Skip to content

tim-hub/powerball-harness / .claude/skills/generate-video

generate-video

Verified

Generates product demo videos and release walkthroughs via Remotion. Use when creating video documentation or animated demos.

Generate Video Skill

A collection of skills responsible for automatically generating product explanation videos.


Overview

This skill is used internally by the /generate-video command. It executes the flow of codebase analysis → scenario proposal → parallel generation.

Feature Details

FeatureDetails
Best PracticesSee references/best-practices.md
Codebase AnalysisSee references/analyzer.md
Scenario PlanningSee references/planner.md
Parallel Scene GenerationSee references/generator.md
Visual Effects LibrarySee references/visual-effects.md
AI Image GenerationSee references/image-generator.md
Image Quality AssessmentSee references/image-quality-check.md

Prerequisites

  • Remotion is set up (/remotion-setup)
  • Node.js 18+
  • (Optional) GOOGLE_AI_API_KEY - for AI image generation

/generate-video Flow

/generate-video
    │
    ├─[Step 1] Analysis (analyzer.md)
    │   ├─ Framework detection
    │   ├─ Key feature detection
    │   ├─ UI component detection
    │   └─ Project asset analysis (Plans.md, CHANGELOG, etc.)
    │
    ├─[Step 2] Scenario Proposal (planner.md)
    │   ├─ Auto-determine video type
    │   ├─ Scene composition proposal
    │   └─ User confirmation
    │
    ├─[Step 2.5] Asset Generation (image-generator.md) ← NEW
    │   ├─ Determine if assets are needed (intro, CTA, etc.)
    │   ├─ Generate 2 images with Nano Banana Pro
    │   ├─ Claude assesses quality (image-quality-check.md)
    │   └─ OK → adopt / NG → regenerate (up to 3 times)
    │
    └─[Step 3] Parallel Generation (generator.md)
        ├─ Parallel scene generation (Task tool)
        ├─ Integration + transitions
        └─ Final rendering

Execution Steps

  1. User runs /generate-video
  2. Verify Remotion setup
  3. Analyze codebase with analyzer.md
  4. Propose scenario with planner.md + user confirmation
  5. Parallel generation with generator.md
  6. Completion report

Video Types (by funnel stage)

TypeFunnel StageApprox. LengthAuto-detection CriteriaCore Structure
LP/Ad TeaserAwareness → Interest30-90sNew projectPain → Result → CTA
Intro DemoInterest → Consideration2-3 minUI changes detectedComplete 1 use case
Release NotesConsideration → Conviction1-3 minCHANGELOG updatedBefore/After focused
Architecture OverviewConviction → Decision5-30 minMajor structural changesProduction use + evidence
OnboardingRetention & Adoption30s - several minFirst-time setupShortest path to Aha moment

Details: references/best-practices.md

Scene Templates

90-second Teaser (for LP/ads)

TimeSceneContent
0-5sHookPain or desired outcome
5-15sProblem+PromiseTarget user and promise
15-55sWorkflowSignature workflow
55-70sDifferentiatorBasis for differentiation
70-90sCTANext step

3-minute Intro Demo (for consideration)

TimeSceneContent
0-10sHookConclusion + pain
10-30sUseCaseUse case declaration
30-140sDemoFull walkthrough on actual screens
140-170sObjectionAddress one common concern
170-180sCTACall to action

Common Scenes

SceneRecommended DurationContent
Intro3-5sLogo + tagline
Feature Demo10-30sPlaywright capture
Architecture Diagram10-20sMermaid → animation
CTA3-5sURL + contact

Detailed templates: ${CLAUDE_SKILL_DIR}/references/best-practices.md

Audio Sync Rules (Important)

Strictly follow these rules for narrated videos:

RuleValue
Audio startScene start + 30f (1-second wait)
Scene length30f + audio length + 20f padding
Transition15f (overlap with adjacent scenes)
Scene start calculationPrevious scene start + previous scene length - 15f

Pre-check: Verify audio length with ffprobe before designing scenes

Details: ${CLAUDE_SKILL_DIR}/references/generator.md

BGM Support

ItemRecommended Value
With narrationbgmVolume: 0.20 - 0.30
Without narrationbgmVolume: 0.50 - 0.80
File locationpublic/BGM/

Details: ${CLAUDE_SKILL_DIR}/references/generator.md

Subtitle Support

RuleValue
Subtitle startSame as audio start
Subtitle durationAudio length + 10f
FontBase64 embedding recommended

Details: ${CLAUDE_SKILL_DIR}/references/generator.md

Visual Effects Library

A collection of effects for impactful videos:

EffectUse Case
GlitchTextHook, titles
ParticlesBackground, CTA convergence
ScanLineAnalysis in-progress effect
ProgressBarParallel processing display
3D ParallaxCard display

Details: references/visual-effects.md

Notes

  • If Remotion is not set up, guide users to /remotion-setup
  • Number of parallel generations auto-adjusts based on scene count (max 5)
  • Generated videos are output to the out/ directory
  • AI-generated images are saved to out/assets/generated/
  • When GOOGLE_AI_API_KEY is not set, image generation is skipped (existing assets or placeholders are used)
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: 471kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexUnverifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall