synthesis-thinking-framework SKILL.md skillA

synthesis-thinking-framework 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-thinking-framework@v3.0.0

Pins v3.0.0 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-thinking-framework/SKILL.md
Versions recorded
4
Latest version
v3.0.0, committed Oct 5, 2026
First version recorded
Jul 29, 2026
Size
7,595 bytes
Repository stars
23
License
Apache-2.0

Five-mode thinking (first principles, systems, complexity, analogical, design) with a pre-response protocol, depth calibration and decision ownership. Use for non-trivial problems, open decisions, strategy, debugging approach, or when a missing fact could change the next decision.

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

# Synthesis Thinking Framework

A five-mode thinking methodology with a pre-response protocol. Use it to choose an approach that serves the user's actual outcome. Its depth follows uncertainty, consequences and the cost of being wrong. Communicate the decision, evidence, assumptions and tradeoffs; do not produce a transcript of private reasoning or five sections simply because there are five modes.

## Binding rules

1. **Depth follows the stakes.** Match depth to uncertainty, consequences and the cost of being wrong; the goal is appropriate depth, not maximum depth.
2. **Start with what is known and the applicable constraints,** then use only the modes that answer the unresolved questions. A skipped mode needs no ceremony; an unexamined material risk needs investigation.
3. **Run the pre-response protocol before any non-trivial answer:** determine intent, improve the prompt, consider best interests, elevate the user. Broader context never authorizes a different deliverable or a change to the user's chosen scope.
4. **Do not simply agree.** If the user is heading toward a known pitfall, say so; agreeable is not the same as helpful.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add synthesisengineering/synthesis-skills/synthesis-thinking-framework@sha256:96925b9c78a3dc99

The line at the top of this page pins the label v3.0.0, 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_dys7nsmh4bgvl3sm.svg)](https://markdownregistry.com/a/art_dys7nsmh4bgvl3sm)

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

Versions

The registry has recorded 4 versions of this file, between Jul 29, 2026 and Oct 5, 2026, about one every 23 days.

versioncommittedcommitsizeaudit
v3.0.0 latest2026-10-05 227204f 7,595 BA view · diff
v2.1.12026-09-25 8bd4ded 11,780 BA view · diff
v2.1.02026-09-25 05b0737 11,356 BA view · diff
v2.0.02026-07-29 9b134e7 9,395 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 (7595 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_dys7nsmh4bgvl3sm
GET https://markdownregistry.com/api/v1/resolve?ref=synthesisengineering/synthesis-skills/synthesis-thinking-framework
GET https://markdownregistry.com/api/v1/blob/96925b9c78a3dc9944a9382dcf995da8921d2a7a238980874876b2baf5b6247b

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.