tim-hub/powerball-harness / .claude/skills/generate-video
generate-video
VerifiedGenerates product demo videos and release walkthroughs via Remotion. Use when creating video documentation or animated demos.
references/analyzer.md
View on GitHub# Video Analyzer - Codebase Analysis Engine
Automatically analyzes projects and extracts information needed for video generation.
---
## Overview
This is the analysis engine executed in Step 1 of `/generate-video`.
It parses the codebase and project assets to determine the optimal video composition.
## Analysis Items
### 1. Framework Detection
| Detection Target | Detection Method |
|------------------|-----------------|
| Next.js | Presence of `next.config.*` |
| React | `package.json` dependencies |
| Vue | `vue.config.*` or `nuxt.config.*` |
| Svelte | `svelte.config.*` |
| Express/Fastify | `package.json` dependencies |
**Execution Commands**:
```bash
# Extract dependencies from package.json
cat package.json | jq '.dependencies, .devDependencies'
# Check for config file existence
ls -la *.config.* 2>/dev/null
```
### 2. Key Feature Detection
| Feature | Detection Pattern |
|---------|-------------------|
| Auth | `auth/`, `login/`, `@clerk`, `@auth0`, `supabase` |
| Payments | `payment/`, `billing/`, `stripe`, `@stripe` |
| Dashboard | `dashboard/`, `admin/`, `analytics` |
| API | `api/`, `routes/`, `trpc`, `graphql` |
| DB | `prisma/`, `drizzle/`, `@supabase` |
**Execution Commands**:
```bash
# Infer features from directory structure
find src app -type d -name "auth" -o -name "login" -o -name "dashboard" 2>/dev/null
# Infer features from packages
grep -E "clerk|stripe|supabase|prisma" package.json
```
### 3. UI Component Detection
| Item | Detection Method |
|------|-----------------|
| Page count | Count of `app/**/page.tsx` or `pages/**/*.tsx` |
| Component count | Count of `components/**/*.tsx` |
| UI library | Detection of `shadcn`, `radix`, `chakra`, `mui` |
**Execution Commands**:
```bash
# Count pages
find . -name "page.tsx" -o -name "page.jsx" 2>/dev/null | wc -l
# Count components
find . -path "*/components/*" -name "*.tsx" 2>/dev/null | wc -l
```
### 4. Project Asset Analysis
| Asset | Use |
|-------|-----|
| `package.json` | Project name, description |
| `README.md` | Project overview, tagline |
| `Plans.md` | Completed tasks (for release notes) |
| `CHANGELOG.md` | Changes (for release notes) |
**Execution Commands**:
```bash
# Extract project info
cat package.json | jq '{name, description, version}'
# Extract first paragraph of README
head -20 README.md
```
---
## Automatic Video Type Detection
### Detection Logic
```
Determine video type from analysis results:
|
+-- CHANGELOG recently updated (within 7 days)
| +-- → Release notes video
|
+-- Large structural changes (new directory additions, etc.)
| +-- → Architecture explanation
|
+-- Many UI changes (component additions/modifications)
| +-- → Product demo
|
+-- Matches multiple conditions
+-- → Composite video (confirm with user)
```
### Detection Criteria
| Type | Condition |
|------|-----------|
| **Release Notes** | `git log --since="7 days ago"` contains tags/releases |
| **Architecture** | New `src/*/` directories, major refactoring |
| **Product Demo** | UI component additions/modifications |
| **Default** | Product demo (most general-purpose) |
---
## Output Format
Analysis results output in the following format:
```yaml
project:
name: "MyAwesomeApp"
description: "Task management made easy"
version: "1.2.0"
framework:
primary: "Next.js"
ui_library: "shadcn/ui"
features:
- name: "Auth"
type: "auth"
path: "src/app/(auth)/"
provider: "Clerk"
- name: "Dashboard"
type: "dashboard"
path: "src/app/dashboard/"
- name: "API"
type: "api"
path: "src/app/api/"
stats:
pages: 12
components: 45
api_routes: 8
recent_changes:
changelog_updated: true
last_release: "2026-01-20"
major_changes:
- "Auth flow added"
- "Dashboard improvements"
recommended_video_type: "release-notes"
confidence: 0.85
```
---
## Execution Example
```
📊 Analyzing project...
✅ Analysis complete
| Item | Result |
|------|--------|
| Project name | MyAwesomeApp |
| Framework | Next.js 14 |
| UI library | shadcn/ui |
| Pages | 12 |
| Components | 45 |
🔍 Detected features:
- Auth (Clerk)
- Dashboard
- API (8 endpoints)
📋 Recent changes:
- v1.2.0 release (3 days ago)
- Auth flow added
- Dashboard improvements
🎬 Recommended video type: Release notes video
Reason: Recent release with major feature additions
```
---
## Notes
- Analysis is non-destructive (does not modify files)
- Completes in seconds even for large projects
- Undetected features can be added manually (in planner.md)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |