lyndonkl/skills/platform-voice-check
skills/platform-voice-check/SKILL.md
--- name: platform-voice-check description: Runs a voice-fidelity audit on each of the four substacker platform outputs (Substack Note, X thread, LinkedIn post, cross-post blurb) before reporting Distribution Translator completion. Checks for voice-don'ts (banned vocabulary, emoji, generic openers, marketing math without source), voice-do compliance (paper attribution preserved, hedges preserved, em-dash reframes present), platform-specific tonal shifts. Emits voice-check.md with pass/fail per a
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude skills/platform-voice-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, 10:18 AM169.8s1 file scanned
SKILL.md
- name:
- platform-voice-check
- description:
- Runs a voice-fidelity audit on each of the four substacker platform outputs (Substack Note, X thread, LinkedIn post, cross-post blurb) before reporting Distribution Translator completion. Checks for voice-don'ts (banned vocabulary, emoji, generic openers, marketing math without source), voice-do compliance (paper attribution preserved, hedges preserved, em-dash reframes present), platform-specific tonal shifts. Emits voice-check.md with pass/fail per artifact. Trigger keywords: platform voice check, voice-check, gate, distribution voice, slop-leak check.
Platform Voice Check
Workflow
Voice-audit the 4 platform outputs:
- [ ] Step 1: Read all 4 output files + voice-profile.md + voices/{section}.md (if applicable)
- [ ] Step 2: For each file:
- Scan voice-don'ts (delve, unpack, paradigm shift, emoji, exclamations, I think, AI-is-transforming, custom CTA)
- Scan voice-dos (opener classification, em-dash reframes, hedge preservation, paper attribution)
- Platform-specific tonal shift check
- [ ] Step 3: Emit voice-check.md with pass/fail per file
- [ ] Step 4: If FAIL on any file, return the flag list to Distribution Translator for loop-back
Platform-specific tonal checks
| Platform | Expected tone shift | Flag if | |---|---|---| | Substack Note | Closest to essay voice | Any over-polishing that reads AI-rewritten | | X | More declarative, more quotable | Over-hedging ("Substack leak on X") | | LinkedIn | Practitioner, slightly less confessional | Raw confession ("Substack leak on LinkedIn") | | Cross-post | Third person | Any first-person use ("I argue…") |
Output format
ops/distribution/{date}-{slug}/voice-check.md:
---
agent: distribution-translator
date: YYYY-MM-DD
post_slug: {slug}
results:
substack-note.md: PASS | FAIL
x-thread.md: PASS | FAIL
linkedin-post.md: PASS | FAIL
cross-post-blurb.md: PASS | FAIL
---
## substack-note.md: PASS | FAIL
- (line / location) — issue — voice-profile citation
## x-thread.md: PASS | FAIL
- variant: short — line X — issue
- variant: medium — line Y — issue
## linkedin-post.md: PASS | FAIL
- ...
## cross-post-blurb.md: PASS | FAIL
- ...
Loop-back
If voice-check reports FAIL on any file, Distribution Translator MUST loop back to the matching rewrite skill with the flags as input. Max 2 loops per artifact. After 2 loops:
DESIGN-NOTE: This essay's voice may not translate cleanly to {platform}. User review recommended.
Ship best-so-far; flag for writer.
Guardrails
- Every flag must cite a voice-profile line. No flag without citation.
- Advisory on first pass; blocking after 2 loops (then ship best-so-far with a design-note).
- Do not write to the platform files directly. Emit the flag list; the rewrite skill re-runs.
- Check banned-vocabulary regex first (fast); tonal-shift checks second (slower).
- Paper attribution rule: if a paper is cited in the essay, check every platform file mentions Author, Institution, Year on first mention.
- Emoji check: zero tolerance across all four files.
Quick reference
- Runs as the final gate in the Distribution Translator pipeline.
- Advisory → loop-back → ship-best-after-2-loops.
- Output: one voice-check.md in the post's distribution folder.
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