{"id":86471,"plugin_id":"plugin_asdk_app_6ad6811f854081919fb827ce3c29273f","kind":"skill","collection_source":"plugin_package","comparison_source":"plugin_package","observed_at":"2026-11-09T01:09:42.938Z","digest":"1a185bd2a9e970769ab8e7b26c9e3f6774c59d5ceabd811c3c4fa6bba466ae75","against":75041,"payload":{"description":"Edit videos with Vidova, an AI video editor with a real timeline. Cut clips, add captions, music, voiceover, motion graphics and effects, and render in the cloud. Use when someone wants a video made or edited from their footage, photos or an idea.","included_files":[],"name":"vidova","skill_md_contents":"---\nname: vidova\ndescription: \"Edit videos with Vidova, an AI video editor with a real timeline. Cut clips, add captions, music, voiceover, motion graphics and effects, and render in the cloud. Use when someone wants a video made or edited from their footage, photos or an idea.\"\nlicense: MIT\n---\n\n# Vidova\n\nVidova is an AI video editor. Its MCP server gives you the editor's tools: projects, uploads, the timeline, templates, effects, captions, music, previews and cloud renders. The person sees every change in the web editor at https://editor.vidova.ai.\n\n## Connect\n\nThis plugin brings the Vidova tools with it. The person signs in with a Vidova account when ChatGPT asks.\n\n## How to edit\n\n1. Start with `get_active_project`, or pick a project with `list_projects` and `open_project`, or make one with `create_project`.\n2. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.\n3. Read the footage with `read_asset`, `read_transcript` and `search_footage`. Watch an existing film with `preview_timeline` before you suggest or make edits.\n4. Call `search_templates`. When a template fits, `read_template` shows its slots and `apply_template` builds the film. Refine it with `patch_film`. When none fits, build the film with `patch_film`.\n5. Find graphics and captions with `search_elements`, effects with `search_effects`, and music, sound effects and device frames with `search_stock`.\n6. Before you render, call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.\n7. Render with `render_video` and wait for it with `wait_for_jobs`. Give the person the project `url` and the link to the finished video.\n\nPass the project's id as `projectId` on every project tool. Another session on the same account can open a different project between your calls.\n\nVidova works on the footage the person provides. Use their facts, names and numbers, and never invent them. Follow their brief: their order, song, length, format and rules come first. The skills in this plugin cover the common kinds of edit, such as `product-ad-video`, `podcast-clips` and `beat-sync-edit`.\n"},"changes":[{"path":"/skill_md_contents","type":"changed","before":"---\nname: vidova\ndescription: \"Edit videos with Vidova, an AI video editor with a real timeline. Cut clips, add captions, music, voiceover, motion graphics and effects, and render in the cloud. Use when someone wants a video made or edited from their footage, photos or an idea.\"\nlicense: MIT\nmetadata:\n  mcp-server: https://mcp.vidova.ai/mcp\n---\n\n# Vidova\n\nVidova is an AI video editor. Its MCP server gives you the editor's tools: projects, uploads, the timeline, templates, effects, captions, music, previews and cloud renders. The person sees every change in the web editor at https://editor.vidova.ai.\n\n## Connect\n\nIf the Vidova tools are not available, add the remote MCP server and sign in with a Vidova account when the client asks.\n\n- Server URL: `https://mcp.vidova.ai/mcp` (Streamable HTTP, OAuth sign-in)\n- Claude Code: `claude mcp add --transport http vidova https://mcp.vidova.ai/mcp`\n- Other clients: add a remote MCP server with the URL above.\n\n## How to edit\n\n1. Start with `get_active_project`, or pick a project with `list_projects` and `open_project`, or make one with `create_project`.\n2. Bring in footage with `upload_files`, `import_asset_url` or `begin_asset_upload`, then `wait_for_asset`.\n3. Watch the film with `preview_timeline` before you suggest or make edits.\n4. For a whole new edit of a known kind (a product ad, podcast clips, a music video, a travel recap and more), call `read_docs` with id `skills` and read the guide that matches.\n5. Call `search_templates` first. When a template fits, `read_template` shows its slots and `apply_template` builds the film. Refine it with `patch_film`.\n6. Before the first `patch_film` or `replace_component` that needs them, call `load_skill` with the skills the tool names.\n7. Before you render and before you say the edit is done, call `check_film` on the whole film and fix what it lists.\n8. Render with `render_video`. Give the person the project `url` so they can open it.\n\nPass the project's id as `projectId` on every project tool. Another session on the same account can open a different project between your calls.\n","after":"---\nname: vidova\ndescription: \"Edit videos with Vidova, an AI video editor with a real timeline. Cut clips, add captions, music, voiceover, motion graphics and effects, and render in the cloud. Use when someone wants a video made or edited from their footage, photos or an idea.\"\nlicense: MIT\n---\n\n# Vidova\n\nVidova is an AI video editor. Its MCP server gives you the editor's tools: projects, uploads, the timeline, templates, effects, captions, music, previews and cloud renders. The person sees every change in the web editor at https://editor.vidova.ai.\n\n## Connect\n\nThis plugin brings the Vidova tools with it. The person signs in with a Vidova account when ChatGPT asks.\n\n## How to edit\n\n1. Start with `get_active_project`, or pick a project with `list_projects` and `open_project`, or make one with `create_project`.\n2. If the person attached files in this chat, bring them in with `import_attached_files`. A file over 512 MB cannot be attached: call `create_upload_link` and give the person its link, where they add the file from their device. Use `import_asset_url` for a link to a file. Call `wait_for_asset` with every Asset ID until the files are ready. For a whole new edit from these files, call `start_routine` with routine `edit_prep` and the person's brief word for word before you read the footage. Call `wait_for_jobs` until it is done, follow its handoff, then go to the step that calls `check_edit`.\n3. Read the footage with `read_asset`, `read_transcript` and `search_footage`. Watch an existing film with `preview_timeline` before you suggest or make edits.\n4. Call `search_templates`. When a template fits, `read_template` shows its slots and `apply_template` builds the film. Refine it with `patch_film`. When none fits, build the film with `patch_film`.\n5. Find graphics and captions with `search_elements`, effects with `search_effects`, and music, sound effects and device frames with `search_stock`.\n6. Before you render, call `check_edit`, then `wait_for_jobs` with its Job ID, and fix what it names.\n7. Render with `render_video` and wait for it with `wait_for_jobs`. Give the person the project `url` and the link to the finished video.\n\nPass the project's id as `projectId` on every project tool. Another session on the same account can open a different project between your calls.\n\nVidova works on the footage the person provides. Use their facts, names and numbers, and never invent them. Follow their brief: their order, song, length, format and rules come first. The skills in this plugin cover the common kinds of edit, such as `product-ad-video`, `podcast-clips` and `beat-sync-edit`.\n"}],"summary":"Fields changed: 1. /skill_md_contents.","summary_kind":"deterministic","summary_metadata":{}}