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

93%

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

93%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 lean and highly actionable, with executable commands and Dart examples plus a numbered failing-run workflow and checklist. Progressive disclosure is well handled through clearly signaled one-level references.

Suggestions

Make the failing-run validation loop explicit: state "fix the violations, then re-run; only stop when the run is clean" as a named feedback loop rather than a single re-run step.

Briefly note which invocation mode is preferred when dart_skills_lint is already a pubspec dependency versus globally activated, so Claude does not have to guess.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: assumes Claude's competence with no padding about what a linter is, and deliberately defers the full flag list to --help "so it never goes stale."	5 / 5
Actionability	Provides copy-paste-ready commands for all three invocation modes plus a complete, executable Dart rule class and test harness covering the common custom-rule case.	5 / 5
Workflow Clarity	The failing-run workflow is numbered with a re-run verification checkpoint and a task-progress checklist, plus a --dry-run preview path; minor gap is that the validation feedback loop is stated implicitly rather than as an explicit fix-then-revalidate cycle.	4 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to the setup skill, RULES.md, and README.md; the bulk rule reference is appropriately split out rather than inlined.	5 / 5
	Total	19 / 20 Passed

Description

92%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 is concrete and well-triggered, pairing four specific capabilities with an explicit "Use when" clause tied to a named tool. It is highly distinct from sibling skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "running the linter, interpreting failures, fixing violations, and authoring custom rules" — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both "what" (the four concrete actions) and "when" via the "Use this skill when you need to..." trigger clause.	5 / 5
Trigger Term Quality	Includes the natural trigger phrase "validate AI agent skills" and the tool name dart_skills_lint, but lacks common synonyms a user might say such as "lint a skill" or "skill quality".	4 / 5
Distinctiveness Conflict Risk	Anchored to a named tool (dart_skills_lint) and a narrow niche (skill validation), clearly distinct from the setup skill it references, with minimal conflict risk.	5 / 5
	Total	19 / 20 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: c3c71cf

Reviewed: about 23 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.