simmer SKILL.md skillA

simmer from 2389-research/simmer is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add 2389-research/simmer/simmer@git:20260706.3f264f4

Pins git:20260706.3f264f4 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: 2389-research/simmer
Path: skills/simmer/SKILL.md
Versions recorded: 2
Latest version: git:20260706.3f264f4, committed Jul 6, 2026
First version recorded: May 7, 2026
Size: 24,056 bytes
Repository stars: 16
License: MIT

Refines any artifact through scored iterations using an investigation-first judge board. Use when the user says "simmer this", "refine this", "hone this", or wants to improve a document, prompt, email, design, spec, or pipeline through multiple rounds of criteria-driven feedback.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Simmer

Iterative refinement loop — take an artifact (single file or workspace) and hone it repeatedly against user-defined criteria until it's as good as it can get.

**Related skills (test-kitchen family):**
- `test-kitchen:omakase-off` — don't know what you want → parallel designs → react → pick
- `test-kitchen:cookoff` — know what you want, it's code → parallel implementations → fixed criteria → steal the best
- `simmer` — know what you want, it's anything → user-defined criteria → iterate until good

## Flow

```
"Simmer this" / "Refine this" / "Optimize this pipeline"
    ↓
┌─────────────────────────────────────┐
│  SETUP (identify + criteria)        │
│  Load simmer-setup subskill         │
│                                     │
│  Output: artifact, rubric, N iters, │
│  evaluator (optional),              │
│  background (optional)              │
└─────────────────────────────────────┘
    ↓
┌─────────────────────────────────────┐
│  LOOP (default 3 iterations)        │
│                                     │
│  Each iteration:                    │
│  1. Dispatch generator subagent     │
│  2. Run evaluator (if present)      │
│  3. Dispatch judge subagent         │
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add 2389-research/simmer/simmer@sha256:85cb525212a3dbb0

The line at the top of this page pins the label git:20260706.3f264f4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_hacjotpjklhke7p6.svg)](https://markdownregistry.com/a/art_hacjotpjklhke7p6)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between May 7, 2026 and Jul 6, 2026, about one every 60 days.

version	committed	commit	size	audit
git:20260706.3f264f4 latest	2026-07-06	3f264f4	24,056 B	A	view · diff
git:20260507.5c94896	2026-05-07	5c94896	24,403 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (24056 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

2389-research/simmer · 16 stars · license MIT · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hacjotpjklhke7p6
GET https://markdownregistry.com/api/v1/resolve?ref=2389-research/simmer/simmer
GET https://markdownregistry.com/api/v1/blob/85cb525212a3dbb038d3bf72bd7678f4f73fd8165500d7b1923f7faacdcdd135

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from 2389-research/simmer

CLAUDE.md CLAUDE.md file

2389-research/simmer · CLAUDE.md

git:20260507.5c94896 · audit A · 16 stars

simmer-generator SKILL.md skill

2389-research/simmer · skills/simmer-generator/SKILL.md · Do not invoke directly — dispatched as a subagent by the simmer orchestrator. Produces an improved artifact version by…