CtrlK
BlogDocsLog inGet started
Tessl Logo

add-codex

Use Codex (OpenAI's codex app-server) as a full agent provider — planning, tool orchestration, MCP tools, server-side history, session resume — alongside or instead of Claude. ChatGPT subscription or OpenAI API key, vault-only via OneCLI. Per-group via `ncl groups config update --provider codex`. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).

63

Quality

75%

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 ./.claude/skills/add-codex/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 content is a tightly written, highly actionable install runbook with deterministic `nc:` directives, a clear multi-step sequence, explicit validation, and a pre-flight checklist. Minor gaps are an inline retry loop at the validate step and a few rationale sentences that could be trimmed.

DimensionReasoningScore

Conciseness

The body is information-dense with no padding of concepts Claude already knows, but includes several rationale sentences (e.g. why no Dockerfile edit is needed, how barrel tests go red) that could be trimmed, landing at the score-4 anchor rather than 5.

4 / 5

Actionability

Guidance is fully executable — exact file paths in `nc:` directives, copy-paste commands (`pnpm run build`, `pnpm vitest run ...`, `ncl groups config update`), and a pinned version — matching the score-5 anchor for copy-paste-ready coverage of common cases.

5 / 5

Workflow Clarity

A clear sequenced workflow (Pre-flight → steps 1–5 → Authenticate → Use it) with an explicit Validate step and a pre-flight skip checklist, but the validate step lacks an inline 'if fails, fix and re-run' loop (recovery is delegated to Troubleshooting), so it sits at 4 rather than 5.

4 / 5

Progressive Disclosure

Good section structure with a clear overview and one well-signaled one-level-deep reference ([docs/provider-migration.md](../../docs/provider-migration.md)); no bundle files exist, and the single-file runbook is appropriately organized, though it is a fairly long single document with only that one external link.

4 / 5

Total

17

/

20

Passed

Description

67%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 well-differentiated, clearly stating what the provider does and drawing a sharp boundary against the similar OpenAI-as-MCP-tool case. Its main weakness is the missing explicit 'when to use' trigger guidance, which caps completeness and lowers trigger-term quality.

Suggestions

Add an explicit 'Use when ...' clause naming natural triggers, e.g. 'Use when the operator wants Codex/ChatGPT as the group's agent backend instead of Claude.'

Soften jargon in the opening ('codex app-server', 'agent provider') with at least one plain-language trigger phrase a user would actually say.

Lead with the action and trigger before the credential/vault mechanics so the 'when' is as prominent as the 'what'.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'planning, tool orchestration, MCP tools, server-side history, session resume' — giving comprehensive coverage of what the provider does, matching the score-5 anchor.

5 / 5

Completeness

The 'what' is clear ('Use Codex ... as a full agent provider'), but there is no explicit 'Use when...' clause or equivalent trigger guidance, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords (Codex, OpenAI, ChatGPT) are present but the phrasing leans technical ('codex app-server', 'agent provider') and lacks the natural 'use when...' trigger phrasing users would say, so it sits at the score-3 anchor rather than 4.

3 / 5

Distinctiveness Conflict Risk

It carves a clear niche and explicitly disambiguates from the nearest rival — 'Distinct from using OpenAI as an MCP tool (where Claude remains the planner)' — giving minimal conflict risk, matching the score-5 anchor.

5 / 5

Total

16

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
nanocoai/nanoclaw
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.