code-review

Code review practices with technical rigor and verification gates. Use for receiving feedback, requesting code-reviewer subagent reviews, or preventing false completion claims in pull requests.

Quality

76%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

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

Quality

Discovery

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 has a clear structure with an explicit 'Use for...' clause, which is good for completeness. However, the specific capabilities described are somewhat abstract (e.g., 'verification gates', 'false completion claims') rather than concrete actions, and the trigger terms miss common user phrasings. The jargon 'code-reviewer subagent' reduces accessibility for typical users.

Suggestions

Replace abstract phrases like 'verification gates' and 'false completion claims' with concrete actions such as 'validate test results before marking PR complete', 'check for unresolved review comments', or 'run automated checks on diffs'.

Add natural trigger term variations users would actually say, such as 'PR review', 'review my code', 'code feedback', 'merge request', or 'review comments'.

Replace internal jargon 'code-reviewer subagent' with more universally understood language like 'automated code review checks' or 'code review automation'.

Dimension	Reasoning	Score
Specificity	Names the domain (code review) and some actions ('receiving feedback', 'requesting code-reviewer subagent reviews', 'preventing false completion claims'), but these are somewhat abstract rather than concrete technical actions like 'analyze diffs', 'check test coverage', or 'validate linting results'.	2 / 3
Completeness	Clearly answers both what ('code review practices with technical rigor and verification gates') and when ('Use for receiving feedback, requesting code-reviewer subagent reviews, or preventing false completion claims in pull requests'), with an explicit 'Use for...' clause providing trigger guidance.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'code review', 'pull requests', and 'feedback', but misses common natural variations users might say such as 'PR review', 'review my code', 'code quality', 'review comments', or 'merge request'. The term 'code-reviewer subagent' is internal jargon unlikely to be used by users.	2 / 3
Distinctiveness Conflict Risk	The code review focus provides some distinctiveness, but 'receiving feedback' is quite broad and could overlap with general coding assistance skills. The 'verification gates' and 'false completion claims' aspects add some niche specificity, but the overall scope could still conflict with general code quality or CI/CD skills.	2 / 3
	Total	9 / 12 Passed

Implementation

85%

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 strong actionability and excellent progressive disclosure. The verification gates protocol is particularly well done with concrete commands and explicit validation checkpoints. The main weakness is moderate redundancy between the overview, decision tree, protocol summaries, and bottom line sections, which could be tightened to save tokens.

Suggestions

Reduce redundancy by consolidating the overview, decision tree, and bottom line—the same triggers and principles are stated three times in slightly different formats.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient but has some redundancy—the overview, quick decision tree, protocol summaries, and bottom line all repeat similar information. The protocol sections duplicate what's in the referenced files while also pointing to those files, creating partial redundancy.	2 / 3
Actionability	Provides concrete, executable bash commands for verification, specific git commands for requesting reviews, explicit behavioral rules (what to say/not say), and a clear decision tree. The protocols give copy-paste ready commands and specific patterns to follow.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (READ → UNDERSTAND → VERIFY → EVALUATE → RESPOND → IMPLEMENT; IDENTIFY → RUN → READ → VERIFY → CLAIM). Verification gates are explicit with clear checkpoints, feedback loops (fix Critical immediately, re-verify), and red flags for stopping. The decision tree provides clear branching logic.	3 / 3
Progressive Disclosure	Excellent structure with a concise overview, inline summaries of each protocol, and clear one-level-deep references to detailed files (references/code-review-reception.md, references/requesting-code-review.md, references/verification-before-completion.md). Navigation is well-signaled with 'Full protocol:' markers.	3 / 3
	Total	11 / 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: secondsky/claude-skills
Commit: 88da5ff

Reviewed: 13 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.