codex-review

OpenAI Codex CLI code review with GPT-5.2-Codex, CI/CD integration

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

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

Quality

Content

65%

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

The content is highly actionable with ready-to-run commands and full CI/CD configs, but it is a long monolithic document that could shed marketing material and split the platform-specific pipelines into reference files. Validation feedback loops are largely absent.

Suggestions

Move the full GitHub/GitLab/Jenkins pipeline examples into separate reference files (e.g. references/ci-github.md) and link to them from a concise overview to improve progressive disclosure.

Add explicit validate→fix→retry checkpoints to the CI/CD review workflow (e.g. parse review.json, fail the build on critical findings, re-run gated).

Trim the 'Why Codex' and 'Claude vs Codex' comparison tables, which sell the tool rather than instruct Claude, to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable commands and configs, but the 'Why Codex for Code Review?' and 'Claude vs Codex' tables plus three full CI/CD pipeline examples (GitHub/GitLab/Jenkins) add marketing and redundancy that could be trimmed, fitting 'Mostly efficient but could be tightened'.	2 / 3
Actionability	Commands, flags, JSON schemas, and complete copy-paste-ready CI/CD YAML/Groovy configs are provided throughout, matching 'Fully executable code/commands; copy-paste ready'.	3 / 3
Workflow Clarity	Installation, auth, and review flows are sequenced with a 'Verify installation' checkpoint and troubleshooting table, but the CI/CD and batch review workflows lack explicit validate→fix→retry feedback loops, which caps workflow clarity at 2 per the rubric notes.	2 / 3
Progressive Disclosure	The ~500-line body is well-sectioned but entirely inline with no bundle files or one-level-deep references; the large GitHub/GitLab/Jenkins configs and cookbook links are content that should be split out, matching 'Some structure but content that should be separate is inline'.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 specific to Codex and CI/CD but reads as a label rather than a trigger-rich sentence and omits an explicit 'Use when' clause. It is serviceable but indistinct from generic code-review skills.

Suggestions

Rewrite as a sentence with concrete actions, e.g. 'Runs OpenAI Codex CLI (GPT-5.2-Codex) code reviews locally and in CI/CD pipelines, outputting structured findings.'

Append an explicit trigger clause: 'Use when the user requests Codex-powered code review, multi-engine review, or CI/CD review automation.'

Add natural trigger terms users would say ('review my PR', 'review the diff', 'CI review') to improve distinctiveness from Claude's built-in review.

Dimension	Reasoning	Score
Specificity	Names the domain ('code review') and integrations ('GPT-5.2-Codex', 'CI/CD integration') but is a noun phrase without enumerating concrete review actions, matching the 'Names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It states what the skill does but the description itself lacks an explicit 'Use when...' trigger (that guidance lives in a separate when-to-use field), so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	'code review' and 'CI/CD' are natural user terms, but 'Codex CLI' and 'GPT-5.2-Codex' lean technical and common variations like 'PR review' or 'review my diff' are absent, fitting 'Some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	'OpenAI Codex CLI code review' carves a clear niche, but the bare term 'code review' overlaps with Claude's built-in review capability, matching 'Somewhat specific but could still overlap with similar skills'.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (511 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: alinaqi/claude-bootstrap
Path: skills/codex-review/SKILL.md
Commit: bb6195f

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.