codex-review

Professional code review with auto CHANGELOG generation, integrated with Codex AI

Quality

45%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./docs/v19.7/configuration/agent/skills_external/antigravity-awesome-skills-main/skills/codex-review/SKILL.md

Quality

Content

40%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 stub that outsources nearly all substantive guidance to an external repository. It is structurally tidy and lean, but a Claude instance reading it would not know how to actually perform a review or generate a changelog. The core value of the skill is undocumented.

Suggestions

Replace the external-GitHub pointers with in-file concrete guidance: an example review invocation, the CHANGELOG format to generate, and where the CHANGELOG entry is appended.

Expand the step-by-step guide with executable specifics, e.g. the exact command to check for Codex CLI ("codex --version") and an explicit list of natural-language triggers.

Cut the empty Troubleshooting and Overview sections (which duplicates the description verbatim) or fill them with actual content, so every section earns its tokens.

Dimension	Reasoning	Score
Conciseness	The body is short and free of concept over-explanation, but tokens are wasted on empty sections: "Troubleshooting: See the GitHub repository" carries no information, the Overview repeats the description verbatim, and the Related Skills list adds nothing. Not 5 because several tokens do not earn their place; not 2 because there is no padded explanation of things Claude already knows.	3 / 5
Actionability	Only one executable command is given ("npx skills add -g BenedictKing/codex-review"); the core skill behavior — how the review is performed and how the CHANGELOG is generated — is never specified, and steps like "Ensure Codex CLI is installed" and "Use /codex-review or natural language triggers" are high-level hints missing the specific steps to execute. Not 3 because no concrete guidance exists for the skill's actual task; not 1 because one concrete, runnable command is present.	2 / 5
Workflow Clarity	A rough three-step sequence exists (install, ensure CLI, invoke), but the steps are trivially thin and poorly defined — no mention of which natural-language triggers work, how to verify the Codex CLI, or any validation checkpoint. Not 3 because the gaps go beyond missing checkpoints into undefined steps; not 1 because a coherent sequence is listed.	2 / 5
Progressive Disclosure	The ~35-line body is well organized with clear section headers, and nothing is inlined that belongs in a separate file (satisfying the simple-skill guideline). Not 5 because essential content — examples and troubleshooting — is outsourced to an external GitHub URL rather than well-signaled one-level-deep bundle references, a minor organization gap.	4 / 5
	Total	11 / 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 names its domain and two concrete capabilities but reads more like a tagline than a trigger specification. It lacks any "when to use" guidance and leans on the buzzword "Professional". Adequate but not competitive with well-formed descriptions.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to review code before committing, review a diff or pull request, or generate/update a CHANGELOG."

Replace the buzzword "Professional" with concrete capabilities, e.g. "Reviews staged changes and diffs for bugs and style issues, and generates CHANGELOG entries from conventional commits."

Include natural synonyms users would say ("code review", "review my diff", "changelog", "release notes") to improve trigger-term coverage and distinguish the skill from built-in review skills.

Dimension	Reasoning	Score
Specificity	"Professional code review with auto CHANGELOG generation" names the domain plus 1-2 concrete actions (review, changelog generation), but "Professional" is fluff and no further specifics are given about what the review actually does. Not 4 since it does not list several specific actions; not 2 since it goes beyond a bare domain label.	3 / 5
Completeness	The description gives a clear "what" (code review plus automatic CHANGELOG generation) but contains no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because "when" is entirely missing rather than just under-specified.	3 / 5
Trigger Term Quality	"code review", "CHANGELOG", and "Codex AI" are relevant keywords, but common user phrasings like "review my diff", "before committing", or "pull request" are absent. Not 4 because few natural trigger phrases are present at all; not 2 because the keywords are domain-relevant rather than purely generic.	3 / 5
Distinctiveness Conflict Risk	"integrated with Codex AI" provides a niche, but the generic "code review" framing overlaps with common built-in review and commit-message skills. Not 4 because the overlap risk is more than minor; not 2 because the Codex integration is a genuine distinguisher.	3 / 5
	Total	12 / 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: duclm1x1/Dive-Ai
Path: docs/v19.7/configuration/agent/skills_external/antigravity-awesome-skills-main/skills/codex-review/SKILL.md
Commit: 20ba150

Reviewed: 6 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.