Skip to content

Thinking Framework Skills

Evidence-graded thinking methods for agents and the humans who work with them. Each one is a mechanism, not a brand, graded honestly, and produces a concrete artifact.

A library of thinking frameworks (premortem, reference-class forecasting, argument mapping, and more) rebuilt for agents. Three things make it different from a list of mental models:

Mechanism over ritual

Each skill implements the durable cognitive move, named for what it does, not a trademarked brand.

Honest evidence grading

Every skill carries a tier (S/M/P/V/A/C/X) and a dossier stating what the research does and does not show. Including when the answer is “the evidence is weaker than people think.”

Artifact, not prose

Every skill produces a concrete, reusable deliverable: a risk register, an option matrix, an argument map, a Thinking Plan.

Explicit 'when not to use'

Each skill says where it misleads, to guard against cargo-cult execution.

I'm not sure where to start

Read the Framework Advisor: describe your situation and get a prioritized plan of which frameworks to use and why.

Teach me by domain

Browse the domains: the families of cognitive operations, from reframing to stress-testing to reflection.

Show me the evidence

The bibliography is the honest-grading promise made browsable: every claim traces to a graded source.

Solve a recurring job

The recipes chain skills end to end: reframe a problem, expand options, stress-test a decision, audit reasoning.

Thinking Framework Skills v0.3.0 · 38 frameworks