Mind map
Opinionated Agent Skills for AI-native autodidacts — deep learning, dense papers, public proof. Opinionated Agent Skills for AI-native autodidacts — deep learning, dense papers, public proof. By School of the Bear
npx -y skills add loursCreatif/ours-stack --skill mind-mapAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 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
Carte mentale interactive — extraction hiérarchique depuis brief/notes/report vers mind-map.json éditable + mind-map.html autonome (pan/zoom, expand/collapse, liens sources). Zero CDN. Presets partagés avec layout-html. Pas de recherche. Déclencheurs : "mind map", "carte mentale", "mind-map", "vue hiérarchique". Commande : /mind-map.
SKILL.md
6.3 KB, as published. Nobody here has run it
Mind Map
Carte mentale cliquable — plus rapide à parcourir qu'un article linéaire, moins immersif qu'un palais 3D.
When to use (vs other skills)
| Skill | Responsibility | Does NOT |
|---|---|---|
/layout-html | Article linéaire + SVG figures | Arbre hiérarchique |
/mind-map | This skill — carte mentale interactive | Nouvelle recherche |
/deep-research | Synthèse + sources-index | Carte mentale |
Optional pipeline (never auto-chained):
/bear-hours → notes / dense-read → /mind-map
/deep-research → /mind-map
Hard rules
- No research — never
WebSearch/WebFetch. Work only from provided text/files. - Zero external assets — no CDN, no Google Fonts, no external scripts/images/stylesheets, no
fetch(). - JSON is source of truth —
mind-map.jsoneditable; HTML regenerated from JSON. - Faithful to source — never invent URLs, claims, or nodes absent from input.
- Limits — max 80 nodes, depth 5. Overflow → merge siblings into one
detailwith bulletnote(deterministic, no ask). - Escape output — embed JSON via structured serialization only; never inject raw markdown HTML into template.
- Open browser —
open <path>on macOS after write.
Step 0: Style — AskUserQuestion
Title: Mind Map — Style
Offer exactly these 4 options (AskUserQuestion max): warm, editorial, minimal, creative. Custom style goes through the automatic "Other" option — treat the free text as a custom preset per references/presets.md § Custom. Smart-skip if one of these presets is named in message.
Default when skipped: warm for all inputs.
Load references/presets.md and token blocks from references/html-template.md.
Step 1: Intake — detect input mode
| Mode | Trigger | Source | Output |
|---|---|---|---|
| A — Study | studies/<slug>/ or slug | brief.md + optional notes.md | studies/<slug>/mind-map.{json,html} |
| B — Research | research/<slug>/ | report.md + optional sources-index.md | research/<slug>/mind-map.{json,html} |
| C — File | path to .md | that file | <dir>/mind-map.{json,html} |
| D — Pasted | text in chat | message body | output/mind-map/<slug>/map.{json,html} |
| E — Regenerate | regenerate / existing JSON | mind-map.json only | regen HTML only |
Invocation examples:
/mind-map biomimetisme-locomotion-chantier
/mind-map studies/biomimetisme-locomotion-chantier/brief.md
/mind-map research/robots-assemblage-structurel-chantier
/mind-map regenerate studies/foo/mind-map.json
Guard: no text and no resolvable slug → ask for content or path.
Step 2: Extract hierarchy
Load references/extraction-rules.md and references/node-schema.md.
Parse markdown headings, bullets, source lines. Assign id, type, label, summary, note, href, collapsed, and optional importance.
Use importance only for visual hierarchy: 5 root / central thesis, 4 major branches, 3 supporting concepts, 2 details or examples, 1 sources or minor leaves. Omit it when unsure; the HTML renderer infers a safe size.
Leave top-level layout omitted or "auto" by default. Set "centered" only when the source is clearly wide/exploratory and shallow; set "tree" only when the user explicitly wants the classic hierarchy.
Run validation:
python3 mind-map/scripts/validate-map.py "<path>/mind-map.json"
On validation error → fix JSON before composing HTML.
Step 3: Write JSON then HTML
- Write
mind-map.jsonwith accuratemeta.nodeCount - Compose HTML:
python3 mind-map/scripts/compose-html.py "<path>/mind-map.json"
Or hand-compose from references/html-template.md if script unavailable.
Overwrite without asking unless file modified <1h ago and user didn't say overwrite.
Step 4: Deliver
open "<absolute-path>/mind-map.html"
Tell the user:
- Output paths (json + html)
- Style preset used
- Input mode
- Node count by type (
concept,detail,example,source); mentionsummary/notecoverage when present - Reminder: edit
mind-map.jsonthen/mind-map regenerate <path>
Errors (deterministic)
| Condition | Action |
|---|---|
| Empty / unparseable markdown | Stop — ask for clearer structure or paste headings |
| No brief (study mode) | Suggest /bear-hours first |
| >80 nodes after extraction | Merge deepest siblings into grouped detail until ≤80 |
Duplicate id | Regenerate ids with slug prefix |
source without href | Keep node; panel shows label only |
| Invalid JSON (regenerate) | Stop — show validate-map.py error |
compose-html.py missing | Fall back to template in references/html-template.md |
Escape hatches
| User says | Action |
|---|---|
regenerate | Mode E — JSON → HTML only |
overwrite | Replace without confirmation |
warm / editorial / minimal / creative | Smart-skip style question |
| Described style ("sombre néon", "pastel"…) | Smart-skip — custom preset per references/presets.md § Custom (meta.customTokens) |
| slug only | Try studies/<slug>/ then research/<slug>/ |
Self-check before delivery
- No WebSearch / WebFetch
- All nodes traceable to input
- ≤80 nodes, depth ≤5
-
validate-map.pypasses - HTML offline-ready (no external URLs in assets)
- JSON + HTML written + browser opened
References
references/node-schema.md— JSON contractreferences/extraction-rules.md— markdown → treereferences/html-template.md— manual compose fallbackreferences/presets.md— layout-html token alignmentreferences/design-decisions.md— design decision logscripts/validate-map.py— schema checkscripts/compose-html.py— JSON → HTML