check-analogy-novelty
$
npx mdskill add lyndonkl/claude/check-analogy-noveltyScans analogies against a catalog to prevent repetitive reuse.
- Blocks writers from repeating common metaphors like library cards.
- Depends on shared-context/analogy-catalog.md for reference data.
- Classifies matches as new, reused, or adjacent to existing entries.
- Outputs flagged analogies with citations to the specific catalog post.
SKILL.md
.github/skills/check-analogy-noveltyView on GitHub ↗
---
name: check-analogy-novelty
description: Cross-references each proposed analogy in a 5-framing set against substacker shared-context/analogy-catalog.md to flag reuse. Classifies each analogy as new, reused-from-catalog (and which entry), or adjacent-to-catalog (close to an existing entry but not identical). Prevents the writer from recycling "imagine a library" for the twentieth time. Use after generate-analogy-set and before presenting framings to the writer. Trigger keywords: novelty, catalog, analogy reuse, already used, imagine a library.
---
# Check Analogy Novelty
## Table of Contents
- [Workflow](#workflow)
- [Match tiers](#match-tiers)
- [Worked example](#worked-example)
- [Guardrails](#guardrails)
**Related skills:** Called by the Intuition Builder after `generate-analogy-set` and before presenting framings. Reads `shared-context/analogy-catalog.md`. Does NOT write to the catalog — that's `update-analogy-catalog`'s job, fired on publish.
## Workflow
```
For each of the 5 framings:
- [ ] Step 1: Extract the analogy's source domain (e.g., "library card catalog")
- [ ] Step 2: Extract the analogy's target concept (e.g., "KV cache")
- [ ] Step 3: Grep analogy-catalog.md for exact or near-exact source × target match
- [ ] Step 4: Classify: new | reused-from-catalog | adjacent-to-catalog
- [ ] Step 5: For reused/adjacent, cite the catalog entry with its post
```
## Match tiers
- **New**: neither the source nor a close variant of it appears in the catalog for this target concept.
- **Reused-from-catalog**: exact source × target match — writer already used this analogy in a published post. Flag strongly; either justify reuse or swap.
- **Adjacent-to-catalog**: source matches a nearby analogy in the catalog (e.g., "drawer" vs. "card catalog") or target is in the catalog but source differs. Flag softly — writer should see the adjacency.
"Close variant" = same source domain (library, immune system, bucket brigade) even if different specific instance.
## Worked example
**Proposed framings for KV cache**:
1. Everyday: "a library's card catalog with a fixed drawer count"
2. Physical metaphor: "a ring buffer with index"
3. Contrarian: "the cache is not the table — it's the index into what's been already paid for"
4. Historical: "before caches, every lookup was recomputation"
5. Counterfactual: "remove the cache and decode becomes quadratic"
**Catalog check**:
- Entry in catalog: *"Agents as departments reading each other's memos but never sitting in on each other's meetings"* — source: institutional. Target: multi-agent. Not related to KV cache.
- Entry: *"Bucket brigade"* — source: bucket brigade. Target: sequential multi-agent. Not related.
- No entry for `library` → KV cache, or `ring buffer`, or `index`.
**Output**:
1. Everyday: new
2. Physical metaphor: new
3. Contrarian: new
4. Historical: new
5. Counterfactual: new
**But**: if the catalog had an entry *"Library index → tokenizer vocabulary"*, framing 1's adjacency would trigger: "adjacent-to-catalog — library appears once for a different target". Flag softly.
## Guardrails
1. Read-only. Never writes to the catalog.
2. Match on both source domain and target concept. Same source for different target is an adjacency, not a reuse.
3. Flag adjacencies, don't auto-reject — the writer decides if reuse is intentional (a recurring analogy can be a feature).
4. Cite the catalog entry + post when flagging. "Reused from catalog" without pointing to the entry is useless.
5. Don't expand near-matches to other analogy directions (biology vs. organizational are different domains, never flag across).
6. If the catalog is empty (early-stage publication), all framings are `new` by definition. Note this once in the output.
## Quick reference
- Input: list of 5 framings + analogy-catalog.md.
- Output: per-framing classification `{new | reused-from-catalog | adjacent-to-catalog}` with citation.
- Side effect: none. Read-only.
More from lyndonkl/claude
- 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".