code-health

Scans the codebase for dead code, tech debt, outdated dependencies, and code quality issues. Delegates to the Centinela (QA) agent.

Quality

61%

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 ./plugins/agent-triforce/skills/code-health/SKILL.md

Quality

Content

57%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 well-structured and appropriately concise for a single-purpose agent-delegation skill, but its workflow relies on unexplained checklist jargon and buries its verification step in Tips rather than the numbered sequence.

Suggestions

Define or inline the 'SIGN IN' and 'Scan Complete (TIME OUT)' checklists instead of referencing them as opaque acronyms.

Promote the false-positive verification step into the numbered workflow as an explicit validation checkpoint (e.g. 'Verify each finding is not a false positive before recording it').

De-duplicate the Example output list against the 'What This Skill Does' steps to trim the token footprint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with no concept over-explanation, but the opening restates the description and the Example output bullets duplicate the 'What This Skill Does' list, so it could be tightened.	3 / 5
Actionability	Gives a concrete invocation ('/code-health') and a concrete output path, but references undefined checklists ('SIGN IN', 'TIME OUT') as jargon, leaving key execution details unspecified.	3 / 5
Workflow Clarity	An 8-step numbered sequence is present, but validation/verification (avoiding false positives) is only implied in Tips rather than explicit checkpoints in the workflow; for a batch codebase scan this caps the score at 3.	3 / 5
Progressive Disclosure	A short (~40-line), self-contained skill with clearly organized sections (When to Use, What This Skill Does, How to Use, Example, Tips) and no nested external references, so it earns the top score for a simple skill.	5 / 5
	Total	14 / 20 Passed

Description

66%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 clearly states what the skill does and enumerates specific scan areas, but omits any explicit 'when to use' trigger guidance, capping completeness. It is concise and reasonably distinct from sibling skills.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when running a pre-release codebase hygiene check, auditing tech debt, or cleaning up dead code before a refactor.'

Include a few natural synonyms users might say ('unused code', 'lint issues', 'dependency vulnerabilities') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete scan targets — 'dead code, tech debt, outdated dependencies, and code quality issues' — plus delegation to a named agent, giving strong coverage with only minor gaps (all actions share the single verb 'scans').	4 / 5
Completeness	The 'what' is clear, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural phrases users would say ('dead code', 'tech debt', 'code quality', 'outdated dependencies'), though a few common synonyms (e.g. 'lint', 'unused code') are missing.	4 / 5
Distinctiveness Conflict Risk	The code-health niche with specific scan targets and the 'Delegates to the Centinela (QA) agent' marker make it mostly distinct, with only minor overlap risk against general review/QA skills.	4 / 5
	Total	15 / 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: davepoon/buildwithclaude
Path: plugins/agent-triforce/skills/code-health/SKILL.md
Commit: ac92f1d

Reviewed: ~12 hours 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.