codex-auth

Setup and manage OpenAI Codex CLI authentication including ChatGPT Plus/Pro OAuth, API keys, and multi-account management. Use when configuring Codex access, switching accounts, or troubleshooting authentication.

Quality

66%

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-auth/SKILL.md

Quality

Content

50%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 highly actionable with concrete commands across many auth scenarios, but it is over-long and monolithic, padding token budget with marketing benefits, dated version notes, and general security advice. Workflows lack explicit validation checkpoints around destructive credential operations.

Suggestions

Trim marketing-style benefits lists and general security platitudes ('Never hardcode keys', 'Rotate keys regularly') that Claude already knows; keep only Codex-specific commands.

Move time-sensitive content ('December 2025', model/version defaults) into a dedicated, clearly-labeled section or reference file so dated info does not inflate the main body.

Split configuration profiles, troubleshooting, and security best practices into separate reference files (e.g. PROFILES.md, TROUBLESHOOTING.md) and add explicit validation checkpoints before destructive steps like 'rm -rf ~/.codex/credentials'.

Dimension	Reasoning	Score
Conciseness	The ~12KB body is noticeably verbose: padded benefits/marketing lists ('4x more usage with Codex-Mini'), general security advice Claude already knows, repeated config.toml blocks, and time-sensitive 'December 2025' dates that the rubric penalizes.	2 / 5
Actionability	Abundant concrete, copy-paste-ready bash and TOML examples (codex login/logout, export OPENAI_API_KEY, pass/keychain storage, curl troubleshooting) with only minor placeholder gaps.	4 / 5
Workflow Clarity	Sequences exist (auth priority order, account-switching script) with some verification calls, but destructive operations like 'rm -rf ~/.codex/credentials' lack explicit validation checkpoints, capping clarity.	3 / 5
Progressive Disclosure	No bundle files exist; the body is monolithic with section headers giving some structure, but config profiles, troubleshooting, and security guidance that belong in separate reference files are all inlined.	3 / 5
	Total	12 / 20 Passed

Description

83%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.

A strong, third-person description that clearly states capabilities and provides an explicit 'Use when...' trigger clause covering configuration, account switching, and troubleshooting. It is specific and distinctive with only minor gaps in action breadth and trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain (Codex CLI authentication) and several concrete actions — 'ChatGPT Plus/Pro OAuth, API keys, and multi-account management' — but stops short of the comprehensive action list needed for a 5.	4 / 5
Completeness	Explicitly answers both what ('Setup and manage OpenAI Codex CLI authentication...') and when ('Use when configuring Codex access, switching accounts, or troubleshooting authentication') with concrete trigger phrases.	5 / 5
Trigger Term Quality	'Use when configuring Codex access, switching accounts, or troubleshooting authentication' provides good natural keyword coverage, though a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Authentication is a clear niche with distinct triggers, but the sibling codex-* skills referenced in the body create minor overlap risk rather than the minimal risk of a 5.	4 / 5
	Total	17 / 20 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
skill_md_line_count	SKILL.md is long (583 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/codex-auth/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.