voice-fitness-check
$
npx mdskill add lyndonkl/claude/voice-fitness-checkRank framings by voice fit to order outputs.
- Filters framings against biology, organizational, and sports priorities.
- Depends on voice-profile.md and section-specific voice files.
- Scores each framing using tier ratings from the profile.
- Flags violations like physics or military analogies.
SKILL.md
.github/skills/voice-fitness-checkView on GitHub ↗
---
name: voice-fitness-check
description: Ranks a proposed set of framings against the writer's voice profile, especially the analogy-direction priority — biology > organizational > sports, with physics/military as voice violations. Produces a tier rating per framing and flags any framing that would break voice. Use in the Intuition Builder pipeline after generating framings, to order them by fit with the writer's register. Trigger keywords: voice fit, analogy direction, biology to AI, organizational to multi-agent, sports to calibration.
---
# Voice Fitness Check
## Table of Contents
- [Analogy direction priority](#analogy-direction-priority)
- [Workflow](#workflow)
- [Tier ratings](#tier-ratings)
- [Worked example](#worked-example)
- [Guardrails](#guardrails)
**Related skills:** Called by the Intuition Builder in the pipeline (step 5). Reads `shared-context/voice-profile.md` and `shared-context/voices/{section}.md` if a target section is specified.
## Analogy direction priority
From `voice-profile.md` section 9:
1. **Biology → AI architecture and emergence** (immune system, thymus, crypts, DNA/protein, ant colony) — Tier 1.
2. **Organizational / institutional → multi-agent systems** (departments, courtroom, bucket brigade) — Tier 2.
3. **Sports → calibration / prediction / betting** (cricket phases, soccer-as-practice, scoreboard) — Tier 3.
Everything else is Tier 4 (acceptable but not a voice signature).
**Physics, military, warfare, weapons, combat** — these are voice violations. Flag strongly. Propose a replacement in Tier 1–3 direction if one is available.
## Workflow
```
For each of the 5 framings:
- [ ] Step 1: Classify the source domain
- [ ] Step 2: Assign a tier (1-4) based on the priority table
- [ ] Step 3: Flag any Tier 4 or voice-violating framings
- [ ] Step 4: Rank the 5 framings overall (tier + craft quality)
- [ ] Step 5: Recommend first choice
```
### Step 1: Domain classification
Look at the source. Is it:
- A living system, cellular process, evolution, immunology? → biology (Tier 1)
- A human organization, hierarchy, committee, courtroom, workflow? → organizational (Tier 2)
- A sport, game, match, contest, calibration of a prediction? → sports (Tier 3)
- A machine, mechanical system, fluid, physical law, vehicle? → physics (Tier 4)
- A battle, weapon, combat, tactic, strategy (in the military sense)? → voice violation
"Neural network" itself counts as biology — but only if the framing actually uses biological relations (neurons firing, learning as development), not just the name.
## Tier ratings
- **Tier 1** (biology): preferred, voice signature. Use often.
- **Tier 2** (organizational): preferred, voice signature. Use when biology doesn't fit.
- **Tier 3** (sports): acceptable for calibration/prediction content specifically. Out of register for pure ML architecture.
- **Tier 4** (other): usable if no Tier 1-3 candidate fits, but not a voice signature.
- **Violation** (physics/military): flag. Do not include without explicit writer override.
## Worked example
**Topic**: Multi-agent AI system.
**5 framings** (from generate-analogy-set):
1. Everyday: "A potluck dinner where each guest brings one dish" — Tier 4 (household).
2. Physical metaphor: "Distributed load across power-grid nodes" — Tier 4 (physics; voice-adjacent violation).
3. Contrarian: "Not a single super-agent; a parliament of specialized agents" — Tier 2 (organizational).
4. Historical: "The Sumerian scribe running grain accounting — system intelligence exceeding any individual" — Tier 2 (borrowed, attributed).
5. Counterfactual: "Remove inter-agent communication; you're back to single-agent with longer prompts" — neutral (structural, not an analogy in the usual sense).
**Ranking**:
1. Contrarian (parliament) — Tier 2, strong fit with writer's voice signature for multi-agent.
2. Historical (Sumerian scribe) — Tier 2, attributed borrow, strong.
3. Counterfactual — neutral; always welcome.
4. Everyday (potluck) — Tier 4, usable but not voice-native.
5. Physical (power grid) — Tier 4 with voice-adjacent risk. **Suggest replacement**: "An immune system's parallel T-cell response" (Tier 1, biology).
**Recommendation**: First choice is the **parliament** contrarian. Swap framing 5 for the biological alternative.
## Guardrails
1. Tier assignments are not opinions — they come directly from the voice-profile's analogy-direction table.
2. Flag voice violations (physics/military) strongly. Do not merely rank low; call them out.
3. Suggest a replacement for any violation, drawn from Tier 1-3.
4. Ranking combines tier + craft quality. A Tier-2 framing with a weak mapping ranks below a Tier-3 with strong mapping. Use judgement for ties.
5. Counterfactual framings are usually neutral — they're structural, not source-domain-based. Rate on mechanical clarity instead.
6. If the target section has its own voice overlay (`voices/{section}.md`) with different priorities, apply those on top of global.
## Quick reference
- Input: 5 framings + voice-profile.md.
- Output: per-framing tier + overall ranking + flagged violations + replacement suggestions.
- Final step before the Intuition Builder presents to the writer.
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".