skill-construire-evaluations

Community

Create robust evaluation cases and evals.json.

Authorniboj
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill helps you create realistic evaluation cases for a skill's triggering and output quality, and generates an evals.json to document prompts that should trigger, should not trigger, and edge cases that reveal weak instructions. Do not use this skill to rewrite the skill itself.

Core Features & Use Cases

  • Generate nominal, edge, incomplete input, and neighbour prompts to thoroughly test a skill's behavior.
  • Separate trigger and non-trigger cases, and express the expected behavior with precise assertions.
  • Reuse the resulting evals.json as a regression suite to guard against future changes.

Quick Start

Create the evals/evals.json file for the target skill detailing trigger prompts, non-trigger prompts, and edge cases.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: skill-construire-evaluations
Download link: https://github.com/niboj/agent-skills-12-factor-app/archive/main.zip#skill-construire-evaluations

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.