Think assumption reversal

Skill product-on-purpose/thinking-framework-skills/skills/think-assumption-reversal

Evidence-graded, agent-executable thinking-method skills - 56 frameworks reduced to their working mechanism, honestly graded, and producing a concrete artifact. 56 frameworks + 4 tools + 9 recipes for Claude Code, Codex, and other AI agents. Advanced (Gold) tier.

Install

npx -y skills add product-on-purpose/thinking-framework-skills --skill think-assumption-reversal

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Generates non-obvious ideas by surfacing the foundational assumptions a problem or solution rests on, negating each, and reframing from the reversed assumptions, then shortlisting, producing an assumptions-and-reversals sheet. Use when an option space feels stuck inside default constraints, or when you need to expose premises that are taken for granted.

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.5 KB, as published. Nobody here has run it

Assumption Reversal

Solutions stay trapped inside the assumptions a problem is stated with. Assumption reversal makes those premises explicit, negates or reverses each, and generates ideas from the reversed world. It is not generic inversion ("how would we cause failure?"); it targets the foundational premises the option space rests on and uses their reversal as an idea generator. The output is an assumptions-and-reversals sheet ending in a shortlist. Reversed assumptions are candidates to explore, not recommendations.

When to Use

An option space feels stuck inside default constraints.
The obvious solutions all seem to share a hidden premise.
Early divergent exploration, when breadth matters more than convergence.

When NOT to Use

When the binding constraints are genuinely fixed (regulatory, physical) and cannot be reversed in reality.
When you need to converge and choose (use a decision skill).
As a source of recommendations (it produces candidates, not decisions).
If it would only reverse trivial, cosmetic assumptions.

Instructions

When asked to run assumption reversal, follow these steps:

State the problem or solution in one line.
Surface the foundational assumptions. List the load-bearing premises it rests on (business model, user, channel, sequence, who pays, what is required). Push for the ones so basic they are usually unspoken.
Reverse each. Negate or invert the assumption ("what if the opposite were true?").
Generate from the reversal. For each reversed assumption, write the ideas it provokes. Keep the ideas genuinely tied to the reversal.
Shortlist. Pick the most promising non-obvious ideas to carry forward, and note what would have to be true for each to be viable.
Emit the sheet per references/TEMPLATE.md.

Output Format

Use the template in references/TEMPLATE.md. The deliverable is the assumptions, reversals, ideas, and shortlist, not prose.

Quality Checklist

Before finalizing, verify:

The assumptions surfaced are load-bearing, not trivial.
Each assumption is genuinely reversed, not just reworded.
The ideas are tied to the reversal, not generic.
A shortlist of non-obvious ideas is selected, flagged as candidates not decisions.
The output is the sheet artifact, not prose.

Evidence

Tier P. Assumption reversal is a recognized divergent-ideation technique from lateral-thinking practice, distinct from inversion. Deliberately challenging default premises broadens the option set, but there is no strong evidence it outperforms other generators, and reversing an assumption does not make the reversal viable. Evidence is transferred from human creativity practice, not AI-validated. Full grading: evidence/dossier.md.

Examples

See references/EXAMPLE.md for a completed sheet.