dart-skills-lint-validation

Use this skill when you need to validate AI agent skills with dart_skills_lint — running the linter, interpreting failures, fixing violations, and authoring custom rules.

Quality

95%

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

Quality

Content

100%

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

An exemplary skill body: concise, fully actionable with executable code, a validated multi-step workflow, and clean one-level-deep navigation to related materials.

Dimension	Reasoning	Score
Conciseness	The body is lean: it assumes Claude knows what a linter/YAML/test is, avoids concept explanations, and every prose line and code block earns its place; the only inline commentary is functional ('skip the inline duplicate so it never goes stale').	3 / 3
Actionability	It provides fully executable commands ('dart run dart_skills_lint:cli -d .agents/skills', '--fix', '--fix --dry-run') and complete, copy-paste-ready Dart code for both a custom rule and its test harness.	3 / 3
Workflow Clarity	The failing-run workflow is a clear numbered sequence with an explicit verification checkpoint ('Re-run to confirm the run is clean') and a task checklist, and the potentially destructive '--fix' step is guarded with '--dry-run' preview.	3 / 3
Progressive Disclosure	It is a clear overview with well-signaled, one-level-deep references to a sibling setup skill and the repo-root RULES.md/README.md, each annotated with what it contains; no nested references and no monolithic inline detail dump.	3 / 3
	Total	12 / 12 Passed

Description

90%

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, specific description with an explicit use-trigger and concrete actions; the only weakness is second-person voice ('when you need to') which the rubric penalizes on the specificity dimension.

Suggestions

Rewrite in third person to avoid the voice penalty, e.g. 'Validates AI agent skills with dart_skills_lint — runs the linter, interprets failures, fixes violations, and authors custom rules. Use when validating agent skills or fixing lint violations.'

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ('running the linter, interpreting failures, fixing violations, and authoring custom rules'), which meets the level-3 anchor, but the second-person phrasing 'when you need to validate' triggers the rubric's voice penalty, reducing specificity by one point.	2 / 3
Completeness	It answers both 'what' (validate skills via the linter and the four listed actions) and 'when' with an explicit 'Use this skill when you need to...' trigger clause.	3 / 3
Trigger Term Quality	It pairs the named tool ('dart_skills_lint') with natural terms a user would actually say ('validate AI agent skills', 'running the linter', 'fixing violations', 'custom rules'), giving good coverage.	3 / 3
Distinctiveness Conflict Risk	The narrow niche of validating AI agent skills with a specifically named Dart tool gives it distinct triggers unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 5 suspicious	Warning

	Total	13 / 16 Passed

Repository: flutter/agent-plugins
Path: tool/dart_skills_lint/skills/dart-skills-lint-validation/SKILL.md
Commit: 8aaa41d

Reviewed: about 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.