codex-debugging

Codex debugging: codex-rs core/tui/exec/cli/app-server/config.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/codex-debugging/SKILL.md

Quality

Content

86%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 an exemplary lean debugging skill: concrete, executable search/read commands, a clear four-step investigative workflow, and clean section structure with no filler. The only real weaknesses are minor executability gaps — a hardcoded repo path, an un-expanded `$browser-use` placeholder, and implicit rather than explicit verification checkpoints.

Dimension	Reasoning	Score
Conciseness	The ~30-line body is lean and assumes competence: no concept explanations, no padding, every line either commands, workflow steps, or a scoping note — matching "every token earns its place". It is not below 5 because nothing present could be cut without losing information.	5 / 5
Actionability	The guidance is mostly executable: copy-paste-ready commands (`sed -n '1,220p' codex-rs/AGENTS.md`, `rg "<symbol\|setting\|error\|feature>" codex-rs/{core,tui,...}`) and a numbered workflow. It falls short of 5 due to minor gaps — the hardcoded `~/Projects/codex` path and the un-expanded `$browser-use` placeholder are not universally executable as written.	4 / 5
Workflow Clarity	The four-step workflow (classify the behavior → read owning module and tests → check config after understanding the contract → prefer small repros) is a clear, well-ordered sequence. It is not 5 because checkpoints are implicit rather than explicit — there is no stated verify/confirm loop after forming a hypothesis — though as read-only investigation it carries no destructive risk, so the feedback-loop cap does not apply.	4 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is organized into well-signaled sections (Source First, Workflow, Notes), which per the scoring notes earns a 5 for a skill of this size. The only referenced file, `codex-rs/AGENTS.md`, is a one-level pointer into the user's own repo, not a nested bundle hop.	5 / 5
	Total	18 / 20 Passed

Description

56%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 concise and clearly scoped to the Codex codebase, with good module-level keywords, but it functions as a domain label rather than a capability statement: no concrete actions are described and there is no explicit "Use when" trigger clause. Adding one or two action verbs and a trigger sentence would lift most dimensions.

Suggestions

Add 1-2 concrete capability verbs, e.g., "Traces behavior and locates the owning module across codex-rs core/tui/exec/cli/app-server/config."

Append an explicit trigger clause, e.g., "Use when investigating Codex CLI/TUI behavior, config parsing, MCP/app wiring, or runtime errors."

Include a few natural user-side synonyms ("Rust", "crash", "config.toml", "OpenAI CLI") to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Codex debugging") and enumerates the target modules ("core/tui/exec/cli/app-server/config") but states no concrete actions — it is a bare label plus a module list, matching "names the domain but actions are minimal or generic". It does not reach 3 because there is no action verb or capability statement at all (e.g., no "locates", "traces", or "fixes" behavior).	2 / 5
Completeness	It has a clear "what" (debugging across the listed codex-rs crates) but no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. It is not 4 because the "when" is entirely absent rather than merely under-specified.	3 / 5
Trigger Term Quality	Good natural keyword coverage: "Codex", "debugging", "codex-rs", "core", "tui", "exec", "cli", "app-server", and "config" are all terms a user would plausibly say when needing this skill. It falls short of 5 because common user-side synonyms and extensions are missing (e.g., "Rust", "crash", "error", "config.toml", "OpenAI CLI").	4 / 5
Distinctiveness Conflict Risk	The "Codex" and "codex-rs" naming carves out a clear niche with distinct triggers, and the module list further narrows it. Minor overlap risk remains with generic debugging or Rust-development skills, so it does not quite reach 5.	4 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: steipete/agent-scripts
Path: skills/codex-debugging/SKILL.md
Commit: 3f8c6a3

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.