Name: codex-review
Rating: 48.8 (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

52%

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/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 brief and well-sectioned but hollow: it offloads the real guidance to an external repository and gives no executable review workflow or validation steps for the CHANGELOG-writing operation it drives.

Suggestions

Add concrete, copy-paste-ready guidance for the review workflow (e.g., how to invoke Codex on a diff, how it produces the CHANGELOG entry) instead of pointing to GitHub.

Include a validation checkpoint (e.g., confirm CHANGELOG.md updated, review comments addressed) since the skill modifies project files.

Move examples and troubleshooting into local reference files (references/EXAMPLES.md, references/TROUBLESHOOTING.md) and link them one level deep instead of relying on an external URL.

Dimension	Reasoning	Score
Conciseness	The body is lean with no over-explanation of concepts Claude already knows, though a few lines ('See the GitHub repository for troubleshooting guides') are filler that earn little.	4 / 5
Actionability	Only the install command ('npx skills add -g BenedictKing/codex-review') is concrete; the core review workflow is reduced to 'Use /codex-review or natural language triggers' with no executable steps.	2 / 5
Workflow Clarity	A rough three-step sequence exists (install, ensure Codex CLI, invoke) but the steps are poorly defined and validation is entirely absent for a flow that writes to CHANGELOG.md.	2 / 5
Progressive Disclosure	Sections are organized, but the actual detail (examples, troubleshooting) is deferred to an external GitHub URL rather than one-level-deep local reference files; no bundle files exist.	3 / 5
	Total	11 / 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 answers both 'what' and 'when' with natural trigger terms, but relies on second-person voice and somewhat generic actions, and 'code review' creates overlap risk with broader review skills.

Suggestions

Rewrite in third person (e.g., 'Performs professional code review...') to avoid the second-person voice penalty.

Make the concrete actions more specific (e.g., name what the review checks or how the CHANGELOG is generated) to lift specificity.

Sharpen the trigger clause with the natural terms users say ('review my diff before commit', 'update CHANGELOG') to improve distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and a few actions ('Professional code review', 'auto CHANGELOG generation', 'integrated with Codex AI') but they stay generic; base ~3 reduced by 1 for second-person voice ('Use when you want...').	2 / 5
Completeness	Explicitly states both what (review + CHANGELOG + Codex integration) and when (a 'Use when...' clause with multiple triggers), but the triggers are slightly less concrete than the anchor-5 example.	4 / 5
Trigger Term Quality	Includes natural phrases users would say ('code review before commits', 'CHANGELOG generation', 'large-scale refactoring') with good coverage, though a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The Codex AI integration and CHANGELOG angle give it a niche, but 'professional code review' is a broad area with real overlap risk against general code-review skills.	3 / 5
	Total	13 / 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/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.