danium/lateral-thinking — explained in plain English
Analysis updated 2026-05-18
Get past obvious feature ideas when a product feels stuck on retention or growth
Use the router skill to diagnose which brainstorming technique fits your situation
Apply named techniques like Six Thinking Hats or SCAMPER inside a coding agent session
Surface the underlying pattern behind a batch of brainstormed ideas instead of just a list
| danium/lateral-thinking | 0-bingwu-0/live-interpreter | 010zx00x1/faresnipe | |
|---|---|---|---|
| Stars | 2 | 2 | 2 |
| Language | — | Python | Python |
| Setup difficulty | easy | moderate | easy |
| Complexity | 1/5 | 2/5 | 2/5 |
| Audience | pm founder | general | general |
Figures from each repo's GitHub metadata at analysis time.
Lateral thinking is a collection of skills that give an AI coding agent structured ways to come up with product ideas that are not the obvious first answer. Instead of one general brainstorming prompt, it includes eight distinct techniques plus a router skill that looks at how you describe being stuck and picks the technique that fits. The techniques are based on real, named methods rather than invented ones: Random Stimulus, Provocation, and Concept Fan come from Edward de Bono's writing on lateral thinking, Six Thinking Hats is also de Bono's, SCAMPER comes from Bob Eberle building on Alex Osborn's checklist, Forced Analogy comes from Synectics, Assumption Inversion is a classic dialectic approach, and Worst Possible Idea is standard reverse brainstorming used in design schools. Each technique targets a specific symptom, for example use random stimulus when ideas all feel the same, use provocation when a rule feels unbreakable, or use six hats when a decision is being made too quickly and everyone already agrees. A key part of the design is that each skill is required to show when a step produces nothing useful, rather than padding its output with a forced idea just to fill a slot. It also asks the agent to look across everything it generated afterward and name the underlying pattern, not just list separate ideas. The README's own example shows a technique reporting three of seven operations as empty, with the meaningful finding turning out to be about what was missing rather than what was generated. Installation works through a generic skills installer command, through a Claude Code plugin marketplace command, by asking Codex's skill installer to pull it from the GitHub repository, or by manually copying the skills folder into an agent's skills directory. The router skill depends on its sibling techniques being installed alongside it, so the whole bundle installs together rather than one piece at a time. The project is released under the MIT license, which allows free use, including commercial use, as long as the copyright notice is kept.
A set of skills that give AI coding agents eight structured brainstorming techniques, plus a router that picks the right one for how you are stuck.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly pm founder.
This repo across BitVibe Labs
Don't trust strangers blindly. Verify against the repo.