lyndonkl/skills/derive-section-voice-overlay
skills/derive-section-voice-overlay/SKILL.md
--- name: derive-section-voice-overlay description: Derives a draft per-section voice overlay (deltas against substacker global voice-profile) once a section reaches ≥3 published posts with shared voice tells. Writes to shared-context/voices/{slug}.md. Writer reviews and commits. Overlay expresses only the DELTA from global voice — not a full rewrite. Use when a section crosses the 3-post threshold. Trigger keywords: voice overlay, section voice, overlay delta, per-section voice. --- # Derive S
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude skills/derive-section-voice-overlayInstall 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, 10:11 AM142.4s1 file scanned
SKILL.md
- name:
- derive-section-voice-overlay
- description:
- Derives a draft per-section voice overlay (deltas against substacker global voice-profile) once a section reaches ≥3 published posts with shared voice tells. Writes to shared-context/voices/{slug}.md. Writer reviews and commits. Overlay expresses only the DELTA from global voice — not a full rewrite. Use when a section crosses the 3-post threshold. Trigger keywords: voice overlay, section voice, overlay delta, per-section voice.
Derive Section Voice Overlay
Workflow
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
Overlay schema
---
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.
Worked example
Section: Kalshi Log (6 posts).
Detected patterns vs global:
- Every post has scoreboard at close (absent from global voice).
- Register leans confessional-operational; the "what actually happened" body, not speculative essay.
- Epistolary second-person register appears in 1 of 6 posts — color, not default.
- No post ends on a universal maxim; all close with forward-looking "next match" or "let's find out."
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.
Guardrails
- Overlay is a delta, not a full voice rewrite. Keep short.
- Requires ≥3 published posts in the section. Below that, section uses global voice.
- Writer reviews and commits. Don't write final overlay without writer confirmation in the Curator review artifact.
- Flag candidate overlay rules that contradict global — those need the writer's explicit promotion.
- Voice overlays are refined over time — first draft is a starting point, not a finished system.
Related Skills
lyndonkl/conf-theme-clustering
testing
VerifiedTrustedCommunity
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-schedule-optimization
development
VerifiedTrustedCommunity
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-program-extraction
development
VerifiedTrustedCommunity
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-preference-elicitation
development
VerifiedTrustedCommunity
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.
127SKILL.mdUpdated Jun 28, 2026