From thinking-frameworks-skills
Derives a draft per-section voice overlay (delta against global voice profile) once a section reaches ≥3 posts with shared voice tells. Writes overlay for writer review and commit.
How this skill is triggered — by the user, by Claude, or both
Slash command
/thinking-frameworks-skills:derive-section-voice-overlayThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
```
When a section reaches ≥3 posts:
- [ ] Step 1: Read all posts in corpus/published/{section}/
- [ ] Step 2: Read global shared-context/voice-profile.md
- [ ] Step 3: Extract patterns present in this section's posts but different from global:
- Tone shifts (confessional vs technical; register)
- Structural shifts (scoreboard required; code fences allowed; H2 permitted)
- Vocabulary shifts (term-of-art allowed; jargon defined on first use)
- Register permissions (epistolary, second-person, etc.)
- [ ] Step 4: Draft the overlay as a delta (bullet list per category; NOT a full voice profile)
- [ ] Step 5: Write shared-context/voices/{slug}.md for writer review
- [ ] Step 6: Emit draft status: "awaits writer commit" in the Curator review artifact
---
name: voice-overlay-{slug}
section: {slug}
type: voice-overlay
purpose: Voice deltas for {section name} against global voice-profile.
based_on: voice-profile.md (global)
maintained_by: curator (seed) + writer (refinements)
last_updated: YYYY-MM-DD
---
# {Section name} — Voice Overlay
Apply these on top of the global voice-profile. Where rules conflict, this overlay wins for posts in section `{slug}`.
## Tone shifts
- {delta bullet}
## Structural shifts
- {delta bullet}
## Vocabulary shifts
- {delta bullet}
## Register permissions
- {delta bullet}
## Carryovers (emphasized for this section)
- {global rule that matters even more here}
## Things this section does NOT do (anti-overlay)
- {negative rule — what the section explicitly does not do that the global voice might allow}
## Changelog
- YYYY-MM-DD — Initial overlay derived from N posts.
Section: Kalshi Log (6 posts).
Detected patterns vs global:
Overlay draft:
## Tone shifts
- Register leans confessional-operational, not speculative-essay.
- Closer points forward, not upward (universal maxim rare).
## Structural shifts
- Scoreboard block required at the close of every post.
- More numbers per paragraph than global voice allows.
- Short-form is default (≤1500 words).
## Register permissions
- Epistolary second-person register permitted (as in *The Letter*). Color, not default.
## Anti-overlay
- No generalizing to other sports / markets without explicit scope.
- No "lessons for life" closes.
npx claudepluginhub lyndonkl/claude --plugin thinking-frameworks-skillsExtracts a voice fingerprint from strong passages to audit and repair voice departures in multi-author documents or when brand voice has drifted.
Applies voice profiles like technical-authority, friendly-explainer, or executive-brief to transform content tone, vocabulary, structure, and perspective. Use for rewriting docs, tutorials, or comms in specific styles.
Measure and enforce a user's writing voice via stylometry (function-word vectors, lexical diversity, sentence-length burstiness, register, opener POS, punctuation rates). Accepts 5-20 writing samples, builds a local YAML fingerprint, and gates drafts against deterministic bands.