From thinking-frameworks-skills
Scans Substacker post corpus for theme clusters suitable as products (course, book, cohort, consulting). Outputs ≤2 candidates with evidence, audience signals, or 'not yet' verdict after 30+ posts.
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.
Per quarterly run (with corpus ≥30 posts):
- [ ] Step 1: Cluster published corpus by theme (NOT by section — themes may cut across)
- [ ] Step 2: For each cluster with ≥5 posts, check product templates:
- Course: 5+ posts forming a progression
- Book: 15+ posts on one theme with coherent through-line
- Cohort: reader-demand signal in audience-notes
- Consulting: "can you help me do this" signal
- [ ] Step 3: For each qualifying cluster, write candidate block
- [ ] Step 4: If no cluster qualifies, say so plainly
**Theme**: {name}
**Product type**: course | book | cohort | consulting
**Supporting posts**: {slug list}
**Minimum-viable product**: {1-2 sentences}
**Audience signal**: {what in the corpus or audience-notes suggests demand}
**Not yet if**: {the condition that would flip this from candidate to real}