codex
Hand off a task to Codex CLI for autonomous execution. Use when a task would benefit from a capable subagent to implement, fix, investigate, or review code. Codex has full codebase access and can make changes.
83
Quality
76%
Does it follow best practices?
Impact
99%
2.67xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xbigboss/claude-code/codex/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly communicates both what the skill does and when to use it. The explicit 'Use when...' clause with trigger scenarios is a strength. However, the action verbs (implement, fix, investigate, review) are somewhat generic, and the trigger terms could include more natural user phrasings.
Suggestions
Add more specific concrete actions beyond generic verbs, e.g., 'refactor modules', 'debug failing tests', 'implement feature branches'
Include additional natural trigger terms users might say, such as 'delegate', 'run in background', 'parallel task', or 'let Codex handle'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Codex CLI, autonomous execution) and lists some actions (implement, fix, investigate, review code), but these are somewhat generic verbs rather than highly specific concrete actions like 'generate commit messages' or 'create pivot tables'. | 2 / 3 |
Completeness | Clearly answers both what ('Hand off a task to Codex CLI for autonomous execution', 'has full codebase access and can make changes') and when ('Use when a task would benefit from a capable subagent to implement, fix, investigate, or review code') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'subagent', 'implement', 'fix', 'investigate', 'review code', and 'codebase access', but missing common variations users might say like 'delegate', 'background task', 'parallel work', or 'autonomous coding'. | 2 / 3 |
Distinctiveness Conflict Risk | The description clearly carves out a distinct niche around delegating to Codex CLI as a subagent for autonomous execution, which is unlikely to conflict with other coding skills that Claude would execute directly. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with clear workflows and validation checkpoints for managing a Codex subagent. The main weakness is moderate verbosity - some explanatory content could be trimmed, and the document length suggests some content could be progressively disclosed via external references. The concrete commands, flag rules, and monitoring strategies are excellent.
Suggestions
Trim the introductory paragraph and model descriptions - Claude doesn't need explanations of what Codex is or what each model is 'best for'
Consider moving the full CTCO template structure to a separate reference file, keeping only a brief example in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary verbosity, such as explaining what Codex is in the intro (Claude knows this), and the model descriptions could be more terse. The CTCO structure explanation and some sections could be tightened. | 2 / 3 |
Actionability | Provides fully executable bash commands, concrete flag rules, specific file paths, and copy-paste ready command structures. The examples section shows real invocations with expected behavior. | 3 / 3 |
Workflow Clarity | Clear multi-step workflow with explicit sequencing: parse args → assess complexity → gather context → generate prompt → execute → monitor → return result. Includes validation checkpoints (check if in git repo, check if summary exists) and explicit guidance on background vs foreground execution with monitoring strategies. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but it's a fairly long monolithic document. Some content like the full CTCO template and detailed monitoring instructions could potentially be split into referenced files for a cleaner overview, though the current structure is navigable. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- NeverSight/skills_feed
- Commit
5342bca
- 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.