plugin-validator

Validate automatically validates AI assistant code plugin structure, schemas, and compliance when user mentions validate plugin, check plugin, or plugin errors. runs comprehensive validation specific to AI assistant-code-plugins repository standards. Use when validating configurations or code. Trigger with phrases like 'validate', 'check', or 'verify'.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%Weight 40%Scale 1-3

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 and well-sequenced, with concrete commands, explicit error-recovery feedback loops, and clean one-level-deep references that all resolve to real files. The only weakness is mild verbosity from repeated field lists and prose restatement that could be pushed to references.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-organized, but several inline details (the full disallowed-fields list repeated across instructions, prerequisites, and the error table) could be tightened by deferring to references, and the prose occasionally restates what each check does.	2 / 3
Actionability	Guidance is concrete and executable: specific shell commands ('jq empty <file>', 'chmod +x', 'pnpm run sync-marketplace'), exact required fields, file globs, and a structured report format with ready-to-run fix commands per failure.	3 / 3
Workflow Clarity	A clearly numbered 11-step sequence with validation built in (JSON parse checks, marketplace cross-checks) and an error-handling table mapping each failure cause to a fix command, providing explicit feedback loops for error recovery.	3 / 3
Progressive Disclosure	SKILL.md is an overview pointing one level deep to real reference files (validation-checks.md, validation-report-format.md, examples.md, errors.md), all of which exist in ./references/, with a clean Resources section organizing navigation.	3 / 3
	Total	11 / 12 Passed

Description

92%Weight 40%Scale 1-3

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, actionable, and explicitly provides both what the skill does and when to trigger it, with natural trigger terms. The main weakness is the over-broad 'validating configurations or code' clause, which dilutes distinctiveness and invites conflicts with unrelated validation skills.

Suggestions

Narrow the 'Use when' clause to plugin-specific contexts (e.g., 'Use when validating Claude Code/AI assistant plugins or preparing a plugin for CI') to reduce conflict with general validation skills.

Drop the redundant 'Trigger with phrases like validate, check, or verify' tail since trigger terms are already covered earlier; keep the description tighter.

Verify the third-person voice is consistent throughout ('runs comprehensive validation' is lowercase and reads as a sentence fragment — align phrasing with the leading 'Validate automatically validates').

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions ('validates plugin structure, schemas, and compliance') and ties them to concrete artifacts (plugin.json, frontmatter, marketplace catalog), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'what' (validates structure, schemas, compliance) and 'when' ('Use when validating configurations or code'; 'Trigger with phrases like validate, check, verify'), with explicit trigger guidance.	3 / 3
Trigger Term Quality	Covers natural terms users would say ('validate plugin', 'check plugin', 'validate', 'check', 'verify') across several phrasings, giving good coverage rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Niche is fairly clear (plugin validation), but 'Use when validating configurations or code' is broad and could overlap with general validation/verification skills, leaving some conflict risk.	2 / 3
	Total	11 / 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: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/examples/jeremy-plugin-tool/skills/plugin-validator/SKILL.md
Commit: c4eafaf

Reviewed: 5 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.