requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
48
35%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/requesting-code-review/SKILL.mdQuality
Discovery
0%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 fails to explain what the skill actually does (its concrete actions or capabilities) and provides only vague, generic guidance on when to use it. Without knowing whether this is a testing skill, a code review skill, a checklist skill, or something else entirely, Claude would have no reliable basis for selecting it.
Suggestions
Add a clear 'what' clause describing the concrete actions this skill performs (e.g., 'Runs test suites, validates code against acceptance criteria, and checks for regressions' or 'Generates a verification checklist from requirements').
Replace vague terms like 'completing tasks' and 'implementing major features' with specific, natural trigger terms users would actually say (e.g., 'run tests', 'verify', 'check requirements', 'QA', 'pre-merge check').
Add an explicit 'Use when...' clause with concrete scenarios, such as 'Use when the user asks to verify code against requirements, run a pre-merge check, or validate that a feature implementation is complete.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'completing tasks' and 'implementing major features' without specifying any concrete actions. It does not describe what the skill actually does—only when to use it. | 1 / 3 |
Completeness | The description only vaguely addresses 'when' (before merging, completing tasks) but completely fails to answer 'what does this do'. There is no explanation of the skill's actual capabilities or actions. | 1 / 3 |
Trigger Term Quality | The terms 'completing tasks', 'implementing major features', and 'before merging' are overly generic and not natural keywords a user would say. 'Verify work meets requirements' is slightly more specific but still vague. | 1 / 3 |
Distinctiveness Conflict Risk | Phrases like 'completing tasks' and 'implementing major features' are extremely generic and could apply to virtually any skill. There is nothing distinctive that would help Claude differentiate this from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured workflow skill that clearly communicates when and how to request code reviews, with good progressive disclosure to a template file. Its main weaknesses are moderate verbosity in the later sections (Red Flags, Integration) which partially repeat earlier content, and the core dispatch step lacks the executable specificity needed for a copy-paste workflow — the actual tool invocation syntax is abstracted away.
Suggestions
Make the dispatch step fully executable by showing the exact Task tool invocation syntax rather than describing it abstractly ('Use Task tool with superpowers:code-reviewer type')
Consolidate the 'Integration with Workflows' and 'Red Flags' sections — much of this repeats the 'When to Request Review' and 'Act on feedback' guidance already provided
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some unnecessary padding — the 'Red Flags' section with 'Never' items and the 'Integration with Workflows' section repeat concepts already covered. The example section is somewhat verbose for what it communicates. | 2 / 3 |
Actionability | Provides concrete bash commands for getting SHAs and a clear placeholder template, but the actual dispatch mechanism is vague ('Use Task tool with superpowers:code-reviewer type, fill template at code-reviewer.md') — the critical step of how to actually invoke the subagent lacks executable specificity. The example uses pseudo-notation rather than actual tool invocation syntax. | 2 / 3 |
Workflow Clarity | The three-step workflow (get SHAs → dispatch reviewer → act on feedback) is clearly sequenced with explicit prioritization of feedback types (Critical → Important → Minor). The feedback loop of fix-then-proceed is well-defined, and the integration section clarifies when to trigger reviews in different workflow contexts. | 3 / 3 |
Progressive Disclosure | The skill is well-structured as an overview with a clear reference to the template file (code-reviewer.md) for detailed content. Sections are logically organized from when/how/example/integration, and the external reference is one level deep and clearly signaled. | 3 / 3 |
Total | 10 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- obra/superpowers
- Commit
b7a8f76
- 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.