requesting-code-review

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

Quality

31%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/requesting-code-review/SKILL.md

Quality

Content

62%

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

This skill provides a reasonable workflow for requesting code reviews via subagents, with clear sequencing and priority-based feedback handling. However, it suffers from some redundancy between sections (When to Request vs. Integration with Workflows), includes obvious advice in the Red Flags section, and lacks full specificity on how to actually dispatch the subagent. The referenced template file is not provided in the bundle, making it hard to assess the complete picture.

Suggestions

Remove or consolidate the 'Integration with Workflows' section into 'When to Request Review' to eliminate redundancy, and trim the 'Red Flags' section to only non-obvious guidance.

Make the dispatch step more actionable by showing the exact Task tool invocation syntax rather than just saying 'Use Task tool with general-purpose type'.

Include the referenced code-reviewer.md template in the bundle, or inline the essential template structure so the skill is self-contained enough to act on.

Dimension	Reasoning	Score
Conciseness	Generally efficient but includes some unnecessary sections like 'Red Flags' with obvious advice ('Never skip review because it's simple', 'Ignore Critical issues') that Claude already knows. The example section is somewhat verbose and could be tightened. The 'Integration with Workflows' section largely repeats the 'When to Request Review' section.	2 / 3
Actionability	Provides concrete git commands for getting SHAs and a clear placeholder-based template approach, but the actual dispatch mechanism is vague ('Use Task tool with general-purpose type, fill template at code-reviewer.md'). The example uses a narrative format rather than executable commands. Key details about how to actually invoke the subagent are missing.	2 / 3
Workflow Clarity	The workflow is clearly sequenced: get SHAs → dispatch reviewer with template → act on feedback with explicit priority tiers (Critical → fix immediately, Important → fix before proceeding, Minor → note for later). The feedback loop for handling reviewer responses is well-defined, including the push-back path when the reviewer is wrong.	3 / 3
Progressive Disclosure	References the template at 'requesting-code-review/code-reviewer.md' which is appropriate, but no bundle files are provided to verify this reference. The skill itself contains content that could be split out (the example section is lengthy). The reference to 'docs/superpowers/plans/deployment-plan.md' in the example adds confusion about what's a real path vs. illustrative.	2 / 3
	Total	9 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is critically weak across all dimensions. It only vaguely describes when to use the skill without ever explaining what the skill actually does. The language is so generic ('completing tasks', 'implementing major features') that it would be nearly impossible for Claude to distinguish this skill from others in a multi-skill environment.

Suggestions

Add a clear 'what' clause describing the concrete actions this skill performs (e.g., 'Runs test suites, checks code coverage, and validates acceptance criteria' or 'Generates a checklist of requirements and verifies each is met').

Replace generic terms like 'completing tasks' and 'implementing major features' with specific, natural trigger terms users would actually say (e.g., 'run tests', 'verify requirements', 'pre-merge check', 'QA review').

Add a structured 'Use when...' clause with explicit triggers tied to the skill's domain, such as 'Use when the user asks to run a final check, validate requirements, or review work before a pull request.'

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'completing tasks' and 'implementing major features' without specifying any concrete actions. It doesn't describe what the skill actually does—only when to use it.	1 / 3
Completeness	The description answers 'when' in a vague way but completely fails to answer 'what does this do'. There is no indication of the skill's actual capabilities or actions.	1 / 3
Trigger Term Quality	The terms 'completing tasks', 'implementing major features', and 'merging' are extremely generic. 'Verify work meets requirements' is slightly more specific but still lacks natural keywords a user would say. There are no domain-specific trigger terms.	1 / 3
Distinctiveness Conflict Risk	This description is extremely generic and could apply to almost any verification, testing, linting, or review skill. 'Completing tasks' and 'implementing major features' would conflict with virtually every other skill.	1 / 3
	Total	4 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: obra/superpowers
Commit: 6fd4507

Reviewed: 14 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.