codex

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.

Quality

92%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

The body is highly actionable with strong workflow checkpoints and clean organization, but it carries redundancy and time-sensitive detail that inflate token cost. Tightening the repeated steps and isolating version/date info would lift conciseness without losing clarity.

Suggestions

Remove the duplicated step numbering (two "3." entries) and consolidate the repeated --skip-git-repo-check and resume-syntax explanations into one canonical location.

Trim the marketing-style "GPT-5.2 Advantages" and "Cached Input Discount" paragraphs, keeping only facts Claude cannot infer from the flag/option tables.

Move time-sensitive details (Codex CLI v0.57.0 requirement, knowledge-cutoff date) into a clearly labeled version/compatibility note so they do not penalize the core conciseness of the workflow.

Dimension	Reasoning	Score
Conciseness	Mostly efficient command reference, but padded with redundancy (duplicate numbered step "3.", --skip-git-repo-check stated twice, resume syntax repeated across sections) and marketing fluff ("GPT-5.2 Advantages: 76.3% SWE-bench..."), plus time-sensitive version/date info (v0.57.0, "Knowledge cutoff: September 30, 2024") not isolated in a deprecated section; not 3 because several tokens do not earn their place.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands (e.g. `echo "..." \| codex exec --skip-git-repo-check resume --last 2>/dev/null`) and concrete flag/quick-reference tables; not 2 which would offer only pseudocode or incomplete guidance.	3 / 3
Workflow Clarity	Clear numbered sequence with explicit checkpoints (ask reasoning effort, ask permission for high-impact flags, stop on non-zero exit) and an Error Handling feedback loop, with destructive ops gated by approval; not 2 where validation gaps or implicit checkpoints would be present.	3 / 3
Progressive Disclosure	Single well-organized file with clearly labeled sections and no nested references; with no bundle files present, the clean section structure satisfies progressive disclosure for a self-contained skill.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 concise, specific, and triggers cleanly on natural user phrasing with an explicit 'Use when' clause. The only soft spot is the trailing buzzword 'state-of-the-art software engineering', which adds no trigger value.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("code analysis, refactoring, or automated editing") plus specific subcommands ("codex exec, codex resume"), matching the anchor for listing several specific concrete actions; not the level below which only names a domain.	3 / 3
Completeness	Explicitly answers both what (run Codex CLI for analysis/refactoring/editing) and when via a clear "Use when the user asks..." trigger clause; not 2 where the when is only implied.	3 / 3
Trigger Term Quality	Covers natural terms a user would actually say ("run Codex CLI", "codex exec", "codex resume", "OpenAI Codex", "refactoring"); not the level below which misses common variations.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to the Codex CLI / OpenAI Codex niche with distinct command-level triggers, making conflict with other skills unlikely; not 2 which could still overlap with similar skills.	3 / 3
	Total	12 / 12 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: jdrhyne/agent-skills
Commit: a4d31ad

Reviewed: 11 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.