source-command-verify-setup

Run the infrastructure health check and fix anything that fails

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/source-command-verify-setup/SKILL.md

Quality

Content

100%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, well-structured runbook with executable commands, an explicit re-run-until-green feedback loop, and appropriately scoped warning handling, hitting the top anchor on every dimension.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding or explanation of concepts Claude already knows; every line (the command, the common fixes, the warning policy) earns its place.	3 / 3
Actionability	It gives fully executable commands (`bash .Codex/scripts/verify-setup.sh`, `cd .Codex/hooks && npm install`, `chmod +x .Codex/hooks/*.sh`) plus concrete, specific guidance for JSON repair and dead registrations.	3 / 3
Workflow Clarity	The five-step sequence is clearly ordered with an explicit feedback loop ("Re-run the script after each fix until it reports 0 failed") and a final reporting checkpoint, which is exactly the validate-fix-retry pattern the rubric rewards.	3 / 3
Progressive Disclosure	This is a simple, single-purpose skill under 50 lines with no bundle files; the content is well-organized into clear sections (Command Template, Steps) which per the rubric earns a 3 without external references.	3 / 3
	Total	12 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 a concise third-person statement of capability but lacks an explicit trigger/when clause and relies on fairly generic phrasing, leaving it at mid-tier across all dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to run the verify-setup or infrastructure health check for the migrated Codex command."

Replace "fix anything that fails" with concrete fix actions (e.g. install missing hook dependencies, repair invalid settings JSON) to raise specificity.

Include natural trigger variations such as "verify-setup", "health check", and "Codex infrastructure" to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Run the infrastructure health check and fix anything that fails" names a concrete action (run the health check) plus a second action (fix failures), but "fix anything that fails" is non-comprehensive rather than enumerating specific fixes, so it sits at the domain-and-some-actions level rather than fully concrete.	2 / 3
Completeness	It states what the skill does (run the health check and fix failures) but provides no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	"infrastructure health check" is a phrase a user might say, but coverage of natural trigger terms is thin and missing common variations; there are no additional keywords a user would naturally voice.	2 / 3
Distinctiveness Conflict Risk	"infrastructure health check" gives it a somewhat specific niche, but "fix anything that fails" is generic enough to overlap with general debugging or repair skills.	2 / 3
	Total	8 / 12 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: diet103/claude-code-infrastructure-showcase
Path: .agents/skills/source-command-verify-setup/SKILL.md
Commit: 07f75ce

Reviewed: ~1 month 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.