synthesis-llm-setup SKILL.md skillA

synthesis-llm-setup from synthesisengineering/synthesis-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add synthesisengineering/synthesis-skills/synthesis-llm-setup@v2.0.0

Pins v2.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
synthesisengineering/synthesis-skills
Path
skills/synthesis-llm-setup/SKILL.md
Versions recorded
2
Latest version
v2.0.0, committed Oct 5, 2026
First version recorded
Jul 29, 2026
Size
5,338 bytes
Repository stars
23
License
Apache-2.0

Guide for setting up and configuring LLM projects across platforms. Use when setting up a Claude Project, creating a ChatGPT GPT, configuring a Gemini Gem, setting up an AI assistant with custom instructions and knowledge, or configuring any LLM platform with AI Knowledge content.

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

# LLM Setup

Configure Claude Projects, ChatGPT GPTs, Gemini Gems, and other LLM platforms using compiled AI Knowledge content from the ragbot system.

## Binding rules

1. **Edit `source/` files, never the generated output.** CI/CD rebuilds `all-knowledge.md` on every push to `source/`, so a hand edit to it is overwritten.
2. **Take instructions from `compiled/{project}/instructions/`:** the file for that platform (`claude.md`, `chatgpt.md`, `gemini.md`), or the closest match for any other LLM.
3. **Recompile instructions only when they change** (`ragbot compile --project {name}`); knowledge concatenation needs no manual step.
4. **Deliver knowledge per platform:** GitHub sync for Claude; upload `all-knowledge.md` to ChatGPT and Gemini, and upload it again after source changes.
5. **Compile where the audience matches.** A compilation includes only repos the compiling user can access, which is what keeps personal content out of team and client projects.
6. **Verify each project** with a representative query before calling it set up.

## Contents
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add synthesisengineering/synthesis-skills/synthesis-llm-setup@sha256:2926d62a4aa92794

The line at the top of this page pins the label v2.0.0, 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 badge

[![mdr](https://markdownregistry.com/badge/art_gxbr7wuqtd7wttcu.svg)](https://markdownregistry.com/a/art_gxbr7wuqtd7wttcu)

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

Versions

The registry has recorded 2 versions of this file, between Jul 29, 2026 and Oct 5, 2026, about one every 68 days.

versioncommittedcommitsizeaudit
v2.0.0 latest2026-10-05 227204f 5,338 BA view · diff
v1.0.02026-07-29 9b134e7 7,230 BA 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 (5338 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

synthesisengineering/synthesis-skills · 23 stars · license Apache-2.0 · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_gxbr7wuqtd7wttcu
GET https://markdownregistry.com/api/v1/resolve?ref=synthesisengineering/synthesis-skills/synthesis-llm-setup
GET https://markdownregistry.com/api/v1/blob/2926d62a4aa927944a29923c0feea8bdb0276f95fd481b7282bc124ec0e633b7

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 synthesisengineering/synthesis-skills

AGENTS.md AGENTS.md file
synthesisengineering/synthesis-skills · AGENTS.md
git:20261105.9bc7d02 · audit A · 23 stars
CLAUDE.md CLAUDE.md file
synthesisengineering/synthesis-skills · CLAUDE.md
git:20260730.93876b7 · audit B · 23 stars
synthesis-absence-coordination SKILL.md skill
synthesisengineering/synthesis-skills · skills/synthesis-absence-coordination/SKILL.md · Coordinate an absence end to end (vacation, conference, family visit, medical leave): notification order, coverage and…
v2.0.0 · audit A · 23 stars
synthesis-action-sheet SKILL.md skill
synthesisengineering/synthesis-skills · skills/synthesis-action-sheet/SKILL.md · One page of what the principal must still do after agents act: done items folded, staged sends awaiting approval codes…
v1.2.0 · audit A · 23 stars
synthesis-adversarial-review SKILL.md skill
synthesisengineering/synthesis-skills · skills/synthesis-adversarial-review/SKILL.md · Run bounded adversarial review by differently shaped agents against the principal's outcome: artifact-complete rounds…
v2.0.0 · audit A · 23 stars
synthesis-agent-conformance SKILL.md skill
synthesisengineering/synthesis-skills · skills/synthesis-agent-conformance/SKILL.md · Audit and verify that synthesis behaves the same in Claude Code, Codex and Muse: source lint, installed parity, hook…
v2.0.1 · audit A · 23 stars
synthesis-agent-correspondence SKILL.md skill
synthesisengineering/synthesis-skills · skills/synthesis-agent-correspondence/SKILL.md · Compose and send honest agent correspondence on Slack, email and other channels: principal-direct, assistant and bot…
v4.1.0 · audit A · 23 stars
synthesis-agent-guardrails SKILL.md skill
synthesisengineering/synthesis-skills · skills/synthesis-agent-guardrails/SKILL.md · Pre-tool guards beyond sends: the account a calendar or mail call acts as, a browser call's Chrome profile, deploys and…
v2.3.2 · audit A · 23 stars
synthesis-anti-shortcuts SKILL.md skill
synthesisengineering/synthesis-skills · skills/synthesis-anti-shortcuts/SKILL.md · Catch the lazy-shortcut antipattern: costume vocabulary that hides deferral, dismissal or false consultation…
v2.2.0 · audit A · 23 stars
synthesis-article-refresh SKILL.md skill
synthesisengineering/synthesis-skills · skills/synthesis-article-refresh/SKILL.md · Refresh an older published article into its best version: clearer argument, fuller period-appropriate evidence, better…
v2.0.0 · audit A · 23 stars
synthesis-article-writing SKILL.md skill
synthesisengineering/synthesis-skills · skills/synthesis-article-writing/SKILL.md · Write and review thought leadership articles and blog posts: reader briefing, research, drafting, critical review, and…
v3.0.0 · audit A · 23 stars
synthesis-autopilot SKILL.md skill
synthesisengineering/synthesis-skills · skills/synthesis-autopilot/SKILL.md · Run an explicitly delegated whole task to the end from a plan file in the project, unattended when needed. Use only on…
v4.0.0 · audit A · 23 stars

Every file in synthesisengineering/synthesis-skills

Browse by kind, by grade A, or by owner.