skills.rest
richardmbailey
richardmbaileyCOMMUNITY
Explore all skills by this author →
GitHub

rb-create-skill-evals

Creates behavioural evaluation suites for agent skills, including trigger accuracy and outcome quality checks.

Updated Jul 2, 2026
Search Tags:#testing#validation#evaluation#regression#quality-assurance#agent-skills
One-click install
npx skills add https://github.com/richardmbailey/rb-skills --skill rb-create-skill-evals
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rb-create-skill-evals
Source: https://github.com/richardmbailey/rb-skills/tree/main/rb-create-skill-evals
Command: npx skills add https://github.com/richardmbailey/rb-skills --skill rb-create-skill-evals

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill addresses the challenge of ensuring agent skills are reliable, effective, and regression-proof by providing a structured framework for behavioural evaluation.

Core Features & Use Cases

  • Behavioural Contract Definition: Translates skill requirements into testable claims, including trigger boundaries and outcome quality.
  • Multi-Dimensional Evaluation: Supports deterministic, semantic, and manual validation to ensure skills perform as expected across various scenarios.
  • Ablation Testing: Facilitates with-skill versus without-skill comparisons to prove the marginal value of an agent skill.

Quick Start

Use the rb-create-skill-evals skill to generate a comprehensive evaluation suite for the target skill directory.

Frequently Asked Questions about rb-create-skill-evals

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

FAQPage Schema
How do I create behavioural tests for agent skills?▼

Behavioural tests for agent skills are created by translating skill requirements into testable claims, defining trigger boundaries, and validating outcome quality across various scenarios.

What is ablation testing for agent workflows?▼

Ablation testing for agent workflows compares with-skill versus without-skill performance to prove the marginal value and validate semantic and deterministic improvements.

How do I prevent regressions in reusable agent workflows?▼

Regression protection for reusable agent workflows is achieved by building evaluation suites that apply multi-dimensional validation, including deterministic, semantic, and manual testing.

Can I validate both trigger accuracy and outcome quality for agent skills?▼

Trigger accuracy and outcome quality are validated through behavioural contract definition, which translates requirements into testable claims and supports failure analysis.

Does this evaluation framework require any external dependencies?▼

This evaluation framework requires no external dependencies, relying solely on its internal scripts and references to generate comprehensive evaluation suites for target skill directories.

Related Skills

Explore More Software Engineering Skills→
syahiidkamilsyahiidkamil
316

skill-creator

Guide users through designing, documenting, and evaluating Claude Code skills.

Community
Advanced
HomericIntelligenceHomericIntelligence
18

run-tests

Execute Mojo or Python test suites and generate validation reports.

Official
Basic
dtsongdtsong
1

AI Evaluation

Design evaluation frameworks for AI features with golden datasets and scoring rubrics.

Community
Advanced
jyang234jyang234

coding

Enforce coding standards and best practices across software development tasks.

Community
Intermediate