dart-run-static-analysis

Execute `dart analyze` to identify warnings and errors, and use `dart fix --apply` to automatically resolve mechanical lint issues. Use during development to ensure code quality and before committing changes.

Quality

83%

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

85%

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

The content is dense, executable, and well-structured with copy-paste-ready commands and a complete config example. The main gap is workflow_clarity: the analysis and fix workflows lack an explicit validate-then-confirm-clean feedback loop, which the rubric caps at 2 for automated/batch operations.

Suggestions

Add an explicit validation checkpoint to the analysis workflow — e.g., a final step 'Re-run `dart analyze` and confirm no errors/warnings remain before proceeding' — to close the feedback loop.

In the fix workflow, make verification mandatory and gated (e.g., 'Do not mark complete until `dart analyze` reports zero issues') rather than listing it as a final optional-style step.

Consider noting that `dart fix --apply` should be followed by a review of the diff before committing, since automated fixes can shift architecture.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it jumps straight into configuration keys, suppression syntax, and concrete commands without explaining what Dart is or how linters work, and every section earns its place with actionable specifics.	3 / 3
Actionability	It provides fully executable commands (`dart analyze <target_directory>`, `dart fix --dry-run`, `dart fix --apply`, `dart format .`), exact YAML keys with valid values, and a complete copy-paste-ready `analysis_options.yaml` plus inline suppression examples, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	Both workflows are clearly sequenced with numbered task-progress steps, but the analysis workflow applies fixes without an explicit validation/verification checkpoint — there is no 're-run analyze and confirm zero errors' feedback loop before declaring done, which the rubric caps at 2 for batch/automated operations. The fix workflow does end with 'Run the static analysis workflow to verify', showing some but not fully explicit per-step validation.	2 / 3
Progressive Disclosure	The skill is a single well-organized SKILL.md with a clear Contents navigation and logically separated sections (configuration, suppression, two workflows, examples); with no bundle directories present there are no nested references, so per the rubric's guidance for skills that need no external references, well-organized sections earn a 3.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 strong: it names concrete commands and outcomes, explicitly states when to use the skill, and occupies a distinct Dart-specific niche. Its only weak spot is trigger-term breadth, leaning on tool names rather than the broader natural phrasings a user might say.

Suggestions

Broaden trigger terms to include natural user phrasings such as 'lint', 'static analysis', 'analyze Dart code', or 'fix lint warnings' so the skill surfaces for less tool-savvy requests.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Execute `dart analyze` to identify warnings and errors' and 'use `dart fix --apply` to automatically resolve mechanical lint issues' — naming specific commands and their outcomes, matching the 'Lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It answers both 'what' (execute dart analyze to find warnings/errors; use dart fix --apply to resolve lint issues) and 'when' explicitly ('Use during development to ensure code quality and before committing changes'), matching the 'clearly answers both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	It includes the tool names ('dart analyze', 'dart fix --apply', 'lint issues') that a developer would naturally invoke, but it does not surface common user-facing phrasings like 'lint', 'static analysis', 'analyze my Dart code', or 'fix warnings'; coverage of natural trigger variations is partial.	2 / 3
Distinctiveness Conflict Risk	It targets a clear niche — Dart static analysis and automated fixes — with tool-specific triggers ('dart analyze', 'dart fix') that are unlikely to conflict with other skills, matching the 'Clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 12 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: flutter/agent-plugins
Path: skills/dart-run-static-analysis/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.