CtrlK
BlogDocsLog inGet started
Tessl Logo

config-codex-cli

Step-by-step agent workflow to configure the OpenAI Codex CLI on any machine (Linux, macOS, Windows) to use OmniRoute as an OpenAI-compatible backend. Detects OS and shell, writes config.toml and 7 named profiles, sets environment variables, and verifies the setup.

61

Quality

71%

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 ./skills/config-codex-cli/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 efficient and actionable for the long-running-tasks edge case, but it under-delivers on its own headline workflow: the promised config.toml writing and setup verification are not shown, leaving workflow clarity at 3. Tightening the duplicated overview and adding a verification step would raise the score.

Suggestions

Add a concrete config.toml snippet (or the 7 named profiles) and a verification step (e.g. a command or check that confirms the backend is wired) so the core workflow matches the description's promise.

Remove the verbatim 'Overview' duplication of the frontmatter description and drop the empty 'Subcommands' placeholder to recover tokens.

Add an explicit validate/retry checkpoint to the multi-hour recipe (e.g. confirm a long turn survives the idle window) since the section targets fragile overnight sessions.

DimensionReasoningScore

Conciseness

Lean, terse bullets with no basic-concept padding, but the 'Overview' duplicates the frontmatter description verbatim and the 'Subcommands' placeholder line adds redundant tokens.

4 / 5

Actionability

Concrete, executable guidance — exact env vars ('STREAM_IDLE_TIMEOUT_MS=0'), settings paths, and TTL values — but the headline promise of 'writes config.toml and 7 named profiles' has no corresponding config.toml example in the body.

4 / 5

Workflow Clarity

A sequenced 'Recommended multi-hour recipe' exists, but the core config-and-verify workflow promised by the description ('verifies the setup') has no explicit verification checkpoint or feedback loop in the body.

3 / 5

Progressive Disclosure

Well-organized with clear section headers and a single, clearly signaled one-level reference ('docs/guides/CODEX-CLI-CONFIGURATION.md'); no bundle files exist to verify, and a placeholder 'Subcommands' line adds minor noise.

4 / 5

Total

15

/

20

Passed

Description

75%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 is specific and highly distinctive, naming concrete actions and a clear niche, but it omits any explicit 'Use when...' trigger clause, which caps completeness at 3. Adding a natural-language trigger phrase would lift the completeness and trigger-term dimensions.

Suggestions

Append a 'Use when...' clause stating when to invoke this skill, e.g. 'Use when setting up or troubleshooting the Codex CLI with an OmniRoute backend.'

Add a couple of natural user-facing synonyms ('set up', 'Codex setup', 'switch Codex to OmniRoute') alongside the technical proper nouns to broaden trigger coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Detects OS and shell, writes config.toml and 7 named profiles, sets environment variables, and verifies the setup' — giving comprehensive coverage rather than just several.

5 / 5

Completeness

Has a clear 'what' (the configuration workflow and its actions) but no 'Use when...' or equivalent explicit trigger guidance, so per the rubric 'when' is only weakly implied and completeness is capped at 3.

3 / 5

Trigger Term Quality

Good keyword coverage ('Codex CLI', 'OmniRoute', 'OpenAI-compatible backend', 'config.toml', 'configure') but mostly proper-noun jargon with a few natural user phrases and synonyms missing.

4 / 5

Distinctiveness Conflict Risk

A clear, narrow niche — configuring the OpenAI Codex CLI against the OmniRoute backend — with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
diegosouzapw/OmniRoute
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.