claude-skills

Claude Skills meta-skill: extract domain material (docs/APIs/code/specs) into a reusable Skill (SKILL.md + references/scripts/assets), and refactor existing Skills for clarity, activation reliability, and quality gates.

Quality

67%

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 ./bundled/skills/claude-skills/SKILL.md

Quality

Content

85%

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 executable scripts, a gated validation workflow, and clean one-level-deep progressive disclosure. The main weakness is moderate conciseness overhead from restated guidance and explanatory asides.

Suggestions

Trim restated explanatory asides (e.g. 'The truly minimal version is just SKILL.md...') that a competent model already infers.

Consolidate the frontmatter rules and the YAML skeleton block so the name/description guidance is stated once.

Move the 'Authoring Rules (Non-negotiable)' prose into references/skill-spec.md to keep the entrypoint leaner.

Dimension	Reasoning	Score
Conciseness	The body is largely lean (skeletons, copy/paste commands, checklists) but includes some instructional padding a competent model does not need, e.g. 'The truly minimal version is just SKILL.md (you can add references/ later)' and restated frontmatter rules; it is mostly efficient yet could be tightened to level 3.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands such as './scripts/validate-skill.sh skills/<skill-name> --strict' and 'create-skill.sh my-skill --full --output skills', plus concrete copy/paste skeleton and yaml blocks — meeting the level-3 executable-code anchor.	3 / 3
Workflow Clarity	The 'Workflow (Material -> Skill)' gives a numbered 1-6 sequence and the Quality Gate + 'validate-skill.sh --strict' step acts as an explicit validation checkpoint with an iterate/retry loop ('run validate-skill.sh --strict and iterate'), matching the level-3 anchor.	3 / 3
Progressive Disclosure	SKILL.md is an overview with one-level-deep, well-signaled references ('references/index.md', 'references/skill-spec.md', 'references/quality-checklist.md') that resolve to real files, and long-form detail is split out rather than inlined — matching the level-3 clear-overview anchor.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 states concrete capabilities clearly but omits an explicit 'Use when...' trigger clause, leaving the activation context implicit. It is well above the vague floor yet falls short of the trigger-rich exemplars.

Suggestions

Append an explicit activation clause, e.g. 'Use when creating, refactoring, or quality-gating a Claude Skill'.

Add natural user-facing trigger keywords ('create a skill', 'build a skill', 'skill quality gate') so it matches what users actually say.

State the boundary briefly ('not a domain skill itself') in the description to improve distinctiveness.

Dimension	Reasoning	Score
Specificity	Quotes concrete actions: 'extract domain material (docs/APIs/code/specs) into a reusable Skill (SKILL.md + references/scripts/assets)' and 'refactor existing Skills for clarity, activation reliability, and quality gates' — multiple specific, named actions rather than vague verbs.	3 / 3
Completeness	The 'what' is clearly stated (extract/refactor into a reusable Skill), but 'when to use it' is only implied — there is no explicit 'Use when...' clause naming activation triggers, which the guidelines cap at 2.	2 / 3
Trigger Term Quality	Uses meta-skill vocabulary ('extract', 'refactor', 'Skill', 'SKILL.md') but lacks the natural user-facing keywords a person would actually say, such as 'create a skill', 'build a skill', or 'skill quality'. Not the level-3 coverage of common phrasings, and above the level-1 jargon-only floor.	2 / 3
Distinctiveness Conflict Risk	Scoped to a fairly clear niche (skill authoring/refactoring), but without explicit trigger guidance it could overlap with general coding or documentation skills, so it does not reach the level-3 distinct-niche bar.	2 / 3
	Total	9 / 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/claude-skills/SKILL.md
Commit: f627ab5

Reviewed: about 8 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.