From thinking-frameworks-skills
Audits voice fidelity across Substack Note, X thread, LinkedIn post, and cross-post blurb outputs, checking banned terms, compliance rules, and platform tones. Emits pass/fail voice-check.md.
npx claudepluginhub lyndonkl/claude --plugin thinking-frameworks-skillsThis skill uses the workspace's default tool permissions.
```
Generates design tokens/docs from CSS/Tailwind/styled-components codebases, audits visual consistency across 10 dimensions, detects AI slop in UI.
Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.
Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.
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 | 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") |
| Practitioner, slightly less confessional | Raw confession ("Substack leak on LinkedIn") | |
| Cross-post | Third person | Any first-person use ("I argue…") |
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
- ...
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.