From thinking-frameworks-skills
Computes weekly and trailing-4-week Substack performance metrics per section from section-map.md and published posts. Reports opens, clicks, subs for sections with ≥3 posts; flags low z-score pruning candidates.
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 week (if ≥2 sections with ≥3 posts each):
- [ ] Step 1: Load section-map.md
- [ ] Step 2: Join CSV posts with corpus/published/{section}/ to map each post to section
- [ ] Step 3: Compute per-section aggregates (mean open rate, click rate, views/send, subs delta)
- [ ] Step 4: Compute trailing 4-week per-section z-score
- [ ] Step 5: Flag sections with median z ≤ -1.0 over 4 weeks → candidate for Curator prune proposal
- [ ] Step 6: Emit per-section table for the weekly report
## Per section
| Section | Posts (week / total) | Open rate (week / 4w baseline) | Click rate (week / 4w baseline) | Sub delta | 4w z |
|---|---|---|---|---|---|
| kalshi-log | 2 / 6 | 0.54 / 0.51 | 0.06 / 0.05 | +8 | +0.7 |
| agent-workshop | 0 / 7 | — | — | +2 | +0.2 |
Narrative: 1-2 sentences per section summarizing what the numbers say (not interpretation — that's attribute-performance's job).