review-checklist
Code review checklist - coordinates specialist reviewers for thorough analysis
75
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
32%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 identifies its domain (code review) and hints at a coordination mechanism with specialist reviewers, but lacks concrete actions and explicit trigger guidance. Without a 'Use when...' clause, Claude cannot reliably determine when to select this skill over other code-related skills.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user asks for code review, PR feedback, pull request analysis, or wants comprehensive code evaluation'
Specify concrete actions the skill performs, such as 'checks for security issues, performance problems, code style, and maintainability'
Clarify what 'specialist reviewers' means - list the types of reviews coordinated (e.g., security review, performance review, style review)
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (code review) and mentions 'coordinates specialist reviewers' and 'thorough analysis', but lacks concrete actions like what types of reviews, what specialists do, or what outputs are produced. | 2 / 3 |
Completeness | Describes what at a high level (coordinates reviewers for analysis) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | 'Code review' and 'checklist' are natural terms users might say, but missing common variations like 'PR review', 'pull request', 'review my code', 'code feedback', or specific review types. | 2 / 3 |
Distinctiveness Conflict Risk | 'Code review checklist' and 'specialist reviewers' provide some distinction, but 'code review' is broad enough to potentially conflict with other code analysis or review skills without clearer scope boundaries. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
92%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-crafted coordination skill that efficiently guides Claude through a sophisticated code review workflow. It excels at actionability with concrete commands, clear branching logic based on diff size, and explicit verification steps to reduce false positives. The only minor weakness is the density of the single file, though the content organization is logical.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is dense with actionable information. No explanations of concepts Claude already knows—jumps straight into commands, patterns, and decision logic. The dispatch strategy threshold and checklist items are all essential. | 3 / 3 |
Actionability | Provides specific commands (git, gh, linter invocations), exact config file patterns to detect tooling, concrete Task call templates with subagent_type, and a complete output format with markdown structure. Copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | Clear branching logic (small vs large diff), explicit verification pass after specialist results, numbered steps for context gathering and static analysis. The merge-and-verify section includes specific validation checks (grep for usages, trace inputs) as feedback loops. | 3 / 3 |
Progressive Disclosure | References external skills (review-security, review-correctness, etc.) appropriately, but the main file is fairly long and dense. Some content like the full output format template and detailed linter detection could potentially be split out, though the single-file approach is workable. | 2 / 3 |
Total | 11 / 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.
- 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.