codex
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.
Overall
score
84%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
90%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 well-structured description with strong trigger terms and explicit 'Use when' guidance. The main weakness is that the capability descriptions are somewhat generic (code analysis, refactoring, automated editing) rather than listing specific concrete actions the skill can perform. The mention of GPT-5.2 adds context but doesn't clarify capabilities.
Suggestions
Add more specific concrete actions beyond 'code analysis, refactoring, or automated editing' - e.g., 'generate code patches, apply multi-file edits, explain code changes'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Codex CLI) and some actions (code analysis, refactoring, automated editing), but doesn't list comprehensive concrete actions. The capabilities are somewhat vague - 'code analysis' and 'automated editing' are broad categories rather than specific operations. | 2 / 3 |
Completeness | Explicitly answers both what (run Codex CLI for code analysis, refactoring, automated editing) and when (starts with 'Use when the user asks to run Codex CLI...'). Has clear explicit trigger guidance at the beginning. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'codex exec', 'codex resume', 'OpenAI Codex', 'code analysis', 'refactoring', 'automated editing'. Good coverage of both command-specific and task-oriented keywords. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche - specifically targets Codex CLI commands ('codex exec', 'codex resume') and OpenAI Codex references. Unlikely to conflict with general coding skills due to the specific tool focus and command names. | 3 / 3 |
Total | 11 / 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, actionable skill with clear workflows and good use of tables for quick reference. The main weaknesses are minor redundancy in the model information and the monolithic structure that could benefit from splitting reference material. The explicit permission checks and error handling demonstrate good safety practices.
Suggestions
Remove duplicate model entries (gpt-5.2 and gpt-5.2-max appear to have identical stats) or clarify their differences
Consider moving the detailed Model Options table to a separate MODELS.md reference file to keep the main skill leaner
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some redundancy (model table has duplicate gpt-5.2 and gpt-5.2-max with same stats, CLI version section repeats default model info). The quick reference table is well-structured but some explanatory text could be tighter. | 2 / 3 |
Actionability | Provides concrete, copy-paste ready commands with specific flags, clear syntax for resume operations, and a practical quick reference table. The command patterns are executable and complete. | 3 / 3 |
Workflow Clarity | Clear numbered sequence for running tasks with explicit validation checkpoints (ask user for reasoning effort, confirm permissions for high-impact flags, summarize outcomes). Error handling section provides explicit feedback loops for failures and partial results. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and tables, but everything is inline in a single file. The model options table and reasoning effort levels could be split to a reference file for a cleaner overview, though the current length (~80 lines) is borderline acceptable. | 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 — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
body_examples | No examples detected (no code fences and no 'Example' wording) | Warning |
Total | 13 / 16 Passed | |
- 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.