generative-thinking
Break out of a locked problem frame by picking one disciplined generative move — reframe, provocation (Po), random stimulus, SCAMPER, inversion, perspective shift, or constraint play — and committing to it before evaluating.
The skill is the interrupt for fixation, not a brainstorming workshop. Pick one move matched to the diagnosis, run it, apply the fire test (could this output have been produced without the move?), stop.
See SKILL.md for the diagnostic table, per-technique recipes with success signals, LLM-specific sourcing notes, and canonical references.
Provenance
- Lateral thinking, Po, random stimulus — Edward de Bono, Lateral Thinking (1970), Serious Creativity (1992)
- SCAMPER — Bob Eberle (1971), built on Alex Osborn's Applied Imagination (1953)
- Oblique Strategies — Brian Eno & Peter Schmidt (1974–2001)
- Functional fixedness (the bias this skill counters) — Karl Duncker (1935/1945); candle problem
- LLM-specific design fixation — Wadinambiarachchi et al., CHI 2024 (doi:10.1145/3613904.3642919): AI-generated examples during ideation increase fixation and reduce fluency, variety, originality vs. no-support baseline. Motivates the LLM-sourcing section.
Complements
- challenging — evaluates after generation
- convening-experts — synthesizes multiple role-based viewpoints
- tiling-tree — exhaustive MECE partitioning of a solution space
This skill generates distance, not judgment, coverage, or consensus.
Skill folder: generative-thinking
Release of generative-thinking version 0.2.0
📥 Download & Install
⬇️ Download generative-thinking.zip
To install:
- Click the download link above (ignore the "Source code" archives below - they're auto-generated by GitHub)
- Go to Claude.ai Skills Settings
- Upload the downloaded ZIP file
- Requires paid Claude Pro or Team account
See official documentation for more details.
Recent Changes
9ce2ded generative-thinking 0.2.0: add Family traversal move
5cca79a docs: Update CHANGELOG.md for released skills