Routes every video generation request through the proper CLI flags, reference handling, and prompt construction. You'll use this whenever someone wants to animate a still, continue a clip, render script notes, or compose anything from a product promo to a music video shot. It enforces the two hard rules (stage every call, audio on by default unless explicitly silenced) and knows the reference caps (9 image, 3 audio, 3 video with a 15s aggregate limit on video refs). The pattern matching is thorough: standalone text-to-video, image animation, storyboard rendering, clip continuation, and multi-shot sequences all get their own prompt scaffolds and edge rules. Handles external URL mirroring, audio timbre anchors for dialogue, and the bracket notation for single-shot polish.

GitHub stars
293
last updated
Jun 9, 2026

Install

$ npx -y skills add utopai-research/pai-pro --skill video-compose --agent claude-code

Installs into .claude/skills of the current project.

Files

Intent dispatcher. Patterns name trigger, call, edges, and prompt reference.

Hard defaults

  • Stage by default per PROJECT_AGENT.md.
  • Audio on by default; pass --no-audio only for explicit silent/no-audio requests. Trailer/portrait/cinematic framing is NOT a trigger; audio is the baseline, not optional polish.
  • Reference-to-clip default: use available character/variant/location/voice refs directly. Storyboard only if requested, hard to control, or needed for diagnosis.
  • Preserve scripted dialogue/VO exactly unless the user asks for rewrite.

First-use video mode

For the ask-once flow and per-mode prices, see the project PROJECT_AGENT.md § "First-use generation choices". Pass --resolution only for 480p Draft or 1080p Final.

CLI shape

node "$PAI_REPO_ROOT/server/cli/generate_video.js" --prompt "..." [--version <2.0|2.5>] [--duration <seconds>]
  [--aspect-ratio 16:9] [--resolution <480p|720p|1080p>] [--no-audio]
  [--label "..."] [--ref-source-id <id> ...] [--ref-audio-source-id <audio_id> ...]
  [--source-node-id <id>] [--shot-id <N>]

Calls go via --stage — see the project PROJECT_AGENT.md § "Draft gate".

Sponsors

Details

Repository
github.com/utopai-research/pai-pro
Categories
AI & Agent Building, Data Science & ML, Automation & Workflows, Marketing & SEO, Sales & Marketing, Mobile Development, CLI & Terminal
First seen
Jun 11, 2026

More from utopai-research/pai-pro

All 6
1wbern avatartddwbern/claude-instructionsRemind agent about TDD approach and continue conversation0skills.sh installs
2zhixiangluo avatarlinkedin-engagementzhixiangluo/10xproductivityAutomated LinkedIn engagement workflow. The agent finds a relevant post on your chosen topic, drafts a comment with a genuine insight, gets your approval in cha0skills.sh installs
3zhixiangluo avatartool-connectorzhixiangluo/10xproductivityConnect any tool you use at work to your agent — including internal company tools, custom-built systems, deployment portals, incident trackers, internal knowled0skills.sh installs
4sickn33 avatarllm-application-dev-langchain-agentsickn33/antigravity-awesome-skillsllm application dev langchain agent306skills.sh installs
5qodex-ai avatarrag-agent-builderqodex-ai/ai-agent-skillsBuild Retrieval-Augmented Generation (RAG) applications that combine LLM capabilities with external knowledge sources. Covers vector databases, embeddings, retr261skills.sh installs
6sickn33 avataragent-memory-mcpsickn33/antigravity-awesome-skillsagent memory mcp1.2Kskills.sh installs