cluster-corpus-by-theme

$npx mdskill add lyndonkl/claude/cluster-corpus-by-theme

Cluster posts by theme using Braun & Clarke's six-phase analysis.

  • Reveals candidate sections from full post bodies without titles.
  • Depends on the substacker corpus of published posts.
  • Groups semantic codes via axial similarity and validates clusters.
  • Outputs YAML with candidate handles, membership, and cohesion.

SKILL.md

.github/skills/cluster-corpus-by-themeView on GitHub ↗
---
name: cluster-corpus-by-theme
description: Performs axial-coding-style thematic clustering over the substacker corpus of published posts to surface candidate sections. Uses Braun & Clarke's six-phase thematic analysis — familiarization, initial coding, searching for themes, reviewing themes, defining themes, naming. Reads full bodies, not titles. Use when re-opening the section question. Trigger keywords: cluster, theme, axial coding, thematic analysis, candidate sections.
---

# Cluster Corpus by Theme

## Workflow

```
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
```

## Output

```yaml
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]
```

## Heuristics

- Cohesion `high`: ≥5 posts, shared centroid, clear register.
- Cohesion `medium`: 3-4 posts or mixed register.
- Cohesion `low`: cluster exists but coherence is weak.
- Reject any cluster with <3 posts (below the 3-post floor for real sections).

## Guardrails

1. Read full post bodies. Titles are marketing; bodies are the beat.
2. Do not force every post into a cluster. Outliers are legitimate.
3. If >30% of corpus doesn't cluster coherently (all cohesion low), emit "corpus too heterogeneous" → Curator abandons section proposals this run.
4. Include rejected clusters in output — they feed `recommend-prune` and "watch" candidates.
5. Single-threaded. Don't race on the corpus.

More from lyndonkl/claude

SkillDescription
abstraction-concrete-examplesBuilds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
academic-letter-architectGuides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
adr-architectureDocuments significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
adverse-selection-priorProduces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it. Applies Akerlof market-for-lemons logic -- if they offered it, they believe it is +EV for them, so the prior that it is +EV for us is materially below 50%. Reusable across trade evaluation, waiver drops (another team dropping a player is also adverse selection), job-offer analysis, M&A, and any "someone offered me this" situation. Use when you receive an unsolicited trade/offer/proposal, analyzing incoming trade prior, evaluating why a counterparty proposed a deal, or when user mentions adverse selection, market for lemons, why did they offer this, incoming trade prior, they proposed it, Bayesian adjustment on received offer.
alignment-values-north-starCreates actionable alignment frameworks that give teams a shared North Star (direction), values (guardrails), and decision tenets (behavioral standards). Enables autonomous decision-making while maintaining organizational coherence. Use when starting new teams, scaling organizations, defining culture, establishing product vision, resolving misalignment, creating strategic clarity, or when user mentions North Star, team values, mission, principles, guardrails, decision framework, or cultural alignment.
analogy-weight-checkFor every analogy in a substacker draft, verifies it carries mechanical weight — the analogy does real work explaining the mechanism, not merely decorates it. Cross-references analogy-catalog.md for novelty (is this analogy reused from a prior post?) and domain fit (biology > organizational > sports preferred; physics/military disfavored). Use whenever an analogy appears in the draft. Trigger keywords: analogy weight, decorative, mechanical weight, reused analogy, catalog check, metaphor check.
answer-uncomfortable-questionTakes one strategic question about substacker ("should we launch paid?", "is this section dead?", "are we writing for the wrong audience?") and produces the mandatory evidence + reasoning + downside triad plus a recommendation. Used 3 times per Growth Strategist review. Trigger keywords: uncomfortable question, strategic question, evidence reasoning downside, triad.
attribute-performanceFor each substacker post that materially over- or under-performs the rolling baseline (|z| ≥ 1.0), produces a plain-English attribution paragraph with calibrated confidence (high / medium / low / unexplained). Considers subject-line effect, topic zeitgeist, external share, day-of-week, length effect, and audience-notes signals. Labels unexplained outliers explicitly rather than fabricating a story. Use after compute-baseline when outlier posts exist. Trigger keywords: attribution, why did this post work, outlier explanation, performance analysis.
auction-first-price-shadingComputes the optimal shaded bid for a first-price sealed-bid auction given a true private value, an estimate of the number of competing bidders N, and a value-distribution assumption. Implements the `(N-1)/N` equilibrium shading rule for uniform private values, adjusts for log-normal or empirical value distributions, layers a risk-aversion adjustment, and caps output against the bidder's remaining budget. Domain-neutral auction theory reusable across fantasy sports (baseball FAAB, NBA/NHL waiver auctions), prediction-market limit sizing, sealed procurement bids, and any blind-bid context. Use when user mentions "first-price auction bid", "sealed bid shading", "(N-1)/N", "FAAB bid amount", "auction shading", "optimal bid first-price", "bid for sealed-bid", "blind bid sizing", or when downstream logic needs a principled shade factor rather than an ad-hoc heuristic.
auction-winners-curse-haircutApplies a Bayesian haircut to a bid valuation for common-value auctions where winning is itself evidence the bidder over-estimated. Takes a raw valuation, a value-type classification (common_value / private_value / mixed), the number of informed bidders N, and a signal-dispersion estimate, and returns an adjusted valuation. Domain-neutral and reusable across fantasy FAAB, prediction markets, M&A bids, ad-auction budgets, and any generic bidding context. Use when user mentions "winner's curse", "common value auction", "valuation haircut", "adverse valuation", "Bayesian bid adjustment", or "over-paying in auction".