lyndonkl/skills/voice-fitness-check
skills/voice-fitness-check/SKILL.md
--- 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, organiza
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude skills/voice-fitness-checkInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 10:26 AM151.6s1 file scanned
SKILL.md
- 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
- Workflow
- Tier ratings
- Worked example
- 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:
- Biology → AI architecture and emergence (immune system, thymus, crypts, DNA/protein, ant colony) — Tier 1.
- Organizational / institutional → multi-agent systems (departments, courtroom, bucket brigade) — Tier 2.
- 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):
- Everyday: "A potluck dinner where each guest brings one dish" — Tier 4 (household).
- Physical metaphor: "Distributed load across power-grid nodes" — Tier 4 (physics; voice-adjacent violation).
- Contrarian: "Not a single super-agent; a parliament of specialized agents" — Tier 2 (organizational).
- Historical: "The Sumerian scribe running grain accounting — system intelligence exceeding any individual" — Tier 2 (borrowed, attributed).
- Counterfactual: "Remove inter-agent communication; you're back to single-agent with longer prompts" — neutral (structural, not an analogy in the usual sense).
Ranking:
- Contrarian (parliament) — Tier 2, strong fit with writer's voice signature for multi-agent.
- Historical (Sumerian scribe) — Tier 2, attributed borrow, strong.
- Counterfactual — neutral; always welcome.
- Everyday (potluck) — Tier 4, usable but not voice-native.
- 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
- Tier assignments are not opinions — they come directly from the voice-profile's analogy-direction table.
- Flag voice violations (physics/military) strongly. Do not merely rank low; call them out.
- Suggest a replacement for any violation, drawn from Tier 1-3.
- 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.
- Counterfactual framings are usually neutral — they're structural, not source-domain-based. Rate on mechanical clarity instead.
- 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.
Related Skills
lyndonkl/skills/zettel-note
development
VerifiedTrustedCommunity
--- name: zettel-note description: The note-writing discipline for this vault's evergreen knowledge graph, modeled on a Zettelkasten reading companion and governed by the vault conventions. Enforces declarative-claim titles, one claim per note (atomicity), own-words prose with no block quotes, the piped [[slug|Title]] link form, the labeled link-relationship vocabulary (Confirms/Contradicts/Extends/Context/Prerequisite/Builds-on/Applies/Example-of/Contrasts-with), 3-6 links per note, and search-
119SKILL.mdUpdated Jun 12, 2026
lyndonkl/wc-transfer-planner
development
VerifiedTrustedCommunity
Plans between-round FIFA World Cup Fantasy transfers — budgets the round's free transfer(s), forces out players whose nation has been eliminated, chases fixture-swing drops, upgrades on value, and decides when a rebuild is large enough to fire the Wildcard instead of spending free transfers one at a time. Ranks candidate in/out pairs by EV gain over each player's remaining survival horizon (delta xEV weighted by progression_carry) MINUS transfer cost (a free transfer is cheap, a points hit is real, churning the squad for marginal swings is a critic flag), and tags forced/fixture/upgrade priority. Emits a `transfer-plan` signal. Use when called by wc-squad-architect (whose transfer work this skill is the engine for) and by the strategists in the populate stage when their candidate is transfer-adjacent rather than a full rebuild.
119SKILL.mdUpdated Jun 12, 2026
lyndonkl/wc-tournament-state
testing
VerifiedTrustedCommunity
Reads and updates the FIFA World Cup Fantasy tournament state machine (footballfantasy/context/tournament-state.md) — the temporal backbone tracking phase (pre-tournament → group MD1-3 → R32 → R16 → QF → SF → final), budget ($100m group / $105m knockouts), nation cap (3 group, loosening in knockouts), chips remaining, surviving nations, each owned player's elimination-risk horizon, and deadlines. Validates state on load (count/feasibility checks), applies phase transitions, and appends to the append-only state log (never silent overwrite). Use to load state at the start of a run and to commit state changes after the manager makes a move.
119SKILL.mdUpdated Jun 12, 2026
lyndonkl/wc-signal-emitter
development
VerifiedTrustedCommunity
Validates and persists FIFA World Cup Fantasy signal files to signals/YYYY-MM-DD-<type>.md. Checks the required frontmatter (type, round, date, emitted_by, confidence, source_urls), range-checks declared numeric signals, confirms every factual claim carries a source URL or "manager-provided", rejects unknown signal types, and refuses to persist a signal that fails validation (logging the failure instead). Keeps the inter-agent signal layer auditable so downstream agents can trust what they read and never re-derive it. Use whenever an agent or skill writes a signal.
119SKILL.mdUpdated Jun 12, 2026