Tutopanda Documentary Producer
Apps & Automationtutopanda-documentary-producerTutopanda Documentary Producer is an Agent Skill for apps & automation published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Coordinate Tutopanda CLI and MCP to generate, edit, inspect, and preview documentary videos (video-audio-music blueprint with FinalVideo export). Use when users ask for Tutopanda to build, edit, or review movies inside Claude Code.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/data/documentary-producer/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/tutopanda-documentary-producer, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Tutopanda Documentary Producer
Use this skill whenever a user wants Tutopanda to create or modify documentary-style videos, export an MP4, or preview results from within Claude Code.
Preconditions
tutopandabinary is available on PATH. If not, stop and ask the user to install the published CLI manually.- Tutopanda has been initialized (
tutopanda init --rootFolder=<absolute-path>). Confirm the config path orTUTOPANDA_CLI_CONFIGbefore running any command. - Default blueprint is
video-audio-music.yamlbecause it emitsFinalVideo(MP4) in addition to the timeline. Switch blueprints only if the user requests a different workflow.
Generation workflow
- Collect required inputs from the user:
InquiryPrompt,Duration,NumOfSegments,SegmentDuration,VideoStyle,AspectRatio,Resolution,VoiceId, plus optionalAudience,Language,Emotion,MusicalStyle. Do not fabricate values. - Write an inputs YAML with those values at an absolute path the user approves.
- Run Tutopanda via MCP (preferred) or CLI:
- CLI example:
tutopanda query "<InquiryPrompt>" \ --inputs=/absolute/path/to/inputs.yaml \ --usingBlueprint=video-audio-music.yaml \ --concurrency=<workers-if-needed> \ --nonInteractive
- CLI example:
- Capture the
movieId, plan path, and friendly view path from the output. - If the user wants a preview, call
tutopanda viewer:view --movieId=<movieId>.
Editing workflow
- Require the existing
movieIdand an explicit inputs file path. Run:tutopanda edit \ --movieId=<movie-id> \ --inputs=/absolute/path/to/inputs.yaml \ --usingBlueprint=video-audio-music.yaml \ --concurrency=<workers-if-needed> \ --nonInteractive - Use
--dryRunor--upToLayeronly when the user asks for them. After the run, refresh the viewer.
Inspection and review
- For prompts/timelines, run
tutopanda inspect --movieId=<movie-id> --prompts --alland summarize key findings. - Keep outputs and artefact paths tied to the configured root; do not relocate them.
Failure handling
- If the CLI or config is missing, stop and ask the user to install or initialize Tutopanda rather than guessing paths or creating defaults.
- Avoid silently falling back to placeholder inputs—always confirm required fields before running.