CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-review-checklist

Comprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is code-review-checklist in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

56%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 well-structured and actionable, with a clear review workflow and concrete good/bad code examples, but it is significantly redundant and verbose — three overlapping checklists and advice that restates knowledge Claude already has. Splitting examples and templates into reference files and consolidating the duplicated checklists would improve both conciseness and progressive disclosure.

Suggestions

Consolidate the three overlapping checklists ('How It Works', 'Examples', 'Complete Review Checklist') into one canonical checklist; the current duplication wastes tokens.

Move the three full example checklists and the review comment templates into a references/ file (e.g. references/templates.md) linked from a short overview, enabling progressive disclosure.

Trim sections that restate knowledge Claude already has (basic security practices, obvious do/don't advice like 'Don't Be Rude') and keep only the non-obvious, team-specific guidance.

DimensionReasoningScore

Conciseness

The ~450-line body contains three overlapping checklists ('How It Works', 'Examples', 'Complete Review Checklist'), obvious best-practice advice ('Don't Be Rude', 'Ask Questions'), and extensive explanation of concepts Claude already knows (SQL injection, XSS, DRY, descriptive naming). This is noticeably verbose with several padded sections, though it stays structured and on-topic rather than severely padded.

2 / 5

Actionability

Provides concrete checkbox items, executable ❌/✅ code patterns (parameterized queries, input validation, separated concerns), and copy-paste review comment templates. Guidance is mostly concrete with minor gaps — many checklist items are generic questions rather than specific instructions, keeping it below fully copy-paste-ready.

4 / 5

Workflow Clarity

A clear 6-step sequence (context → functionality → quality → security → performance → tests) with per-step checklists serving as checkpoints, plus a pre-review section. Minor gap: no explicit verification of findings before posting the review; this is not a destructive/batch operation, so no cap applies.

4 / 5

Progressive Disclosure

The single file is well-sectioned with headers, but at ~450 lines the example checklists and review comment templates are inlined content that clearly belongs in separate reference files, and no references/ bundle exists. Structure is present but organization into one-level-deep references is missing.

3 / 5

Total

13

/

20

Passed

Description

50%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 communicates a clear domain and scope but is generic in its actions and entirely missing 'when to use' trigger guidance. Adding an explicit 'Use when...' clause with natural trigger phrases (pull request, PR, code audit) would substantially improve it.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when reviewing pull requests, conducting code audits, or establishing team code review standards.'

Include natural trigger terms and synonyms such as 'pull request', 'PR review', 'code audit', and 'review feedback' so the skill triggers on phrases users actually say.

Replace filler words ('Comprehensive', 'thorough') with one or two concrete outputs, e.g. 'provides step-by-step review checklists and comment templates'.

DimensionReasoningScore

Specificity

Names the domain ('code reviews') and four coverage areas ('functionality, security, performance, and maintainability'), but the only action is the generic 'conducting thorough code reviews' — 'comprehensive' and 'thorough' are filler, so it does not reach the level of listing several specific concrete actions.

3 / 5

Completeness

The 'what' is clear (a checklist covering four review areas), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

'code reviews' is a natural phrase users would say, but common variations like 'pull request', 'PR', or 'code audit' are missing, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

'Code review' is a real niche, but the description does not distinguish this checklist skill from closely related ones (the body itself references @requesting-code-review and @receiving-code-review), leaving overlap risk with similar skills.

3 / 5

Total

12

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

BigSimmo/Communication

Path

.agents/skills/code-review-checklist/SKILL.md

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.