Name: codex-review
Rating: 52.8 (1 reviews)
Author: administrakt0r

codex-review

Professional code review with auto CHANGELOG generation, integrated with Codex AI. Use when you want professional code review before commits, you need automatic CHANGELOG generation, or reviewing large-scale refactoring.

Quality

58%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/codex-review/SKILL.md

The canonical home for this skill is codex-review in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

43%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 concise and well-sectioned but offers little executable guidance: the actual review workflow, CHANGELOG format, and troubleshooting all live off-site, so a reader cannot act on the skill from the file alone.

Suggestions

Add an executable example showing `/codex-review` invocation and the CHANGELOG entry format it produces, so the skill is actionable without leaving the file.

Replace 'Ensure Codex CLI is installed' with the concrete install/verification command, and add a validation checkpoint (e.g. confirm CHANGELOG.md was updated) to the step-by-step workflow.

Inline at least a minimal troubleshooting entry locally instead of deferring all troubleshooting to the external repo.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding or explanations of concepts Claude already knows; the only trimmable redundancy is that the Overview and When-to-Use sections restate the frontmatter description. It is not a 5 because of that mild duplication.	4 / 5
Actionability	Beyond the install command (`npx skills add -g ...`), guidance is high-level: 'Ensure Codex CLI is installed' gives no install command, and examples/troubleshooting are deferred to an external GitHub repo. This matches the score-2 anchor of minimal concrete guidance with missing executable steps.	2 / 5
Workflow Clarity	The Step-by-Step Guide lists a rough sequence (install, ensure Codex CLI, run `/codex-review`) but steps are poorly defined and there are no validation checkpoints or error-handling guidance. It is not a 1 because a sequence does exist.	2 / 5
Progressive Disclosure	Sections are clearly labeled and the body is short, but all substantive detail (examples, troubleshooting) is deferred to an external GitHub URL rather than local one-level-deep references, leaving the SKILL.md as a pointer. It is not a 4 because the deferred content is external and substantive rather than minor.	3 / 5
	Total	11 / 20 Passed

Description

73%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 answers both 'what' and 'when' clearly with natural trigger terms and a recognizable niche, but it loses points for second-person voice and only modest action specificity.

Suggestions

Rewrite in third person to avoid the 'Use when you want...' second-person voice (e.g. 'Use when professional code review is needed before commits').

Add one or two more concrete capabilities (e.g. 'generates categorized changelog entries from diffs', 'runs Codex CLI on staged changes') to lift specificity toward comprehensive coverage.

Include natural synonyms/extensions such as 'commit', 'pull request', and 'codex CLI' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('Professional code review') and two concrete actions ('auto CHANGELOG generation', 'integrated with Codex AI'), matching the score-3 anchor, but the description uses second person ('Use when you want...') which per the judging guidelines reduces the specificity score by one. It is not a 1 because it does name real actions rather than being purely vague.	2 / 5
Completeness	It explicitly states what the skill does ('Professional code review with auto CHANGELOG generation, integrated with Codex AI') and gives concrete 'Use when...' trigger clauses, matching the score-5 anchor for answering both what and when.	5 / 5
Trigger Term Quality	Phrases like 'professional code review before commits', 'automatic CHANGELOG generation', and 'reviewing large-scale refactoring' are natural things a user would say, giving good keyword coverage. It is not a 5 because common synonyms and file/CLI extensions (e.g. 'commit', 'PR review', 'codex') are only partially covered.	4 / 5
Distinctiveness Conflict Risk	The 'integrated with Codex AI' framing plus CHANGELOG generation carves a distinct niche, but 'professional code review before commits' overlaps broadly with general code-review skills, so it is mostly distinct rather than minimal-conflict.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/codex-review/SKILL.md
Commit: 57c135b

Reviewed: 2 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.