pneuma-clipcraft
pneuma-clipcraft is a video-production environment where a structured domain model—not files—drives your workflow. Generate video, audio, and captions through bundled scripts, then register assets and lineage in a timeline-based composition system. The viewer displays your project as an exploded 3D timeline, syncing edits instantly without reload.
pneuma-clipcraft orchestrates AI-driven video production, letting you generate, edit, and compose clips with structured asset and provenance tracking.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-27
pneuma-clipcraft orchestrates AI-driven video production, letting you generate, edit, and compose clips with structured asset and provenance tracking. pneuma-clipcraft is a video-production environment where a structured domain model—not files—drives your workflow. Generate video, audio, and captions through bundled scripts, then register assets and lineage in a timeline-based composition system. The viewer displays your project as an exploded 3D timeline, syncing edits instantly without reload.
Use it when
- Yes.
- pneuma-clipcraft manages video assets and tracks lineage via a provenance graph that records the origin and relationships of every clip.
Verify before relying
Read SKILL.md below before installing (16 files). Open directory: indexed for reading, not audited.
Install
pandazki/pneuma-skills/skill · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I generate a video clip with pneuma-clipcraft?
pneuma-clipcraft lets you generate video clips through bundled AI scripts that orchestrate the production process. You define your shot parameters in the structured domain model, invoke the generation scripts, and the system creates your video asset. Once generated, register it in the timeline-based composition system to see it rendered in the 3D viewer instantly.
Can I add narration to video and generate background music?
Yes. pneuma-clipcraft supports creating narration, background music, and captions for your video through dedicated production scripts. Generate TTS narration, compose music, or add captions—all assets are tracked and registered in the system's provenance graph so you maintain full lineage of every element in your project.
What does pneuma-clipcraft's provenance graph track?
pneuma-clipcraft manages video assets and tracks lineage via a provenance graph that records the origin and relationships of every clip, audio track, caption, and variant. This structured tracking lets you understand how each asset was created, edited, and composed, enabling confident iteration and re-takes without losing production history.
How do I edit a video timeline in pneuma-clipcraft?
pneuma-clipcraft uses a structured domain model instead of files to drive your workflow. Place clips on the timeline by editing the project composition, and the 3D viewer displays your multi-track timeline instantly. Edits sync without reload, letting you iterate on shot placement and timing in real time.
Can pneuma-clipcraft generate another take of a video?
Yes. pneuma-clipcraft supports iterating on video shots with variant generation and re-takes. Modify your shot parameters in the domain model and invoke generation again—the system creates a new take and registers it in the provenance graph, letting you compare and select the best version for your timeline.
What license does pneuma-clipcraft use?
pneuma-clipcraft is released under the MIT license, making it free to use, modify, and distribute for both personal and commercial projects.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
ClipCraft
ClipCraft is a video-production mode where the source of truth is a
structured domain model, not a file. The in-memory model is an
event-sourced craft store from @pneuma-craft: an Asset registry, a
Composition with Tracks and Clips, and a Provenance DAG that tracks
how each asset was generated (and from what). The file project.json
at the
(truncated - see the full file via the links below)
File tree — 15 files
modes/clipcraft/skill/SKILL.md
modes/clipcraft/skill/references/asset-ids.md
modes/clipcraft/skill/references/character-consistency.md
modes/clipcraft/skill/references/craft.md
modes/clipcraft/skill/references/direction-notation.md
modes/clipcraft/skill/references/filter-retries.md
modes/clipcraft/skill/references/production-bible.md
modes/clipcraft/skill/references/project-json.md
modes/clipcraft/skill/references/reference-directives.md
modes/clipcraft/skill/references/storyboard-design.md
modes/clipcraft/skill/references/storyboard-workflow.md
modes/clipcraft/skill/references/workflows.md
modes/clipcraft/skill/scripts/generate-bgm.mjs
modes/clipcraft/skill/scripts/generate-tts.mjs
modes/clipcraft/skill/scripts/generate-video.mjs
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Generate, edit, or compose video clips with AI orchestration”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Create short video clips by describing a scene or uploading an image. VideoAgent Video Studio automatically selects the right generation mode, enhances your input, and delivers the video URL—supporting seven AI video backends including Kling, Veo, and Seedance.
Seedance Video Gen converts text descriptions into MP4 videos powered by the Seedance 2.0 model, with command-line control over resolution, aspect ratio, and length. It supports both text-to-video and preset virtual avatar modes, eliminating the need for API configuration or platform account setup.
seedance-camera translates creative intent into filmmaking grammar, routing camera requests to specific moves—dolly, orbit, crane, handheld, locked—with physical endpoints and subject relationships. It anchors shots to emotional purpose rather than decoration, ensuring each frame serves the scene's intention.
Route text and image prompts to the right AI video model via RunComfy's CLI. The skill handles model selection across HappyHorse, Kling, Seedance, Veo, Wan, and others—each optimized for different outputs like in-pass audio, multi-shot character consistency, or physics-accurate motion. Get the exact `runcomfy run` command and prompt patterns for your use case.
Seedance 2.0 is ByteDance's unified video-and-audio model, available as OpenMontage's premium default for trailers, teasers, and motion-heavy work. It handles single-pass synchronized audio, multiple shots in one generation, director-level camera language, lip-sync from dialogue, and character identity consistency across cuts. Access it via fal.ai, Replicate, Runway, Higgsfield, or other aggregators by routing through `video_selector` with `preferred_provider="seedance"`.
HyperFrames treats HTML as the source for video production, letting you author compositions with GSAP timelines for animation, data attributes for timing, and CSS for styling. Build title cards, overlays, captions, text-to-speech narration, beat-synced visuals, and scene transitions—then render to video. The framework handles clip visibility, media playback, and timeline synchronization across your composition.
More skills hyperframes (MIT)