openchatcut
Connect an MCP-capable coding agent to OpenChatCut and edit local video projects. Use when the user asks to install, connect, or…
Assemble product footage, UGC, and b-roll into a conversion-oriented montage with a hook → pain → demo → proof → CTA rhythm. Use for 带货混剪, 产品混剪, 商品短视频, 种草视频, ecommerce montage, product reel, UGC cutdown, or when the user wants selling footage cut into a short that converts.
Claude Code
$ npx -y skills add 0xsline/OpenChatCut --skill ecommerce-product-montage --agent claude-code
Codex
$ npx skills add 0xsline/OpenChatCut --skill ecommerce-product-montage -a codex -y
Cursor
$ npx skills add 0xsline/OpenChatCut --skill ecommerce-product-montage -a cursor -y
Gemini CLI
$ npx skills add 0xsline/OpenChatCut --skill ecommerce-product-montage -a gemini-cli -y
GitHub Copilot
$ npx skills add 0xsline/OpenChatCut --skill ecommerce-product-montage -a github-copilot -y
OpenCode
$ npx skills add 0xsline/OpenChatCut --skill ecommerce-product-montage -a opencode -y
Windsurf
$ npx skills add 0xsline/OpenChatCut --skill ecommerce-product-montage -a windsurf -y
name: ecommerce-product-montage description: | Assemble product footage, UGC, and b-roll into a conversion-oriented montage with a hook → pain → demo → proof → CTA rhythm. Use for 带货混剪, 产品混剪, 商品短视频, 种草视频, ecommerce montage, product reel, UGC cutdown, or when the user wants selling footage cut into a short that converts.
Use this workflow when the goal is a short that *sells*, not just one that looks good. The failure mode to avoid is a pretty montage with no sales spine: strong footage, pleasant cuts, and zero reason for the viewer to act.
This workflow decides **structure and sequencing** for selling footage. It does not write the ad copy — when the hook, angles, or CTA text are not given, hand off to `product-ad-video-script` for the script, then come back here to assemble. It does not re-explain music tooling — for beat-driven placement use `beat-sync-montage` or `music-intelligence`.
This is a OpenChatCut-native workflow. Use the current project, source assets, asset-frame inspection, AV/script context, and OpenChatCut editing tools.
1. Fix the one job the edit must do: which objection it dissolves or which action it drives (save, tap, buy, follow). If the brief names none, propose one and confirm. 2. Inventory the material by sales role, not by file: hero demo, UGC reaction, proof (review/result), context b-roll, price/offer card. See [references/material-roles.md](references/material-roles.md). Footage that fills no role is parked, not force-inserted. 3. Lay the sales spine before cutting: hook (0–3s, the open loop) → pain/context → demo → proof → CTA. See [references/sales-spine.md](references/sales-spine.md). Every beat maps to a spine position; a clip with no spine position is cut. 4. Lead with the hook from a real moment, not a title card. The first three seconds either open a loop ("you are doing X wrong") or show the payoff; a logo sting as opener loses the scroll. 5. Place the demo where the viewer is curious, not where the script says "demo." Demo proves the hook; if the hook is a result, demo the path to it. 6. Insert proof as a pattern interrupt, not a block. One real review line or result frame beats a stacked proof montage. See [references/proof-placement.md](references/proof-placement.md). 7. Hold the CTA long enough to read. Price, offer, and the exact action each get a legible beat; a CTA flashed for one cut is a CTA nobody acts on. 8. Keep claims grounded. Do not manufacture prices, guarantees, medical, or earnings claims the assets do not support. Pull offer text from the product page or user notes; if absent, ask. 9. QA by the spine, not by the cut list: can a cold viewer state the offer and the action after watching once? If not, the edit sells nothing. 10. Report the spine coverage and any role with no usable footage, so a thin section is flagged before shipping.
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…
Plan AI short films with story, shots, prompts, and continuity.
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.…
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…