openchatcut
Connect an MCP-capable coding agent to OpenChatCut and edit local video projects. Use when the user asks to install, connect, or…
Plan AI short films with story, shots, prompts, and continuity.
Claude Code
$ npx -y skills add 0xsline/OpenChatCut --skill ai-cinematic-short-film --agent claude-code
Codex
$ npx skills add 0xsline/OpenChatCut --skill ai-cinematic-short-film -a codex -y
Cursor
$ npx skills add 0xsline/OpenChatCut --skill ai-cinematic-short-film -a cursor -y
Gemini CLI
$ npx skills add 0xsline/OpenChatCut --skill ai-cinematic-short-film -a gemini-cli -y
GitHub Copilot
$ npx skills add 0xsline/OpenChatCut --skill ai-cinematic-short-film -a github-copilot -y
OpenCode
$ npx skills add 0xsline/OpenChatCut --skill ai-cinematic-short-film -a opencode -y
Windsurf
$ npx skills add 0xsline/OpenChatCut --skill ai-cinematic-short-film -a windsurf -y
name: ai-cinematic-short-film description: Plan AI short films with story, shots, prompts, and continuity.
Use this workflow when the user wants OpenChatCut to create a cinematic AI-generated short film or story-led visual sequence.
This is a OpenChatCut-native workflow. If a source workflow depends on external image/video generation or manual assembly, replace that step with OpenChatCut's equivalent capability when available. Do not add unrelated OpenChatCut features just because they exist.
1. Define the creative brief: premise, emotion, audience, platform, aspect ratio, duration, and ending. 2. Create a compact story structure: hook image, setup, escalation, reveal or payoff, final beat. 3. Build a style bible using [references/cinematic-ai-workflow.md](references/cinematic-ai-workflow.md): world, character, color, lens/camera language, motion, lighting, and continuity rules. 4. Draft a shot list. Each shot should have a purpose, duration, visual action, camera move, prompt notes, and continuity note. 5. Use existing or generated reference frames only when continuity would otherwise break, especially for characters, products, locations, or costumes. 6. Write prompts per shot with subject, action, environment, camera, lighting, mood, and negative constraints. Keep prompts specific but not brittle. 7. Generate clips, review continuity, and regenerate only shots that break story clarity or visual consistency. 8. Assemble the selected shots in the timeline. Add audio or text only when the brief or source workflow explicitly calls for it. 9. Final QA: story clarity, shot order, continuity, visual artifacts, and export readiness.
When planning, show a concise brief and shot list. When executing, report generated clips, timeline structure, and any shots that need user review.
Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.
Connect an MCP-capable coding agent to OpenChatCut and edit local video projects. Use when the user asks to install, connect, or…
Use when acquiring or importing media into a OpenChatCut project asset library for video editing or creation, including…
Turn one pool of existing project media into a batch of distinct, publishable montage cuts instead of a single hero edit. Use for…
Plan and build a finished beat-synced montage where cut placement serves the content, not just the metronome. Use for 卡点混剪, 卡点剪辑,…
Use whenever the agent needs to add, create, hand-author, patch, or place Motion Graphic JSX assets in a OpenChatCut project.…
Assemble product footage, UGC, and b-roll into a conversion-oriented montage with a hook → pain → demo → proof → CTA rhythm. Use…
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use…
AI-driven presentation workflow for generating editable PPTX decks and slides, reconstructing page visuals, creating reusable…
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style…
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to…