This description is extremely weak across all dimensions. It fails to describe what the skill actually does, relying entirely on vague 'when' guidance that itself is too generic to be useful. Without knowing the skill's concrete actions, Claude cannot meaningfully select it from a pool of available skills.

Suggestions

Add concrete actions describing what the skill does (e.g., 'Runs test suites, checks code coverage, validates linting rules, and verifies build integrity').

Replace generic phrases like 'completing tasks' and 'implementing major features' with specific trigger terms users would naturally say (e.g., 'run tests', 'check coverage', 'verify build', 'pre-merge check').

Restructure to clearly separate 'what' from 'when', e.g., 'Validates code quality by running tests and checking coverage. Use when the user asks to run tests, verify a feature, or perform pre-merge checks.'

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 extremely generic and would not help distinguish this skill. 'Verify work meets requirements' is slightly more specific but still vague. No natural user keywords are present.	1 / 3
Distinctiveness Conflict Risk	Phrases like 'completing tasks' and 'implementing major features' are so generic they could apply to virtually any skill. This would conflict with many other skills and provides no clear niche.	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 skill with clear workflow sequencing and good progressive disclosure. Its main weakness is that the core action (dispatching the subagent) lacks fully concrete/executable syntax, and some sections contain guidance that's unnecessary for Claude (behavioral 'never' rules, motivational taglines). The example is helpful but could be tighter.

Suggestions

Show the exact Task tool invocation syntax for dispatching the code-reviewer subagent rather than describing it abstractly

Trim the 'Red Flags' section—Claude doesn't need behavioral admonitions like 'never skip review because it's simple'; focus on technical decision criteria instead

Dimension	Reasoning	Score
Conciseness	Generally efficient but has some unnecessary padding like the 'Red Flags' section with 'Never' items that are somewhat obvious behavioral guidance Claude doesn't need, and the 'Core principle' tagline adds no value. The example section is useful but slightly verbose.	2 / 3
Actionability	Provides concrete bash commands for getting SHAs and clear placeholder descriptions, but the actual dispatch mechanism is vague ('Use Task tool with superpowers:code-reviewer type, fill template at code-reviewer.md') without showing the exact invocation syntax. The example uses a mix of pseudocode and real commands rather than being fully executable.	2 / 3
Workflow Clarity	The three-step workflow (get SHAs → dispatch subagent → act on feedback) is clearly sequenced with explicit prioritization of feedback types (Critical → Important → Minor). The integration section clearly maps review timing to different workflow contexts, and the feedback triage acts as a validation checkpoint.	3 / 3
Progressive Disclosure	The skill is well-structured with clear sections (When, How, Example, Integration, Red Flags) and appropriately references the external template at 'requesting-code-review/code-reviewer.md' as a single-level-deep reference. Content is appropriately scoped for the SKILL.md level.	3 / 3
	Total	10 / 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.

Reviewed

1 day ago

Table of Contents

Discovery Implementation Validation