code-review
Comprehensive code review checklist for pull requests
47
26%
Does it follow best practices?
Impact
76%
1.10xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./code-review/SKILL.mdQuality
Discovery
22%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 is too terse and vague to effectively guide skill selection. It identifies the general domain (code review for PRs) but fails to enumerate specific actions performed or provide explicit trigger conditions. Without a 'Use when...' clause and concrete capability details, Claude would struggle to reliably select this skill over similar ones.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks for a code review, PR review, pull request feedback, or merge request checklist.'
List specific concrete actions the checklist covers, e.g., 'Checks for security vulnerabilities, code style consistency, test coverage, error handling, and performance issues in pull request diffs.'
Include common keyword variations users might say, such as 'PR', 'merge request', 'diff review', 'code feedback', and 'review comments'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'comprehensive code review checklist for pull requests' but does not list any concrete actions like 'checks for security vulnerabilities, validates naming conventions, ensures test coverage.' It names a domain but remains abstract about what it actually does. | 1 / 3 |
Completeness | The description weakly addresses 'what' (a code review checklist) but completely lacks any 'when' clause or explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also vague, so this scores a 1. | 1 / 3 |
Trigger Term Quality | It includes some relevant keywords like 'code review', 'checklist', and 'pull requests' that users might naturally say, but misses common variations like 'PR review', 'PR', 'review comments', 'merge request', or 'diff review'. | 2 / 3 |
Distinctiveness Conflict Risk | While 'code review checklist for pull requests' is somewhat specific, it could overlap with general code review skills, linting skills, or PR description/template skills. It lacks enough specificity to clearly carve out a distinct niche. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
29%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a generic code review checklist that restates widely known best practices without adding actionable, concrete guidance. While it is well-organized into clear categories, it lacks examples, workflow steps, and any specificity that would make it more useful than Claude's existing knowledge. It reads more like a reminder list than an instructional skill.
Suggestions
Add concrete examples for each category showing what a good vs. bad pattern looks like (e.g., an example of hardcoded values vs. configurable ones, or a parameterized vs. non-parameterized SQL query).
Include a workflow for conducting the review: e.g., start with PR description, check diff, run tests locally, leave structured comments, and specify criteria for approve/request-changes decisions.
Add a template or example of a well-structured review comment that Claude should produce, so the output format is clear and actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The checklist is reasonably concise but contains items that are generic knowledge Claude already possesses (e.g., 'SQL queries are parameterized', 'No credentials or secrets in code'). The entire skill is essentially a restatement of widely known code review best practices without adding project-specific or novel guidance. | 2 / 3 |
Actionability | The skill provides only a checklist of abstract criteria with no concrete examples, commands, or executable guidance. It describes what to check but never shows how—no example of a good vs. bad review comment, no specific tool commands, no templates for review feedback. | 1 / 3 |
Workflow Clarity | There is no workflow or sequencing—just a flat list of checkboxes. There's no guidance on how to conduct the review (e.g., order of operations, what to do when issues are found, how to communicate findings, when to approve vs. request changes). | 1 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines with no need for external references, the content is organized into clear, well-labeled sections. The six categories provide logical grouping and easy scanning. | 3 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- block/agent-skills
- Commit
60bfdad
- 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.