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 content is concise, well-structured, and action-oriented with executable source-navigation commands and a clear investigation workflow. The only notable gap is the rg command's placeholder pattern and the absence of an explicit validation feedback loop, which keep actionability and workflow clarity just below full marks.

Suggestions

Replace the rg placeholder with a concrete example (e.g. `rg "config.toml|AppConfig" codex-rs/config`) alongside the flexible template so a user has a copy-paste-ready starting point.

Add an explicit validation checkpoint to the workflow, e.g. "5. Confirm the fix against the focused test before finalizing," to close the validate-fix loop.

Optionally split the per-subsystem search hints into a short reference (e.g. references/subsystems.md) if the skill grows, though the current single-file structure is appropriate at this size.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding or explanations of concepts Claude already knows; every line (source-first commands, workflow steps, notes) earns its place, matching the anchor for lean, efficient content that assumes competence.	5 / 5
Actionability	It provides concrete executable commands (cd, sed, rg) and a numbered workflow, but the rg example uses a placeholder pattern ("<symbol\|setting\|error\|feature>") that is a template rather than fully copy-paste-ready, placing it just below the top anchor.	4 / 5
Workflow Clarity	A clear four-step sequence is present with an implicit checkpoint (read owning module and tests before proposing changes), but there is no explicit validate-then-fix feedback loop, matching the anchor for a clear sequence with minor validation gaps.	4 / 5
Progressive Disclosure	The skill is under 50 lines with no external bundle files and is organized into clear, well-signaled sections (Source First, Workflow, Notes), which per the simple-skill guidance earns the top score without needing separate reference files.	5 / 5
	Total	18 / 20 Passed

Description

57%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 Codex's codex-rs subsystems with strong distinctiveness, but it lacks an explicit "Use when..." trigger and relies on a single action verb with limited natural trigger-term variation. Adding a trigger clause and broader natural keywords would raise completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when debugging Codex CLI/app behavior, config parsing errors, tool/MCP wiring issues, or runtime bugs in codex-rs."

Broaden natural trigger terms to include phrases users actually say, such as "codex bug", "codex error", "codex config problem", or "codex not working".

Name one or two concrete debugging actions (e.g. "traces errors to their owning module", "reproduces failures with focused tests") beyond the single word "debugging" to strengthen specificity.

Dimension	Reasoning	Score
Specificity	The phrase "Codex debugging" names the domain and the enumerated "codex-rs core/tui/exec/cli/app-server/config" lists concrete subsystem targets, but only one actual action (debugging) is stated rather than several distinct actions, matching the anchor that names a domain with limited concrete actions.	3 / 5
Completeness	It states a clear "what" (Codex debugging across the listed subsystems) but provides no "Use when..." trigger clause, so per the boundary guidance completeness is capped at 3 with the "when" only weakly implied.	3 / 5
Trigger Term Quality	It includes relevant keywords ("debugging", "Codex", "config") but omits natural variations a user might say (e.g. "codex bug", "codex error", "codex not working"), matching the anchor with some relevant keywords but missing common synonyms.	3 / 5
Distinctiveness Conflict Risk	The scope is tightly bound to codex-rs's specific subsystems (core/tui/exec/cli/app-server/config), giving it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	14 / 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: efa3b2f

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.