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

48%

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 ./skills/codex-review/SKILL.md

Quality

Content

25%Scale 1-5

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

This skill is essentially a placeholder that provides almost no actionable guidance. It tells Claude to install a tool and use a trigger but never explains what the tool actually does, how to configure it, what the review output looks like, or how CHANGELOG entries are generated. The content fails to teach Claude anything it could act on.

Suggestions

Add concrete examples showing what a code review interaction looks like - include sample input (diff/staged changes) and expected output (review comments, CHANGELOG entry)

Document the actual workflow: how does Claude perform the review, what format should feedback take, how is the CHANGELOG entry structured and where is it inserted

Include the CHANGELOG format specification (e.g., Keep a Changelog format) with a concrete before/after example

Replace external GitHub links with inline content or bundle files that Claude can actually access during execution

Dimension	Reasoning	Score
Conciseness	The content is relatively short but includes unnecessary sections like 'When to Use' that repeat the description, and 'Troubleshooting' and 'Related Skills' sections that add no actionable value. Some padding exists but it's not severely verbose.	3 / 5
Actionability	The skill provides almost no concrete, executable guidance. It tells you to install and 'use /codex-review or natural language triggers' but never shows what the actual review process looks like, what commands to run, what output to expect, or how CHANGELOG generation works. Examples are deferred entirely to an external URL.	1 / 5
Workflow Clarity	The 'Step-by-Step Guide' is only 3 vague steps (install, ensure CLI exists, use trigger) with no validation, no detail on what happens during review, no feedback loops, and no explanation of the CHANGELOG generation workflow.	2 / 5
Progressive Disclosure	All references point to an external GitHub repository rather than bundle files, providing no actual content at any level. There are no bundle files to support the skill, and the references are essentially dead ends for Claude's context. The structure exists but contains no substance.	2 / 5
	Total	8 / 20 Passed

Description

71%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 provides a clear purpose and explicit trigger guidance with a well-structured 'Use when' clause covering three scenarios. Its main weaknesses are moderate specificity—it could detail what aspects of code review are covered—and limited trigger term coverage, missing common synonyms like 'PR review', 'pull request', or 'release notes'. Overall it's a functional description that would work reasonably well for skill selection.

Suggestions

Add more specific actions describing what the code review covers (e.g., 'checks for bugs, style issues, security concerns') and what CHANGELOG format is produced.

Include additional trigger terms and synonyms such as 'PR review', 'pull request', 'release notes', 'change log', 'diff review' to improve matching against natural user language.

Dimension	Reasoning	Score
Specificity	Names the domain (code review, CHANGELOG generation) and mentions integration with Codex AI, but the actions are somewhat high-level. 'Professional code review' and 'auto CHANGELOG generation' are two concrete capabilities, but lacks detail on what the review covers or how CHANGELOG entries are structured.	3 / 5
Completeness	Clearly answers both 'what' (professional code review with auto CHANGELOG generation, integrated with Codex AI) and 'when' (explicit 'Use when' clause with three concrete trigger scenarios: before commits, needing CHANGELOG generation, or reviewing large-scale refactoring).	5 / 5
Trigger Term Quality	Includes relevant terms like 'code review', 'CHANGELOG', 'commits', and 'refactoring', which users might naturally say. However, it misses common synonyms and variations like 'PR review', 'pull request', 'change log', 'release notes', 'diff review', or 'git'.	3 / 5
Distinctiveness Conflict Risk	The combination of code review + CHANGELOG generation + Codex AI integration creates a fairly distinct niche. However, 'professional code review' could overlap with generic code review or linting skills, and 'before commits' could overlap with commit message generation skills.	4 / 5
	Total	15 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: 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.