CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/codex-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

47%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 skill body is lean and well-sectioned but almost entirely content-free: it defers its core value (examples, troubleshooting, actual review guidance) to an external GitHub repository rather than providing executable instructions. A user following it would know how to install the skill but not what it does or how to run a review.

Suggestions

Add a concrete review workflow: how to invoke Codex on a diff (with the actual command), what to do with its output, and how the CHANGELOG entry is generated and appended.

Include a short CHANGELOG format example (input diff -> generated entry) so output style is reproducible, mirroring the commit-message example pattern.

Move the GitHub-hosted examples and troubleshooting into local reference files (e.g., references/examples.md) so the skill is self-contained and the deferral is a well-signaled one-level reference.

Replace 'Ensure Codex CLI is installed' with the actual installation/verification command (e.g., a version check) so step 2 is executable.

DimensionReasoningScore

Conciseness

The body is short, uses clear headers, and does not explain concepts Claude already knows; minor waste comes from boilerplate in 'Limitations' and sections that merely link out ('See GitHub Repository for examples'), fitting 'efficient; minor instances that could be trimmed'.

4 / 5

Actionability

The only concrete, executable content is the install command 'npx skills add -g BenedictKing/codex-review'; there is no review procedure, no Codex CLI invocation, and no CHANGELOG format example, matching 'minimal concrete guidance; high-level hints but missing the specific steps to execute'.

2 / 5

Workflow Clarity

The 'Step-by-Step Guide' lists three trivial setup steps (install, ensure Codex CLI, invoke the command) with no description of the actual review-to-CHANGELOG workflow, no checkpoints, and no validation ('Ensure Codex CLI is installed' gives no command), matching 'rough sequence present but many gaps; validation absent'.

2 / 5

Progressive Disclosure

The body is under 50 lines with clearly organized sections and no bundle files to reference. It falls short of anchor 5 because examples and troubleshooting are deferred to an external GitHub URL instead of local reference files Claude can actually load.

4 / 5

Total

12

/

20

Passed

Description

66%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 follows a good structure with an explicit 'Use when...' trigger clause covering three scenarios, and its trigger terms are reasonably natural. Its main weaknesses are a vague 'what' (never stating what the review actually produces or does) and generic code-review phrasing that risks overlap with other review skills.

Suggestions

Replace 'Professional code review' with the concrete outputs and actions of the skill (e.g., 'Analyzes git diffs, flags bugs and style issues, and generates a categorized CHANGELOG.md entry').

Add natural trigger synonyms users would say, such as 'review my changes', 'review the diff/staged changes', or 'update the changelog'.

Sharpen distinctiveness by leading with what makes this skill unique (Codex-powered analysis plus automatic CHANGELOG generation) rather than the generic 'code review' phrase.

DimensionReasoningScore

Specificity

The phrase 'Professional code review with auto CHANGELOG generation, integrated with Codex AI' names the domain and two actions (review, CHANGELOG generation), but 'professional code review' does not state what the skill concretely does (e.g., analyze diffs, flag issues), matching the 'domain and 1-2 concrete actions, but not comprehensive' anchor.

3 / 5

Completeness

Both a 'what' ('Professional code review with auto CHANGELOG generation, integrated with Codex AI') and an explicit 'Use when...' clause with three trigger conditions are present. It falls short of anchor 5 because the 'what' is generic rather than a concrete capability list with concrete trigger phrases.

4 / 5

Trigger Term Quality

Natural phrases like 'code review before commits', 'CHANGELOG generation', and 'reviewing large-scale refactoring' are present and would be said by users, but common variations such as 'review my changes', 'review the diff', or 'PR review' are missing, fitting the 'good keyword coverage; a few natural terms missing' anchor.

4 / 5

Distinctiveness Conflict Risk

Generic 'code review' wording overlaps many existing review skills and built-in review capabilities; only the CHANGELOG generation and Codex integration provide differentiation, matching 'somewhat specific but could still overlap with similar skills'.

3 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

BigSimmo/Communication

Path

.agents/skills/codex-review/SKILL.md

Reviewed

Table of Contents

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.