From thinking-frameworks-skills
Drafts one-sentence suggestions to acknowledge simplified-boundary claims as teaching moments rather than hidden fragility.
How this skill is triggered — by the user, by Claude, or both
Slash command
/thinking-frameworks-skills:flag-boundary-breakThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
```
Per simplified-boundary claim:
- [ ] Step 1: Identify the intuition the writer was using (analogy, metaphor, concrete picture)
- [ ] Step 2: Identify precisely where the intuition breaks using primary source
- [ ] Step 3: Draft a one-sentence suggestion that names the break as a feature
- [ ] Step 4: Optionally suggest a follow-up post if break is too rich for a sentence
- [ ] Step 5: Return {intuition, break_point, fold_suggestion, optional_follow_up}
Claim: "Attention is O(n²) in memory."
Classification: simplified-boundary.
Primary source: Dao et al. 2022 — FlashAttention, arXiv:2205.14135. "FlashAttention uses O(N) memory rather than the O(N²) of standard attention."
Fold suggestion:
"The O(n²) figure is the naive memory cost — modern production attention (FlashAttention, Dao et al. 2022) is actually O(n) in HBM by never materializing the full attention matrix. The quadratic view is still the right intuition for 'why context windows are expensive' circa 2020, but the actual frontier now is 'attention is memory-bandwidth-bound,' which is a richer story — probably a follow-up post."
Optional follow-up: "FlashAttention as memory-bandwidth reframe."
wrong claims — those get fixed, not folded.npx claudepluginhub lyndonkl/claude --plugin thinking-frameworks-skillsStress-tests analogies by finding mapping breaks, classifying break type, and framing the break as a teaching opportunity for writing.
Construct well-structured arguments using the hypothesis-argument-example triad. Use for PR descriptions, ADRs, code review feedback, and technical proposals.
Reviews technical writing for clarity and accessibility by flagging unexplained jargon, hand-wavy process descriptions, and skipped steps. Useful when reviewing documentation, tutorials, or process-heavy content.