From thinking-frameworks-skills
Web-fetches full posts or arXiv abstracts from Trend Scout candidates, generates one-line 'teaches X' summaries, classifies signal types (mechanism/empirical/tool/opinion/announcement/benchmark), and evaluates intuition density for weekly pre-ranking.
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 candidate item:
- [ ] Step 1: WebFetch the URL; ask: "Extract the core argument in 300 words. What mechanism does this teach? Is there a diagram/analogy? Is this a capability announcement?"
- [ ] Step 2: Classify signal_type: mechanism | empirical | tool | opinion | announcement | benchmark
- [ ] Step 3: Classify intuition_density: high (diagram + analogy + worked example) | medium | low (prose-only announcement)
- [ ] Step 4: Compose one-line summary framed as "teaches that X" or "shows that Y"
- [ ] Step 5: Voice-check the summary against voice-profile don'ts
Appends to candidate record:
{
"summary": "Teaches that X",
"signal_type": "mechanism",
"intuition_density": "high",
"teaches_mechanism": true,
"full_text_excerpt_300w": "..."
}
summary: "FETCH_FAILED" and let ranker drop.teaches_mechanism: false — downstream ranker drops it.