Skills
.Work. You
Rest

generate-eval

Official

Create and certify eval tasks for precise API detail measurement.

Software Engineering#code evaluation#task authoring#eval task#API measurement#library certification
Authortangle-network
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill assists in authoring and certifying execution-certifiable, search-discriminating eval tasks for a given target, ensuring accurate API detail measurement.

Core Features & Use Cases

  • Task Authoring: Author eval tasks that measure whether web search aids a coding agent in obtaining correct API details.
  • Certification: The runtime certifies the candidate tasks against both grounding and discrimination gates.
  • Use Case: For a library version or release notes, create a task that an independent certifier will validate against the real target.

Quick Start

Use the generate-eval skill to create an eval task for the library '[email protected]' and output the candidate JSON object to 'task.json'.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 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: generate-eval
Download link: https://github.com/tangle-network/agent-runtime/archive/main.zip#generate-eval

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 620,000+ vetted skills library on demand.