recognizable-quality-test-generator
OfficialTurn results into verifiable judge prompts.
Software Engineering#workflow#calibration#generate#prompt-engineering#llm-judge#agent-evaluation#quality-rubric
Authorm2ai-portfolio
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Generates a structured, verifiable rubric that an agent can use as a judge to evaluate its own outputs and determine pass/fail criteria.
Core Features & Use Cases
- Converts a workflow description and 3–5 historical outputs into a formal evaluation rubric with 4–8 criteria.
- Produces a self-contained LLM-as-judge prompt that can be embedded into an agent's evaluation step.
- Supports calibration workflows to refine criteria based on outcome examples.
Quick Start
Provide a workflow description and 3–5 historical outputs to generate the judge rubric.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 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: recognizable-quality-test-generator Download link: https://github.com/m2ai-portfolio/m2ai-skills-pack/archive/main.zip#recognizable-quality-test-generator Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.