health

Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask in any language to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application code or reviewing PRs.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

77%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.

A well-structured, highly actionable audit workflow with strong validation checkpoints, weakened by verbose calibration prose and three dangling references to an agents/ directory that is not shipped in the bundle.

Suggestions

Ship the referenced agents/inspector-context.md, agents/inspector-control.md, and agents/inspector-maintainability.md files, or replace the Read instructions with inline guidance so no bundle path is dangling.

Tighten the long compound-sentence calibration paragraphs (security baseline, budget posture, permission-layer gating) into short bullet rules to improve token efficiency.

Verify every path mentioned in the body (e.g. agents/*.md) against the actual bundle so progressive-disclosure references all resolve.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids explaining concepts Claude already knows, but several calibration passages (e.g. the security-baseline and budget-posture paragraphs) are long compound sentences with heavy hedging that could be tightened into shorter rules.	3 / 5
Actionability	Fully executable guidance: copy-paste-ready PowerShell and Bash launcher snippets that self-resolve the skill base path, exact probe/collector commands, and a concrete finding template whose Action field is required to be copy-pasteable.	5 / 5
Workflow Clarity	Clear Step 0 -> Step 1/1b/1c -> Step 2 -> Step 3 sequence with explicit validation checkpoints ("Do not interpret yet", treat "(unavailable)" as insufficient data, wait for and reconcile inspectors, list unreviewed scope), a deep-re-run/local-fallback loop, and a gotchas checklist.	5 / 5
Progressive Disclosure	Good sectioning and clearly signaled one-level-deep links to real references/ files, but the deep-audit routing references agents/inspector-context.md, agents/inspector-control.md, and agents/inspector-maintainability.md, none of which exist in the bundle, breaking navigation on that path.	3 / 5
	Total	16 / 20 Passed

Description

95%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.

A strong, third-person description that clearly states what the skill does, when to use it with concrete multilingual triggers, and what it is not for. Minor room to widen the specificity of audited surfaces within the description itself.

Dimension	Reasoning	Score
Specificity	Names the audit action and four concrete surfaces ("instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability") with a budget-aware qualifier; not a full 5 because it is one verb applied to surfaces rather than multiple distinct actions, and supply-chain/memory surfaces appear only in the body.	4 / 5
Completeness	Explicitly answers both what ("Runs a budget-aware agent-assisted engineering health audit...") and when ("Use when users ask in any language to audit...") with concrete trigger phrases and an explicit "Not for..." boundary.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms ("audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift") covering multiple AI-coding-agent products plus the "in any language" signal for synonyms.	5 / 5
Distinctiveness Conflict Risk	Clear niche (agent-config health + AI-maintainability health) with an explicit "Not for debugging application code or reviewing PRs" boundary that minimizes conflict with code-review skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: tw93/Waza
Path: plugins/waza/skills/health/SKILL.md
Commit: f902996

Reviewed: 1 day 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.