skill-test

Validate skill files for structural compliance and behavioral correctness. Three modes: static (linter), spec (behavioral), audit (coverage report).

Quality

72%

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 ./.claude/skills/skill-test/SKILL.md

Quality

Content

77%

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

The body is highly actionable with clear phased workflows and explicit validation verdicts, though it carries verbosity from multiple full report templates. Progressive disclosure is the weakest point: everything lives in one monolithic file with no reference bundle to offload detail.

Suggestions

Move the four full output-format templates into a references/ file (e.g., REPORT_FORMATS.md) and link to it one level deep to improve progressive disclosure.

Tighten the example report blocks to minimal representative snippets rather than full multi-line mock reports.

Fix the phase ordering inconsistency (Phase 2D: Category appears before Phase 2C: Audit) so the numbered sequence reads in order.

Dimension	Reasoning	Score
Conciseness	The body is instruction-dense without explaining concepts Claude already knows, but four full example report templates inflate the token budget and could be tightened or moved to references.	2 / 3
Actionability	Concrete and specific throughout: seven named checks with exact criteria, explicit Glob paths, exact output-format templates — fully actionable for an instruction-only skill.	3 / 3
Workflow Clarity	Clear phased sequence (Phase 1 → 2A–2D → 3) with per-mode numbered steps, explicit PASS/FAIL/WARN verdicts, and approval gates ('May I write'), providing explicit validation checkpoints.	3 / 3
Progressive Disclosure	Content is well-sectioned but monolithic — a ~350-line SKILL.md with no bundle files, keeping detail (e.g., full report templates) inline that could be split into one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and well-scoped to a clear niche, but it omits an explicit 'Use when' trigger and leans on technical phrasing rather than natural user keywords. It also advertises 'Three modes' while the body implements four (static, spec, category, audit), an accuracy gap worth fixing.

Suggestions

Add an explicit 'Use when…' clause naming natural triggers (e.g., 'Use when testing or auditing skills for compliance').

Reconcile the mode count: the body has four modes (static, spec, category, audit) but the description says 'Three modes' and omits category.

Soften jargon ('structural compliance', 'behavioral correctness') toward terms a user would naturally say, like 'lint skills' or 'test skills'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Validate skill files for structural compliance and behavioral correctness' — plus three named modes (static/spec/audit) with descriptors, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	The 'what' is clearly stated, but 'when' is only implied — there is no 'Use when…' clause or equivalent explicit trigger guidance, which caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant terms appear ('skill files', 'linter', 'coverage report') but the phrasing leans technical ('structural compliance', 'behavioral correctness') and omits common natural variations plus any 'Use when' trigger.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (testing/validating skill files) with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/skill-test/SKILL.md
Commit: 984023d

Reviewed: 3 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.