code-review-checklist

Code review guidelines covering quality, security, and best practices.

Quality

34%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agent/skills/code-review-checklist/SKILL.md

Quality

Content

32%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is little more than a link directory: an empty checklist section and eight numbered links to sub-skill files that are not present in the bundle. It is token-lean but offers no actionable review guidance, no defined workflow, and broken navigation.

Suggestions

Populate the 'Quick Review Checklist' with concrete, copy-paste-ready review items so the body is actionable on its own.

Either add the referenced ./sub-skills/*.md files to the bundle or remove/inlining the broken links so navigation resolves.

Turn the module list into a sequenced workflow with explicit validation checkpoints (e.g. run tests, re-check after fixes) for the review process.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean with no padding or over-explanation of concepts Claude already knows, so it respects the token budget well. It stops short of 5 because the '## Quick Review Checklist' header is empty — a token that does not earn its place and could be trimmed.	4 / 5
Actionability	The body provides no concrete, executable guidance: the 'Quick Review Checklist' section is empty and the eight entries are only category links with no instructions, code, or commands. This matches the 'entirely vague or abstract; no concrete code or commands' anchor.	1 / 5
Workflow Clarity	There is a rough sequence in the numbered list of eight modules, but each step is just a category link to a nonexistent file with no defined actions and no validation checkpoints. This fits the 'rough sequence present but many gaps; steps poorly defined; validation absent' anchor rather than the incoherent/sequence-missing level at 1.	2 / 5
Progressive Disclosure	Although the references are one-level-deep and clearly signaled in form, all eight links point to a ./sub-skills/ directory that does not exist and the 'Quick Review Checklist' overview is empty, so the disclosure structure promises detail it cannot deliver and navigation is broken. This makes it effectively minimal/non-functional, matching the score-2 anchor better than the 'some structure' level at 3.	2 / 5
	Total	9 / 20 Passed

Description

36%Weight 40%Scale 1-5

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 names the code-review domain but stays at a high, generic level: it lists topic areas rather than concrete actions and omits any 'Use when' trigger guidance. It is distinguishable enough to avoid total genericness yet lacks the specificity and explicit triggers needed for strong routing.

Suggestions

Add concrete actions, e.g. 'Reviews diffs for correctness bugs, security vulnerabilities, and performance issues'.

Append an explicit trigger clause such as 'Use when reviewing a pull request, staged diff, or code change for quality and security.'

Include natural synonyms users say — 'PR review', 'pull request', 'diff review' — to improve trigger matching.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Code review guidelines') but offers no concrete actions, only generic topic areas ('quality, security, and best practices') rather than things like 'identifies bugs' or 'flags vulnerabilities'. It sits at the anchor that names the domain with minimal/generic actions, not yet at 3 which requires 1-2 concrete actions.	2 / 5
Completeness	It has only a vague 'what' ('guidelines covering quality, security, and best practices') and no 'when' clause at all — there is no 'Use when...' trigger guidance. This matches the score-2 anchor (vague what, no when); the missing trigger clause also caps completeness at 3 per the guidelines, and it does not reach 3 because the 'what' itself is vague.	2 / 5
Trigger Term Quality	'Code review' is a natural phrase users would actually say, and 'quality', 'security' add some relevant coverage, but common synonyms and variations like 'PR review', 'pull request', 'diff review', or 'peer review' are missing. It matches the anchor with some relevant keywords but lacking common variations, falling short of the comprehensive coverage at 4.	3 / 5
Distinctiveness Conflict Risk	'Code review' carves out a somewhat specific niche, but the broad trailing phrase 'quality, security, and best practices' widens it so it could still overlap with other development/code-quality skills. It fits the 'somewhat specific but could still overlap' anchor rather than the mostly-distinct level at 4.	3 / 5
	Total	10 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 8 missing	Warning

	Total	14 / 16 Passed

Repository: Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI
Path: .agent/skills/code-review-checklist/SKILL.md
Commit: c4a059b

Reviewed: 1 hour 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.