Name: run-evals
Rating: 65.60000000000001 (1 reviews)
Author: flutter

run-evals

Run evaluations for one, multiple, or all skills using the agent orchestration framework. Make sure to use this skill whenever the user asks to run evals, test a skill's performance, run benchmarks, or compare baseline versus with-skill execution.

Quality

80%

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/run-evals/SKILL.md

Quality

Content

76%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 well-sequenced, actionable orchestration workflow with strong validation checkpoints and lean prose. Its main weakness is progressive disclosure: it references multiple resource files that are not bundled with the skill, leaving navigation unverified.

Suggestions

Bundle the referenced 'resources/*.md' template and prompt files under a real references/ directory so the cited paths resolve.

Use explicit link syntax (e.g., [with_skill_execution_prompt.md](resources/with_skill_execution_prompt.md)) rather than bare inline paths so navigation is clearly signaled.

Tighten the workspace-limitation warning paragraph, which currently repeats the rationale across multiple sentences.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean procedural guidance with bolded critical warnings rather than padded concept explanation, though a few sentences (e.g., explaining workspace bleed and the cross-skill path substitution) could be tightened.	4 / 5
Actionability	Provides concrete, executable direction (specific subagent profiles, named resource files like 'resources/with_skill_execution_prompt.md', explicit verification commands 'dart pub get', 'dart format', 'dart analyze', 'dart test') with minor gaps such as placeholder-only references to templates rather than inline content.	4 / 5
Workflow Clarity	A clear six-step numbered sequence with explicit validation/verification checkpoints (the Grade step requires listing failed expectations vs actual findings, the verification commands, and the explicit workspace-confinement and workspace-limitation warnings) and error-recovery feedback for batch/destructive operations.	5 / 5
Progressive Disclosure	The body points to several reference files ('resources/with_skill_execution_prompt.md', 'resources/baseline_execution_prompt.md', 'resources/agent_judge_prompt.md') and a README, but no references/scripts/assets bundle directory is present in the skill folder, so the referenced paths cannot be verified and navigation/signaling is only weakly structured.	3 / 5
	Total	16 / 20 Passed

Description

83%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, action-oriented, and explicitly covers both what the skill does and when to use it with natural trigger phrasing. It is strong across all dimensions with only minor synonym/coverage gaps.

Suggestions

Add a few synonym trigger terms (e.g., 'evaluate skills', 'regression tests', 'A/B compare') to broaden natural phrasing coverage.

Consider naming the supported scope (e.g., 'Dart/Flutter packages') to sharpen distinctiveness from generic testing skills.

Dimension	Reasoning	Score
Specificity	Names the domain (skill evals) and several concrete actions ('run evaluations', 'test a skill's performance', 'run benchmarks', 'compare baseline versus with-skill execution'), with only minor gaps in coverage relative to the full orchestration flow.	4 / 5
Completeness	Explicitly answers both what ('Run evaluations for one, multiple, or all skills using the agent orchestration framework') and when ('Make sure to use this skill whenever the user asks to run evals, test a skill's performance, run benchmarks, or compare baseline versus with-skill execution') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrasings ('run evals', 'test a skill's performance', 'run benchmarks', 'compare baseline versus with-skill execution') that a user would naturally say, though it lacks synonym/extension variants like 'evaluate' or 'regression tests'.	4 / 5
Distinctiveness Conflict Risk	The eval/benchmark/baseline-vs-with-skill niche is fairly distinct from general skills, with minor overlap risk against a generic testing skill; triggers are specific enough to avoid most conflicts.	4 / 5
	Total	17 / 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/run-evals/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.