definition-of-done

Mandatory checks to run before completing any task that touches md files or dart code in this repository.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./tool/dart_skills_lint/.agents/skills/definition-of-done/SKILL.md

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 content is a tight, highly actionable Definition-of-Done checklist with executable commands and explicit output formatting, excelling in conciseness, actionability, and structure. The only minor gap is the externally-resolved threshold in step 3 and the absence of an explicit retry loop.

Suggestions

Inline the concrete cognitive-complexity threshold value (or point to the exact line in the workflow YAML) instead of the placeholder '<N>' to remove an external lookup step.

Add a short validate-fix-retry note for the analysis and metrics steps (e.g., 'If dart analyze reports issues, fix and re-run until clean') to strengthen the feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient with every line being a concrete check, command, or formatting rule; it assumes Claude's competence and adds no padded explanations of known concepts.	5 / 5
Actionability	It provides fully executable, copy-paste-ready commands (e.g., 'dart format .', 'dart analyze --fatal-infos', 'dart test', 'dart run dart_skills_lint -d .agents/skills') plus concrete output-format examples covering the common cases.	5 / 5
Workflow Clarity	The 8 mandatory steps are clearly numbered with explicit pass conditions ('ensure there are zero issues', 'ensure all tests pass'), but step 3 defers the cognitive-complexity threshold to an external workflow file via '<N>' and the checklist lacks an explicit validate-fix-retry feedback loop, leaving a minor validation gap.	4 / 5
Progressive Disclosure	The skill is under 50 lines, has no external bundle files, and is organized into clearly headed sections (Mandatory Verification Steps, Output Formatting), meeting the simple-skill exception for a top progressive-disclosure score.	5 / 5
	Total	19 / 20 Passed

Description

53%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 concise and domain-scoped but stops short of listing concrete actions or providing an explicit 'Use when...' trigger clause, leaving completeness and trigger guidance at the midpoint. It is reasonably distinct within its repository niche.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when finishing a task that edits .md files or Dart code in this repo') to raise completeness and trigger-term quality.

Name 1-2 concrete checks in the description (e.g., 'runs dart format, dart analyze, and dart test') to lift specificity above the midpoint.

Dimension	Reasoning	Score
Specificity	The description names the domain ('md files or dart code') and a concrete action category ('checks to run'), but does not enumerate multiple specific concrete actions, matching the 'names domain and 1-2 concrete actions' anchor.	3 / 5
Completeness	It gives a clear 'what' (mandatory checks to run) but the 'when' is only weakly implied via a condition ('before completing any task that touches md files or dart code') rather than an explicit 'Use when...' trigger clause, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	It includes some natural terms a user might say ('checks to run', 'completing any task', 'md files', 'dart code') but lacks common synonyms or variations, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The scope is tightly bound to this repository's md files and dart code, making it mostly distinct with only minor overlap risk against other repo-linting skills.	4 / 5
	Total	13 / 20 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: flutter/agent-plugins
Path: tool/dart_skills_lint/.agents/skills/definition-of-done/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.