simmer-reflect

Record and organize evaluation trajectories across iterations with best-candidate tracking.

14|3|Updated Apr 2, 2026

Search Tags:#iteration #trajectory #ASI #scores #reflect #simmer #best-candidate

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reflect records the full iteration history, trajectory table, and best candidate, enabling regression rollback and ASI forwarding in simmer rounds.

Core Features & Use Cases

Tracks the full score history across iterations and identifies the best candidate.
Handles regression by signaling when to revert to a prior iteration and pass ASI forward.
Supports both single-file and workspace modes, integrating with the simmer orchestrator.

Quick Start

After each judge round, instruct Reflect to update the trajectory and propagate the ASI to the next round.

Frequently Asked Questions about simmer-reflect

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

FAQPage Schema

How do I track iteration scores and identify the best candidate across multiple rounds?▼

Tracking iteration scores and identifying the best candidate involves recording the full evaluation trajectory history, preserving score changes across rounds to lock in the highest-performing output for subsequent generation.

What is ASI forwarding and how does it propagate judge scores to the next round?▼

ASI forwarding passes the judge's evaluation scores from the current round to the next generator, using the preserved trajectory history to ensure subsequent iterations build upon the best-so-far candidate.

How do I handle score regression and rollback to a prior iteration during evaluation?▼

Handling score regression involves signaling when to revert to a prior iteration by using the recorded trajectory table, allowing you to roll back to a previous best candidate and pass its context forward instead of continuing with degraded results.

Can I use trajectory tracking in both single-file and workspace modes?▼

Trajectory tracking supports both single-file and workspace modes, enabling you to organize evaluation histories and manage best-so-far candidates whether your iteration process operates on individual files or across a full workspace environment.

When should I update the iteration trajectory table during a simmer evaluation round?▼

You should update the iteration trajectory table after each judge round completes, recording the latest scores and changes so the best candidate is identified, regression is detected, and the ASI is propagated to guide the next generator.