dart-fix-runtime-errors

Uses get_runtime_errors and lsp to fetch an active stack trace, locate the failing line, apply a fix, and verify resolution via hot_reload.

Quality

76%

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 ./skills/dart-fix-runtime-errors/SKILL.md

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 body is highly actionable with a well-sequenced, validated workflow and complete executable examples. Its main weaknesses are conceptual padding in Core Concepts and a content mismatch: the description promises runtime-error tooling (get_runtime_errors/lsp/hot_reload) that the static-analysis body never uses.

Suggestions

Trim the Core Concepts section to non-obvious guidance only, removing basic Dart modifier/exception explanations Claude already knows.

Resolve the description/body mismatch by either documenting runtime-error tooling (get_runtime_errors, lsp, hot_reload) or aligning the description to static analysis.

Consider moving the type-system/null-safety reference material to a separate reference file so the main body stays lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands and examples, but the Core Concepts section restates Dart fundamentals Claude already knows (e.g. "Apply `?` for nullable types, `!` for null assertions, and `required` for named parameters") and could be tightened, so it is not the lean level-3 anchor.	2 / 3
Actionability	Provides fully executable commands ("dart analyze . --fatal-infos", "dart fix --dry-run", "dart fix --apply", "dart test") and complete input/output Dart examples with error-type-specific conditional fixes, matching the copy-paste-ready level-3 anchor.	3 / 3
Workflow Clarity	The four-step workflow has an explicit checklist and a 'Verify fixes (Feedback Loop)' step with conditional recovery ("If `dart analyze` reports errors: Return to Step 3"), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	No external references are needed and the single file is well organized with a Contents TOC and clearly headed sections (Core Concepts, Workflows, Examples), which the rubric allows to score 3 for self-contained skills with good organization.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 specific and distinct, naming a clear fetch-locate-fix-verify sequence, but it lacks an explicit 'Use when' trigger and leans on internal function names rather than natural user language. Adding a trigger clause and user-facing keywords would lift completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when a Dart app crashes or reports a runtime error and an active stack trace is available.'

Replace leading internal tool names with natural terms a user would say (e.g. 'runtime error', 'stack trace', 'crash', 'exception') alongside the tool references.

Reconcile the description's 'runtime errors' framing with the body's static-analysis focus so activation matches the actual skill content.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "fetch an active stack trace", "locate the failing line", "apply a fix", "verify resolution via hot_reload" — matching the 'multiple specific concrete actions' anchor rather than the partial anchor at 2.	3 / 3
Completeness	It clearly answers 'what does this do' (fetch, locate, fix, verify) but has no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 2.	2 / 3
Trigger Term Quality	Some relevant natural terms appear ("stack trace", "failing line", "apply a fix") but the description leads with internal tool/jargon names ("get_runtime_errors", "lsp", "hot_reload") and omits common user phrasings like 'runtime error', 'crash', or 'Dart exception', so it is not the level-3 full coverage anchor.	2 / 3
Distinctiveness Conflict Risk	The specific tooling and runtime-error framing give it a clear niche unlikely to trigger for unrelated skills; it is more distinct than the level-2 'could overlap' anchor.	3 / 3
	Total	10 / 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-fix-runtime-errors/SKILL.md
Commit: 8aaa41d

Reviewed: about 13 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.