Stats
Actions
Tags
From thinking-frameworks-skills
Performs axial-coding thematic clustering over a Substack corpus of published posts to surface candidate sections, using Braun & Clarke's six-phase analysis methodology.
How this skill is triggered — by the user, by Claude, or both
Slash command
/thinking-frameworks-skills:cluster-corpus-by-themeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
```
Per Curator run:
- [ ] Step 1: Read every post in corpus/published/** end-to-end (not just titles)
- [ ] Step 2: Extract 3-5 codes per post (concepts, methods, domains)
- [ ] Step 3: Group codes across posts by semantic similarity (axial)
- [ ] Step 4: Validate clusters — split or merge where needed
- [ ] Step 5: Report candidate clusters with membership, cohesion, outliers
cluster_1:
candidate_handle: "kalshi-log"
posts: [list of slugs]
cohesion: high | medium | low
centroid_codes: [top 5 codes]
outlier_posts: [weakly-attached members]
rejected_clusters: [clusters with <3 posts]
high: ≥5 posts, shared centroid, clear register.medium: 3-4 posts or mixed register.low: cluster exists but coherence is weak.recommend-prune and "watch" candidates.npx claudepluginhub lyndonkl/claude --plugin thinking-frameworks-skillsConverts 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.
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.
Plans and executes semantic topic clusters for blogs using SERP research, intent grouping, and automated content generation with interlinking. Invoke via /blog cluster.