thinking-map
/thinking-map
Split a subject into orthogonal axes, spread candidates along each, cross-link items from different axes into combinations that were not on any list, then prune against a stated criterion. Use for idea generation, choosing a direction, opening a problem from several angles, comparing options, or widening a set of candidate causes. Triggers — "mind map", "think this through with me", "open this up", "widen the options", "break it into axes", "what am I not considering", "help me brainstorm".
- Author
- beyondworks ↗
- Repository
- castra ↗
- Licence
- MIT
- Last repository change
- 16.09.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 16.09.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Split a subject into orthogonal axes, spread candidates along each, cross-link items from different axes into combinations that were not on any list, then prune against a stated criterion. Use for idea generation, choosing a direction, opening a problem from several angles, comparing options, or widening a set of candidate causes. Triggers — "mind map", "think this through with me", "open this up", "widen the options", "break it into axes", "what am I not considering", "help me brainstorm".
Triggers from the description
Arguments
/thinking-map [subject] [what you want out of it: options / ideas / candidate causes...]
Original author description
Split a subject into orthogonal axes, spread candidates along each, cross-link items from different axes into combinations that were not on any list, then prune against a stated criterion. Use for idea generation, choosing a direction, opening a problem from several angles, comparing options, or widening a set of candidate causes. Triggers — "mind map", "think this through with me", "open this up", "widen the options", "break it into axes", "what am I not considering", "help me brainstorm".
How it works
- 1. Split into axes first
- 2. Spread each axis
- 3. Cross-link — this is the stage that matters
- 4. Prune
- Output
- Do not
SKILL.md preview
---
name: thinking-map
description: Split a subject into orthogonal axes, spread candidates along each, cross-link items from different axes into combinations that were not on any list, then prune against a stated criterion. Use for idea generation, choosing a direction, opening a problem from several angles, comparing options, or widening a set of candidate causes. Triggers — "mind map", "think this through with me", "open this up", "widen the options", "break it into axes", "what am I not considering", "help me brainstorm".
user-invocable: true
argument-hint: "[subject] [what you want out of it: options / ideas / candidate causes...]"
---
The point is not to widen. It is to **connect**. Producing many items is something a model already does well. What it does badly is putting two branches together and getting something that was on neither list. This procedure constrains that one step.
Work through four stages in order. Skipping one collapses the result back into an ordinary list.
## 1. Split into axes first
Before writing a single candidate, break the subject into **orthogonal axes**. Usually three to five.
One test decides whether the split is right: **two items belong to the same axis only if they cannot both be true at once.** If they can co-occur, they belong to different axes. "Free" and "subscription" are one axis (pricing model). "Free" and "sold to enterprises" are two (pricing model, buyer).
Name each axis as a noun phrase. When the axes are down, ask once what is missing. The three most often forgotten are time (when), actor (who), and constraint (what blocks this).
## 2. Spread each axis
Write **at least four** candidates per axis. Stopping at three leaves you with the three obvious ones.
Make the last item on each axis a **deliberate extreme or inversion**: the thing nobody does, the opposite choice, or removing that axis altogether. Most of the combinations worth having in stage 3 come out of these.
Do not judge yet. Evaluating while spreading stops the spread.
## 3. Cross-link — this is the stage that matters
Pair items from **different** axes. Grouping within one axis is classification, not connection.
Make at least six pairs, and for each one **write the mechanism in a sentence**. Two words side by side is not a connection.
- Not a connection: "subscription + enterprise"
- A connection: "if enterprises pay per seat, individual users can stay free and the revenue still stands up"
Discard any pair whose mechanism you cannot write. Some pairs will turn out to need a third element to work — those are usually the valuable ones.
When the pairs are down, **ask once more**: what happens if two of these combinations are joined? Second-order links are where something genuinely absent from the original lists shows up.
## 4. Prune
Fix the criterion **before** cutting, and take it from the user's actual goal. Cutting without a stated criterion just keeps whatever is most familiar.
For each surviving combination, ask what would have to be true for it to work, whether that can be checked now, and what small test would settle it if not.
Cut down to three or fewer. Keep the one that lost narrowly, with the reason — when conditions change, that is the one that revives first.
## Output
Draw a mermaid mind map once there are more than six branches. Below it, list the surviving combinations with their mechanisms, and close with the single next step.
```mermaid
mindmap
root((subject))
axis one
item
item
axis two
item
item
```
Mermaid's mindmap syntax cannot express the cross-links, so write them below the diagram. The links matter more than the picture.
## Do not
- Start listing items without splitting axes first. That discards the entire value of the procedure.
- Stop at three items per axis. The unfamiliar ones start at the fourth.
- Pair words without a mechanism. That is a list pretending to be a synthesis.
- Cut on "this one looks best" with no stated criterion.
- Re-open a direction the user has already decided. Fix the settled axes and spread only the rest.
Files in this package (2)
- SKILL.ko.md 5 KB
- SKILL.md 4 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · beyondworks/castra | 100 | MIT |
| linssenstudio/thinking-map | 100 | MIT |
Database snapshot: 13.11.2026 · package version ed4c59b88711 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90brainstorm
Decompose a problem, feature, or goal into candidate ADRs and plan items for a documentation-led repo — one decision per ADR, dependency edges, suggested ordering. Proposes drafts for review and writes nothing until approved. Use when the user says "brainstorm ADRs", "break this… - 90brainstorm
Diverge on ideas for a project or feature, then capture them as atomic, grouped, Obsidian-compatible notes in .idea/. Use when the user wants to brainstorm, explore options, think through a problem space, generate ideas, or asks "what could we build", "what are our options",… - 100mind-map-analysis
Use when ideas, concerns, stakeholders, causes, or options are scattered and need a clear structure before deeper analysis. Use when applying the Mind Map Analysis consulting method and when a user asks for Mind Map Analysis, method execution, structured diagnosis, or action planning. - 100brainstorming
This skill should be used when the user wants to brainstorm, explore ideas, think through options, says 'let's brainstorm', 'what are our options', 'how might we', 'what if we', 'help me think through', 'explore approaches', or presents an open-ended problem without a clear… - 100think
Thinking mode router — selects the right analytical approach for a question. Use when thinking through a problem, analyzing deeply, brainstorming ideas, debating options, decomposing to root cause, challenging assumptions, or exploring from multiple perspectives. - 95ce:brainstorm
Explore requirements and approaches through collaborative dialogue before writing a right-sized requirements document and planning implementation. Use for feature ideas, problem framing, when the user says ''let''s brainstorm'', or when they want to think through options before…