CtrlK
BlogDocsLog inGet started
Tessl Logo

codex

Run, configure, and troubleshoot OpenAI Codex CLI in non-interactive headless environments. Use for Codex automation in Bash or PowerShell, native Windows or WSL2, shell scripts, CI/CD, Docker, Kubernetes, remote servers, agent harnesses, or batch jobs; for constructing `codex exec` commands; selecting sandbox and approval modes; consuming JSONL events or structured output; resuming sessions; passing prompts through stdin; and handling failures caused by unavailable interactive input such as `request_user_input`.

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

A lean, highly actionable guide built from executable code blocks, clear sequenced workflows with validation checkpoints, and properly split one-level references. The only minor weakness is a handful of framing/clarifying sentences that slightly duplicate the description or state the obvious.

Suggestions

Trim the opening line 'Use Codex CLI as a deterministic, non-interactive worker suitable for automation and agent orchestration.' — it restates the frontmatter description without adding operational value.

Drop or merge parenthetical clarifications like 'It disables Codex approvals and sandboxing.' after --yolo, since the audience already understands the flag from context.

DimensionReasoningScore

Conciseness

Dense, operational prose with no explanations of concepts Claude already knows (what a CLI/CI/Docker is); however the opening framing line and a few clarifying asides ('It disables Codex approvals and sandboxing') could be trimmed, placing it just below the 'every token earns its place' anchor-5.

4 / 5

Actionability

Provides numerous copy-paste-ready, fully executable bash commands with concrete flags covering read-only, workspace-write, --yolo, structured output, resume, stdin, and auth cases, matching the anchor-5 example.

5 / 5

Workflow Clarity

Multi-step processes are clearly sequenced with validation checkpoints and feedback loops: 'Diagnose Failures' (run --help, inspect stderr/JSONL, re-run with smaller task), 'Completion Standard' checklist, 'Handle request_user_input' sequence, and explicit validation ('Validate repository diffs and test results before treating a run as successful').

5 / 5

Progressive Disclosure

SKILL.md is a clear overview that splits detail into two real, one-level-deep, well-signaled reference files — [references/windows.md] and [references/recipes.md] (both verified to exist) — each referenced at the end of the relevant section with a scoped description of its contents.

5 / 5

Total

19

/

20

Passed

Description

100%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 precise, third-person description that names concrete capabilities, supplies an explicit 'Use for' trigger clause covering many natural environments, and occupies a distinct niche with low conflict risk. It hits the top anchor on all four dimensions without verbosity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Run, configure, and troubleshoot', 'constructing codex exec commands', 'selecting sandbox and approval modes', 'consuming JSONL events', 'resuming sessions', 'passing prompts through stdin', 'handling failures' — with comprehensive coverage, matching the anchor-5 example.

5 / 5

Completeness

Explicitly answers both 'what' ('Run, configure, and troubleshoot OpenAI Codex CLI in non-interactive headless environments') and 'when' ('Use for Codex automation in ... CI/CD, Docker, Kubernetes, remote servers, agent harnesses, or batch jobs') with concrete trigger phrases, matching the anchor-5 example.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and environments users actually name — 'Bash or PowerShell', 'native Windows or WSL2', 'CI/CD', 'Docker', 'Kubernetes', 'remote servers', 'agent harnesses', 'batch jobs'; file extensions are N/A for a CLI skill so they are not missed.

5 / 5

Distinctiveness Conflict Risk

Carves a clear niche — non-interactive headless Codex CLI automation — with distinct triggers (codex exec, JSONL events, request_user_input failures, sandbox/approval modes) that are unlikely to fire for unrelated skills.

5 / 5

Total

20

/

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
XiaomiMiMo/MiMo-Code
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.