skills.rest
nklisch
nklischCOMMUNITY
Explore all skills by this author →
GitHub

skill-evaluator

Evaluate AI agent skills against quality rubrics and generate improvement reports.

7|4|Updated Mar 2, 2026
Search Tags:#agent#rubric#test#skill#report#evaluate
One-click install
npx skills add https://github.com/nklisch/skills --skill skill-evaluator-nklisch
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-evaluator
Source: https://github.com/nklisch/skills/tree/main/plugins/skill-authoring/skills/skill-evaluator
Command: npx skills add https://github.com/nklisch/skills --skill skill-evaluator-nklisch

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Developers and AI practitioners often lack a consistent, objective way to assess the quality of their agent skills. This leads to hidden weaknesses, poor emotional tone, and unreliable activation across sessions.

Core Features & Use Cases

  • Type Classification – Automatically determines whether a skill is a reference, workflow, interactive, or principle skill.
  • Comprehensive Scoring – Applies universal, type‑specific, and emotional‑tone rubrics to generate structural and affective scores.
  • Actionable Recommendations – Provides concrete rewrite suggestions and prioritized improvement steps for any low‑scoring dimension.
  • Test Scenario Generation – Produces realistic test cases to validate the evaluated skill after revisions.

Use case: a software engineer can run this evaluator on a newly authored workflow skill to receive a detailed report, fix tone issues, and obtain test scenarios before deployment.

Quick Start

Ask the skill evaluator to evaluate the skill located at './plugins/skill-authoring/skills/skill-evaluator'.

Frequently Asked Questions about skill-evaluator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate an AI agent skill against quality rubrics?▼

To evaluate an AI agent skill against quality rubrics, apply the evaluator to any skill directory to classify its type, score structural and emotional dimensions, and generate a detailed improvement report.

What is a skill evaluation rubric and how does it work?▼

A skill evaluation rubric is a scoring framework that applies universal, type-specific, and emotional tone criteria to assess an AI agent skill's structural and affective quality across sessions.

How do I test AI agent skills after revising their content?▼

To test AI agent skills after revisions, use the generated test scenarios to validate the evaluated skill, ensuring the structural and emotional tone updates perform reliably.

Can I score the emotional tone of an interactive agent skill?▼

Yes, you can score the emotional tone of an interactive agent skill by applying the emotional-tone rubric, which evaluates affective dimensions and provides concrete rewrite suggestions for low-scoring areas.

Does the skill evaluator work with reference skills and workflow skills?▼

Yes, the skill evaluator works with reference skills and workflow skills by automatically determining the skill type to apply the correct type-specific rubrics for comprehensive scoring.

Related Skills

Explore More Software Engineering Skills→
miethemiethe

amcs-validator

Score composed artifacts against a blueprint rubric and output scores, issues, and pass.

Community
Advanced
Qiue-GQiue-G

verify

Execute an application and observe outcomes to validate code changes.

Community
Basic
aah-stackaah-stack

skill-creator

Create and optimize reusable Claude skills with SKILL.md authoring and evaluation workflows.

Community
Advanced
HaykTarkhanyanHaykTarkhanyan

peer-review

Generate hierarchical peer-review reports with major and minor comments.

Community
Advanced