skill-validator

Ensure Claude Code skills meet quality standards through validation operations for structure, content, patterns, and production readiness. Task-based validation with pass/fail criteria, automated checks, and compliance reporting. Use when validating skills before deployment, ensuring standards compliance, certifying production readiness, or quality gating skill releases.

Quality

77%

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 ./skills/skill-validator/SKILL.md

Quality

Content

62%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 delivers a clear, well-sequenced validation workflow with explicit pass/fail checkpoints and feedback loops, and mostly actionable guidance. Its main weaknesses are significant duplication (Quick Reference restating the operations) and a fully monolithic structure with no progressive disclosure into reference files.

Suggestions

Remove the 'Minimum Standards' subsection (and other Quick Reference entries) that duplicate the per-operation pass criteria verbatim, keeping the Quick Reference to the summary table and decision tree only.

Split the Validation Report Format template and the per-pattern criteria (Workflow/Task/Reference) into a references/ file (e.g. REPORT-TEMPLATE.md, PATTERN-CRITERIA.md) linked from the body, enabling progressive disclosure.

Compress the five Best Practices entries into a short bulleted list — the repeated Practice/Rationale/Application scaffolding adds padding without new information.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose and padded: the 'Quick Reference → Minimum Standards' section repeats the operations' pass criteria nearly verbatim, 'Best Practices' repeats a Practice/Rationale/Application block five times, and the closing paragraph restates the overview. Not 1 because it does not explain concepts Claude already knows; not 3 because entire duplicated sections go beyond minor trim opportunities.	2 / 5
Actionability	Mostly executable guidance: concrete thresholds ('Must be ≥4 to pass', 'minimum 3' examples), one runnable command ('python3 review-multi/scripts/validate-structure.py <skill>'), and a copy-paste report template. Not 5 because it depends on another skill's script without a fallback and most per-step instructions stay at the checklist level.	4 / 5
Workflow Clarity	Each operation has purpose, pass criteria, numbered process, and an explicit PASS/FAIL verdict; Operation 4 adds a deployment decision tree and the skill prescribes a Validate → Fix → Re-validate feedback loop with re-validation after fixes. Matches the anchor with explicit validation steps and error-recovery loops; not a destructive/batch skill so no cap applies.	5 / 5
Progressive Disclosure	Well-organized internal headers and tables, but the ~300-line body is a single file with no references/ or scripts/ bundle: the report template, per-pattern criteria, and minimum-standards detail all remain inline where a reference file would serve better. Not 4 because nothing is split out at all; not 2 because section structure and navigation within the file are clear.	3 / 5
	Total	14 / 20 Passed

Description

83%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 description: third-person, concise, with explicit what and when clauses and multiple natural trigger phrases. Its only weaknesses are limited depth on what the validation checks entail and some missing synonyms for discovery.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'validation operations for structure, content, patterns, and production readiness', 'pass/fail criteria, automated checks, and compliance reporting' — with minor gaps (no detail on how validation is performed). Not 5 because coverage of what the checks actually entail is thin; not 3 because multiple specific actions are named beyond a single generic one.	4 / 5
Completeness	Clearly answers both: what ('validation operations for structure, content, patterns, and production readiness' with pass/fail criteria) and when (an explicit 'Use when...' clause with four concrete trigger phrases). Matches the anchor-5 example structure.	5 / 5
Trigger Term Quality	'validating skills before deployment, ensuring standards compliance, certifying production readiness, or quality gating skill releases' gives good natural-phrase coverage a user would say. Not 5 because common synonyms like 'review skill', 'check skill', or 'skill audit' are missing; not 3 because multiple natural trigger phrases are present.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear pass/fail deployment-gating niche distinct from general skill review, but 'validating skills' and 'standards compliance' could overlap with a closely related skill-review/scoring skill. Minor overlap risk only.	4 / 5
	Total	17 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/skill-validator/SKILL.md
Commit: 93ed392

Reviewed: 14 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.