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

66%

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

78%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 a well-structured, actionable operator's manual with real bundle files backing its references and a validation feedback loop. Main opportunities are trimming the duplicated skeleton/checklist content and adding intermediate validation checkpoints in the primary workflow.

Suggestions

Replace the inline full skeleton with a pointer to assets/template-complete.md to reduce token duplication, keeping only the minimal frontmatter example inline.

Add intermediate validation checkpoints within the six-step workflow (e.g. verify frontmatter after step 2, verify patterns after step 3) rather than gating only at the final step.

Tighten the Quality Gate checklist by cross-referencing references/quality-checklist.md instead of restating the full nine-point list inline.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — bullets, short imperatives, and no explanation of concepts Claude already knows — though the embedded full skeleton and repeated checklist/restatements add tokens that could be trimmed.	4 / 5
Actionability	Runnable copy-paste commands (validate-skill.sh, create-skill.sh) and three concrete examples cover common cases, but the skeleton's abstract placeholders ([Trigger 1], [capability 1]) keep it just below fully copy-paste-ready.	4 / 5
Workflow Clarity	The six-step Material->Skill workflow is clearly sequenced with an explicit gate (step 6) and a validate->fix->retry loop in Example 3, but the primary workflow gates only at the end rather than at intermediate checkpoints.	4 / 5
Progressive Disclosure	The body is a clear overview with well-signaled one-level-deep references (references/index, skill-spec, quality-checklist, anti-patterns, README) plus scripts/ and assets/ — all confirmed to exist — with content appropriately split and an explicit navigation section.	5 / 5
	Total	17 / 20 Passed

Description

53%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 states a clear purpose and a distinct niche, but it omits any explicit 'Use when...' trigger guidance, which caps completeness and limits trigger-term quality. Adding concrete activation triggers would lift the two capped dimensions.

Suggestions

Add an explicit 'Use when...' clause naming concrete activation triggers (e.g. 'Use when creating a new Skill from docs/specs/repos or refactoring an existing SKILL.md').

Expand the action list beyond 'extract' and 'refactor' to cover more concrete capabilities (e.g. scaffold directories, write frontmatter, run validation gates) for higher specificity.

Include natural user phrasings and synonyms (e.g. 'build a skill', 'author SKILL.md', 'quality-gate a skill') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (skill authoring) and two concrete actions — "extract domain material" and "refactor existing Skills" — but the action list is not comprehensive enough to reach the 'several specific actions' bar of 4.	3 / 5
Completeness	The 'what' is clear (extract and refactor Skills), but there is no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Core keywords like "Skill", "SKILL.md", "refactor existing Skills" are present, but natural-phrase coverage is thin with few synonyms or variations a user would naturally say.	3 / 5
Distinctiveness Conflict Risk	The "Claude Skills meta-skill" framing carves a clear niche distinct from domain skills with minor overlap risk, though the absence of explicit trigger phrases keeps it just below a 5.	4 / 5
	Total	13 / 20 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: d5ae560

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.