From thinking-frameworks-skills
Converts a candidate cluster from cluster-corpus-by-theme into a named section proposal with promise, fit confidence rating, and reasons-to-reject for writer review.
How this skill is triggered — by the user, by Claude, or both
Slash command
/thinking-frameworks-skills:propose-sectionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
```
Per qualifying cluster:
- [ ] Step 1: Name the cluster (working name from centroid codes)
- [ ] Step 2: Call write-section-promise for the one-sentence promise
- [ ] Step 3: Score each member post: tight | fair | borderline
- [ ] Step 4: Check non-overlap against existing section-map.md and other proposals this run
- [ ] Step 5: Assign fit_confidence:
- high: ≥5 tight-fit posts + strong cohesion + unambiguous non-overlap
- medium: 3-4 posts with mixed fit + narrowing promise
- low: borderline throughout; defer
- provisional: confident enough to name, uncertain enough to need probation
- [ ] Step 6: Write proposal block with reasons_to_reject (steelman the case against)
proposal:
name: "{Human name}"
slug: {kebab-case}
promise: "{one sentence}"
fit_confidence: high | medium | low | provisional
supporting_posts: [{slug, fit}]
borderline_posts: [{slug, reason}]
non_overlap_check: "Distinct from {other section} because..."
reasons_to_reject: "Two of these posts also fit {other section}. If those migrate, cluster drops to 3 posts and becomes marginal."
npx claudepluginhub lyndonkl/claude --plugin thinking-frameworks-skillsAssigns Substack draft or published posts to the best-fitting section based on content and section promises in section-map.md. Used for editorial workflows to load voice overlays or batch classify.
Plans and executes semantic topic clusters from a seed keyword: SERP research, intent grouping, hub-and-spoke architecture, SVG cluster map, and automated content generation with internal links.
Drafts publication-ready Theory sections for sociology journal articles. Guides structure, paragraph functions, contribution clusters, and prose calibration from analysis of 80 Social Problems/Social Forces papers.