review subagent to verify work against requirements" so the "what" lists specific actions rather than the abstract "verify work meets requirements".

Include natural user phrasing such as "review my code", "check this before merge", or "code review" as trigger terms alongside the milestone-based triggers.

Sharpen distinctiveness by tying triggers to the review-specific niche (e.g. "before merging to main" or "after finishing a feature") rather than the generic "completing tasks".

Dimension	Reasoning	Score
Specificity	The only stated action is "to verify work meets requirements", which names a domain (tasks/features/merging) and a purpose but is abstract rather than a list of concrete actions, so it sits above the vague score-1 anchor but below the multi-action score-3 anchor.	2 / 3
Completeness	It has an explicit "Use when..." clause (when) and a stated purpose "to verify work meets requirements" (what), so both halves are answered with explicit triggers, fitting the score-3 anchor rather than score-2 where the when is missing or only implied.	3 / 3
Trigger Term Quality	Triggers like "completing tasks, implementing major features, or before merging" are natural-ish dev milestones, but common variations a user would actually say ("review my code", "check this before merge") and the keyword "review" are missing, matching the score-2 "some relevant keywords but missing common variations" anchor.	2 / 3
Distinctiveness Conflict Risk	"completing tasks" and "implementing major features" are generic dev milestones that could overlap with other development skills, so while the before-merge/verify niche adds some specificity, it does not reach the clearly-distinct score-3 anchor.	2 / 3
	Total	9 / 12 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
Commit: d884ae0

Reviewed: 2 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.