What problem does it solve?
This Skill guides creators through conversational discovery to design, build, edit, and quality-check AI agents that are outcome-driven rather than mechanically over-specified. It reduces wasted tokens and brittle behavior by enforcing persona-led prompts, selective scripting for deterministic work, and clear activation/headless patterns.
Core Features & Use Cases
- Conversational Discovery & Build Process: Six-phase guided flow to capture intent, strategy, requirements, and produce a complete agent structure (persona, capabilities, optional memory, assets, and scripts).
- Quality Analysis & Reporting: Deterministic lint scripts plus LLM scanners synthesize a capability dashboard, agent portrait, and ranked opportunities for improvement.
- Script & Execution Guidance: Identifies script opportunities, PEP 723 patterns, headless execution contracts, and outputs ready-to-run artifacts in the configured skills folder.
- Use Cases: Create a new agent from intent, convert/edit an existing agent to be outcome-driven, run automated quality scans, or enable headless builds in CI.
Quick Start
Invoke the builder and say: Create an agent that acts as a technical reviewer for pull requests and save it to the project's skills folder.