Evaluate expectations against an execution transcript and outputs. Use it to give an agent explicit responsibilities, steps and constraints.

Compare two outputs WITHOUT knowing which skill produced them. Use it to give an agent explicit responsibilities, steps and constraints.

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions. Use it to navigate the topic and choose relevant methods, papers or tools.

A skill for creating new skills and iteratively improving them. Use it to make implementation decisions and avoid common dead ends.

If you need to fill out a PDF form, first check to see if the PDF has fillable form fields. Run this script from this file's directory: python scripts/check fillable fields , and depending on the result go to either the "Fillable fields" or "Non-fillable fields" and follow thos. Use it to ground design choices in named patterns, trade-offs and examples.

This skill provides a structured workflow for guiding users through collaborative document creation. Act as an active guide, walking users through three stages: Context Gathering, Refinement & Structure, and Reader Testing. Use it to make implementation decisions and avoid common dead ends.

Pattern Control - Define your patterns once, AI uses them forever ✋ Approval Gates - Review and approve before execution 🔁 Repeatable Results - Same patterns = Same quality code 📝 Editable Agents - Full control over AI behavior 👥 Team-Ready - Everyone uses t. Use it to build a structured path from fundamentals to hands-on practice.

A curated reference on agent design & orchestration centered on AgentBench. Use it to navigate the topic and choose relevant methods, papers or tools.