code-review

Run a final code review on a pull request

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/code-review/SKILL.md

Quality

Content

76%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 a tight, actionable orchestrator instruction set with excellent token efficiency, but its batch workflow lacks validation/dedup checkpoints and it provides no concrete examples of subagent invocation or finding format. It is well above average for a short instruction skill.

Suggestions

Add a validation checkpoint after subagents return, e.g. confirm every code-review-* skill was covered and deduplicate overlapping findings before reporting.

Include a short example of the expected finding format (numbered Markdown with file path and line number) so output is copy-paste consistent.

Group the directives under light section headers (e.g. "## Dispatch", "## Report") to improve scannability without adding length.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanations Claude doesn't need; every line is an actionable directive and every token earns its place.	5 / 5
Actionability	Directives like "One subagent per skill", "Pass full skill path to subagents", and "Each finding must include a specific file path and line number" are concrete, but no example subagent invocation or finding-format template is given.	4 / 5
Workflow Clarity	A rough sequence exists (dispatch subagents, collect all issues, format as numbered Markdown, conditionally label), but there are no validation checkpoints; because dispatching one subagent per skill is a batch operation, the rubric caps this at 3.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no external references needed and all content appropriately inline, but it is flat prose with no section headers, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

61%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 is concise and names a concrete, distinct action with natural trigger terms, but it omits any explicit "when to use" guidance and lacks synonyms like "PR". It is solid but incomplete.

Suggestions

Add an explicit trigger clause, e.g. "Use when performing a final code review on a pull request before merge."

Include the common synonym "PR" alongside "pull request" to broaden natural trigger coverage.

Optionally hint at scope (e.g. "aggregating findings from all code-review skills") to sharpen the distinction from individual review skills.

Dimension	Reasoning	Score
Specificity	"Run a final code review on a pull request" names a specific domain (code review on a PR) and one concrete action, matching the anchor for 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	It clearly states the "what" (run a final code review) but has no "Use when..." or equivalent trigger guidance for the "when", which the guidelines cap at 3.	3 / 5
Trigger Term Quality	"code review" and "pull request" are natural phrases users say, giving good keyword coverage; the common synonym "PR" is missing, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	"final code review on a pull request" carves a mostly-distinct orchestrator niche, with only minor overlap risk against the other code-review-* skills referenced in the body.	4 / 5
	Total	14 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/codex
Path: .codex/skills/code-review/SKILL.md
Commit: 78245b4

Reviewed: 5 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.