llms.txt@site/publicA

llms.txt@site/public from product-on-purpose/thinking-framework-skills is an llms.txt file: plain text a project publishes for AI models to read.

Install it, pinned
mdr add product-on-purpose/thinking-framework-skills/site/public/llms.txt@git:20261021.903ca21

Pins git:20261021.903ca21 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
llms.txt file
Repository
product-on-purpose/thinking-framework-skills
Path
site/public/llms.txt
Versions recorded
8
Latest version
git:20261021.903ca21, committed Oct 21, 2026
First version recorded
Jun 16, 2026
Size
22,168 bytes
Repository stars
21
License
Apache-2.0

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

# Thinking Framework Skills

> An evidence-graded library of agent-executable thinking-method skills for Claude Code, Codex, and other AI agents. 63 skills, 4 tools, and 9 recipes; every skill produces a concrete, named artifact, and 3 of these components also run as Claude Code subagents. 150 methods were evaluated and graded, 63 ship as skills.

Machine-readable: [catalog.json](https://thinking-framework-skills.productonpurpose.com/catalog.json) (the invokable skills, tools, and recipes) and [evaluated.json](https://thinking-framework-skills.productonpurpose.com/evaluated.json) (all 150 evaluated methods). Full text: [llms-full.txt](https://thinking-framework-skills.productonpurpose.com/llms-full.txt) inlines every component for one-fetch ingestion.

## Start here
- [Getting started](https://thinking-framework-skills.productonpurpose.com/start/getting-started/): install and first run
- [Showcase](https://thinking-framework-skills.productonpurpose.com/showcase/): worked, end-to-end examples
- [Does this work?](https://thinking-framework-skills.productonpurpose.com/start/does-this-work/): the behavioral-eval results
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add product-on-purpose/thinking-framework-skills/site/public/llms.txt@sha256:f71fa9177da3f397

The line at the top of this page pins the label git:20261021.903ca21, 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_24r3mgm3xwt5cjhf.svg)](https://markdownregistry.com/a/art_24r3mgm3xwt5cjhf)

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

Versions

The registry has recorded 8 versions of this file, between Jun 16, 2026 and Oct 21, 2026, about one every 18 days.

versioncommittedcommitsizeaudit
git:20261021.903ca21 latest2026-10-21 903ca21 22,168 BA view · diff
git:20261020.a23e8f82026-10-20 a23e8f8 22,168 BA view · diff
git:20261015.c1784342026-10-15 c178434 22,168 BA view · diff
git:20260620.c129d3c2026-06-20 c129d3c 20,656 BA view · diff
git:20260620.105aec42026-06-20 105aec4 19,629 BA view · diff
git:20260619.06bd3b32026-06-19 06bd3b3 19,190 BA view · diff
git:20260616.058baca2026-06-16 058baca 19,044 BA view · diff
git:20260616.c9ce7232026-06-16 c9ce723 19,668 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (22168 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

product-on-purpose/thinking-framework-skills · 21 stars · license Apache-2.0 · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_24r3mgm3xwt5cjhf
GET https://markdownregistry.com/api/v1/resolve?ref=product-on-purpose/thinking-framework-skills/site/public/llms.txt
GET https://markdownregistry.com/api/v1/blob/f71fa9177da3f397131824067f396e8e5d432b3b310ad14cb3d725bd1e90b44e

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: how to add an llms.txt file to a website · which agent file does what.

More from product-on-purpose/thinking-framework-skills

AGENTS.md AGENTS.md file
product-on-purpose/thinking-framework-skills · AGENTS.md
git:20261021.903ca21 · audit A · 21 stars
llms-full.txt@site/public llms.txt file
product-on-purpose/thinking-framework-skills · site/public/llms-full.txt
git:20261021.903ca21 · audit A · 21 stars
think-abstraction-laddering SKILL.md skill
product-on-purpose/thinking-framework-skills · skills/think-abstraction-laddering/SKILL.md · Builds an abstraction ladder that moves a problem up ("why / to what end?") and down ("how / what specifically?") to…
v0.1.0 · audit A · 21 stars
think-affinity-mapping SKILL.md skill
product-on-purpose/thinking-framework-skills · skills/think-affinity-mapping/SKILL.md · Produces a clustered theme map that groups many raw notes, observations, quotes, or data points bottom-up into a small…
v0.1.0 · audit A · 21 stars
think-after-action-review SKILL.md skill
product-on-purpose/thinking-framework-skills · skills/think-after-action-review/SKILL.md · Produces a structured after-action review by comparing what was expected against what actually happened, diagnosing why…
v0.1.0 · audit A · 21 stars
think-analysis-of-competing-hypotheses SKILL.md skill
product-on-purpose/thinking-framework-skills · skills/think-analysis-of-competing-hypotheses/SKILL.md · Handles a by-name request for ACH (Analysis of Competing Hypotheses), the evidence-by-hypothesis disconfirmation…
v0.1.0 · audit A · 21 stars
think-argument-mapping SKILL.md skill
product-on-purpose/thinking-framework-skills · skills/think-argument-mapping/SKILL.md · Produces an argument map by laying out a claim's supporting reasons, the co-premises each silently depends on, and the…
v0.1.0 · audit A · 21 stars
think-assumption-reversal SKILL.md skill
product-on-purpose/thinking-framework-skills · skills/think-assumption-reversal/SKILL.md · Generates non-obvious ideas by surfacing the foundational assumptions a problem or solution rests on, negating each…
v0.1.0 · audit A · 21 stars
think-authentic-dissent SKILL.md skill
product-on-purpose/thinking-framework-skills · skills/think-authentic-dissent/SKILL.md · Checks whether a decision has genuine minority dissent or only smooth surface consensus, identifies who actually holds…
v0.1.0 · audit A · 21 stars
think-backcasting SKILL.md skill
product-on-purpose/thinking-framework-skills · skills/think-backcasting/SKILL.md · Produces a backcast path by fixing a vivid desired future state and reasoning backward through the milestones and…
v0.1.0 · audit A · 21 stars
think-belief-update-routine SKILL.md skill
product-on-purpose/thinking-framework-skills · skills/think-belief-update-routine/SKILL.md · Produces a belief-update ledger that re-scores a standing inventory of open beliefs against newly arrived evidence on a…
v0.1.0 · audit A · 21 stars
think-boundary-critique SKILL.md skill
product-on-purpose/thinking-framework-skills · skills/think-boundary-critique/SKILL.md · Audits the boundary judgments that silently define a problem frame. For each of four sources, who benefits, who…
v0.1.0 · audit A · 21 stars

Every file in product-on-purpose/thinking-framework-skills

Other files named llms.txt@site/public

llms.txt@site/public llms.txt file
silverstein/minutes · site/public/llms.txt
git:20261020.330074e · audit A · 1,562 stars
llms.txt@site/public llms.txt file
gnosil/semantix · site/public/llms.txt
git:20260907.7b873db · audit A · 819 stars
llms.txt@site/public llms.txt file
jaypokale/chisle · site/public/llms.txt
git:20261016.6d798df · audit A · 696 stars
llms.txt@site/public llms.txt file
mverab/egeoagents · site/public/llms.txt
git:20261008.311a43a · audit A · 205 stars
llms.txt@site/public llms.txt file
vaibhavarora14/job-application-agent · site/public/llms.txt
git:20261022.ca79dcc · audit A · 161 stars
llms.txt@site/public llms.txt file
jkheadley/instar · site/public/llms.txt
git:20260309.f153ee9 · audit A · 84 stars
llms.txt@site/public llms.txt file
millw14/merrymen · site/public/llms.txt
git:20261015.398f511 · audit A · 68 stars
llms.txt@site/public llms.txt file
midagedev/gadak · site/public/llms.txt
git:20260918.ef7114a · audit A · 44 stars

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