dart-skills-lint-setup

Use this skill when you need to set up validation for AI agent skills in a Dart project for the first time. Adds the linter as a dev_dependency, creates a configuration file, and generates a baseline for legacy repos.

Quality

84%

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

86%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.

A tight, well-structured setup skill with executable code, a clear sequence, and good progressive disclosure via one-level-deep references. The main gaps are the CI step's reliance on the README and the absence of an explicit post-setup verification checkpoint.

Suggestions

Inline a minimal GitHub Actions snippet in step 4 (or a one-line verification command) so the skill is copy-paste complete without a README round-trip.

Add an explicit verification step after step 2 or 3, e.g. 'Run `dart run dart_skills_lint:cli --skills-directory=.agents/skills` to confirm the config resolves and exits clean.'

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout: a brief orientation pointer, four numbered steps with tight code blocks, and a one-line handoff; it never explains concepts Claude already knows and every line earns its place.	5 / 5
Actionability	Steps 1-3 are fully executable with copy-paste YAML and bash, but step 4 delegates the CI wiring to README recipes rather than providing the recipe inline, a minor gap against anchor 5.	4 / 5
Workflow Clarity	A clear four-step sequence where the baseline command provides implicit verification, but there is no explicit 'run the linter to confirm the setup exits clean' checkpoint, leaving a minor validation gap.	4 / 5
Progressive Disclosure	An overview that splits content well and points one level deep via clearly signaled references to the sibling validation skill, README#recipes, and RULES.md, making navigation easy.	5 / 5
	Total	18 / 20 Passed

Description

82%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 well-constructed description that clearly states both the triggering scenario and the concrete actions performed, with a distinct niche. The only notable issue is the second-person trigger phrasing, which the rubric penalizes on specificity.

Suggestions

Rephrase the trigger in third person to avoid the specificity penalty, e.g. 'Sets up validation for AI agent skills in a Dart project on first integration. Use when wiring dart_skills_lint into a repository for the first time.'

Add a couple of natural synonyms or file extensions (e.g. 'linting', 'pubspec', '.agents/skills') to lift trigger term coverage toward comprehensive.

Dimension	Reasoning	Score
Specificity	Lists three concrete actions ('Adds the linter as a dev_dependency, creates a configuration file, and generates a baseline for legacy repos'), matching the anchor-4 example of several specific actions; reduced by one per the rubric's second-person penalty because the trigger clause says 'you need to set up'.	3 / 5
Completeness	Explicitly answers both 'what' (the three setup actions) and 'when' ('Use this skill when you need to set up validation ... for the first time') with a concrete trigger phrase, matching the anchor-5 example.	5 / 5
Trigger Term Quality	Natural trigger terms are present ('set up validation', 'Dart project', 'for the first time', 'AI agent skills') with good coverage, but it lacks common synonyms and file extensions that would push it to anchor 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (first-time Dart skill-validation wiring) and explicitly distinguishes itself from the sibling ongoing-use skill, giving minimal conflict risk.	5 / 5
	Total	17 / 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-setup/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.