simmer-generator

Generate improved artifact versions from ASI feedback in the simmer loop.

14|3|Updated Apr 2, 2026

Search Tags:#refinement #iteration #generator #artifact #simmer #asi

Ready to run

npx skills add https://github.com/2389-research/simmer --skill simmer-generator

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: simmer-generator
Source: https://github.com/2389-research/simmer/tree/main/skills/simmer-generator
Command: npx skills add https://github.com/2389-research/simmer --skill simmer-generator

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generates an improved version of an artifact by applying the judge's ASI feedback from the previous round, enabling faster convergence to a high-quality candidate.

Core Features & Use Cases

Works with both single-file and workspace targets
Executes ASI-driven direction to craft refined artifacts
Supports end-to-end iteration within the simmer orchestration loop for repeatable improvements

Quick Start

Provide the next improved artifact candidate based on the judge's ASI and current iteration context.

Frequently Asked Questions about simmer-generator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I use ASI feedback to improve an artifact?▼

To improve an artifact using ASI feedback, provide the current candidate text, rubric, ASI, and iteration number to generate an updated version within a serialized refinement loop.

Can I apply iterative refinement to a whole workspace instead of a single file?▼

Yes, iterative refinement supports both single-file and workspace targets, applying the ASI-driven direction to craft an updated artifact across the entire specified workspace.

What inputs are required to generate an improved artifact candidate?▼

Generating an improved artifact candidate requires the current text or workspace reference, rubric, ASI, iteration number, artifact type, and optional background context to execute the refinement.

How does the serialized refinement loop handle convergence?▼

The serialized refinement loop processes ASI feedback from the previous round to generate a complete updated artifact, enabling faster convergence to a high-quality candidate in the next iteration.

Does iterative artifact generation work outside of the simmer orchestrator?▼

No, the artifact generation executes ASI-driven direction specifically within the simmer orchestrator's iterative workflow, requiring its loop context to apply judge feedback properly.

What is the best way to automate repeatable artifact improvements?▼

To automate repeatable artifact improvements, run end-to-end iterations within the simmer orchestration loop, applying ASI feedback sequentially to generate refined candidates automatically.