[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ACYP9M176F25CH7R844HJZ":3,"skill-same:01M7ACYP9M176F25CH7R844HJZ":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7ACYP9M176F25CH7R844HJZ","video-editing",null,"Video Mode editing guidance for agentic storyboard, timeline, caption, audio, render, and publish work through video_* MCP tools.","bravew\u002FNeumar","bravew","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10855844?v=4","01M7ACJ91JZSQYHT81XPVYR7VA","Yong","01M7ACJ92CH2PCT42AG4GYHFV7",12,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-editing\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: video-editing\ndescription: Video Mode editing guidance for agentic storyboard, timeline, caption, audio, render, and publish work through video_* MCP tools.\n---\n\n# Video Editing\n\nUse this skill whenever you are editing a Video Mode project through the\n`mcp__video-edit__*`, `mcp__media__*`, or `mcp__ffmpeg-processing__*` tools.\n\n## Operating Rules\n\n1. Read current project state before editing. Start with\n   `video_get_project_summary`; use `video_get_scene`,\n   `video_get_timeline`, and `video_list_assets` for narrower context.\n2. Use Video Mode tools for every project mutation. Do not use shell or file\n   editing tools to change `project.json`, assets, timeline JSON, or renders.\n3. Read and reversible write operations can proceed directly. Anything that\n   removes content, changes timing substantially, spends money, renders, or\n   publishes needs explicit approval.\n4. Prefer one clear operation at a time when the user is reviewing edits.\n   Use `video_propose_timeline_ops` for multi-op plans before applying them.\n5. Never trim mid-word. When transcript timing exists, snap edit boundaries to\n   word or sentence boundaries and preserve 30-200 ms of context unless the\n   user asks for frame-tight cuts.\n6. Keep audio continuity deliberate. After visual transitions longer than\n   500 ms, set the clip audio seam to `cut` unless the user asks to preserve\n   source audio under the transition.\n7. Subtitles come after structural edits. Make cuts, reframes, overlays, and\n   narration decisions first, then add or refresh captions.\n8. For generated images or video, use existing project assets as references\n   when the user asks to keep identity, layout, or product appearance stable.\n9. Surface cost in plain language after generation or render work. Do not stop\n   because of cost unless the user asks for a budget limit.\n10. Verify before publish. Use render verification and mention any degraded\n    transitions, missing media, loudness issues, or caption drift.\n11. Preflight storyboard duration against the project template before approval:\n    `ugc-ad` allows 15 seconds, themed templates allow 60 seconds, and `custom`\n    is unlimited. If the confirmed edit is longer, explain the mismatch and use\n    `video_set_project_template` or trim it before `video_approve_storyboard`.\n    `video_select_template` is only for HTML\u002FMotion gallery templates and does\n    not change this ceiling.\n12. A vivid photo sequence needs a designed visual treatment, not only generic\n    zoom keyframes. Analyze each photo and adjacent footage, choose one coherent\n    vivid-overlay or gallery-template family, vary content-aware motion, and\n    inspect composited frames. Keep the supplied photos recognizable; generate\n    derived or replacement imagery only when the user asks and approves cost.\n13. If image\u002Fvideo generation fails, report the provider error. Do not silently\n    substitute a placeholder, unrelated asset, or unmaterialized AI scene.\n\n## Project directory contract\n\nEvery Video Mode project on disk uses this layout. Honor it when picking\nwork directories for ad-hoc tool calls (e.g. `mcp__ffmpeg-processing__*`)\nand when describing where files live to the user:\n\n```\n\u003CprojectDir>\u002F\n  project.json          # journal + storyboard + timeline + asset registry\n  assets\u002F               # ALL source \u002F working media\n                        #   - generated images (Seedream \u002F Imagen \u002F GPT-Image)\n                        #   - generated videos (Veo \u002F Seedance \u002F Runway)\n                        #   - generated voiceover (TTS) and music\n                        #   - generated b-roll, lipsync renders\n                        #   - user uploads and reference images\n                        #   - any ffmpeg intermediate the agent produces\n                        # The runtime steers media MCP outputs here automatically.\n  sources\u002F              # imported original captures before processing\n  cache\u002F                # render cache (per-scene + per-clip previews)\n  output\u002F               # ONLY the final rendered video + its caption .srt\n                        # Do not write anything else here.\n```\n\nIf you call `mcp__ffmpeg-processing__*` for an ad-hoc transform (trim,\nconcat, audio normalize, frame extract), pass `work_dir` as\n`\u003CprojectDir>\u002Fassets` so the result lands with the rest of the working\nmedia. Reach `\u003CprojectDir>` via `video_get_project_summary` if you don't\nalready have it from earlier in the turn.\n\n## Tool Selection\n\n- `video_get_project_summary`: first read of every turn.\n- `video_set_project_template`: change the duration-governing project template;\n  use it for an approved long-form edit that cannot pass the current ceiling.\n- `video_describe_scene`: user asks what is in a scene or wants an edit scoped\n  to a scene.\n- `video_add_scene`, `video_remove_scene`, `video_reorder_scenes`: storyboard\n  structure changes.\n- `video_set_duration`, `video_set_transition`, `video_set_timeline_bookend`,\n  `video_set_clip_audio_seam`: timeline timing and boundary polish.\n- `video_propose_timeline_ops`: batch edits, auto-cuts, pacing changes, source\n  capture insertion, or recipe-driven operation sets.\n- `video_apply_timeline_op`: one reviewed timeline operation.\n- `video_set_caption`, `video_add_captions`: caption content and style.\n- `video_generate_voiceover`, `video_generate_music`: narration or music plans.\n- `mcp__media__media_generate_image` and `mcp__media__media_generate_video`:\n  asset generation. Ask before calls because they can spend money. The output\n  file is auto-registered as a project asset by the runtime — you do not need\n  to call any follow-up tool to attach it to the library. Mention to the user\n  that the new asset is in the project's Assets panel and offer to attach it\n  to a specific scene with `video_attach_asset` (with sceneId) when the\n  context implies a target scene.\n- `video_analyze_image`, `video_list_overlay_presets`,\n  `video_inspect_timeline_frames`: the minimum loop for vivid, cinematic, or\n  style-matched photo slides. Prefer a consistent overlay\u002Fframe family plus\n  subject-aware motion over three repeated scale-only moves.\n- `video_reframe`: aspect-ratio adaptation.\n- `video_render`, `video_verify_render`, `video_publish_to`: finalization path.\n\n## Approval Copy\n\nWhen asking for approval, be concrete:\n\n- Say what will change.\n- Name the affected scene, clip, track, aspect ratio, or destination.\n- Mention likely cost for generation\u002Frender work when available.\n- Keep the approval text short enough to fit a card.\n\nGood examples:\n\n- \"Generate 4 reference images for Scene 2 using the product hero asset?\"\n- \"Trim clip `clip-voice-1` from 12.4s to 18.9s and journal undo data?\"\n- \"Render a 9:16 draft locally with burned-in captions?\"\n\n## Response Discipline\n\nAfter tool use, summarize the result, not the implementation. If an edit was\njournaled, mention that undo is available. If a requested operation cannot be\ndone with the current tools, say which project fact is missing and ask for the\nsmallest next input.\n","# Video Editing\n\nUse this skill whenever you are editing a Video Mode project through the\n`mcp__video-edit__*`, `mcp__media__*`, or `mcp__ffmpeg-processing__*` tools.\n\n## Operating Rules\n\n1. Read current project state before editing. Start with\n   `video_get_project_summary`; use `video_get_scene`,\n   `video_get_timeline`, and `video_list_assets` for narrower context.\n2. Use Video Mode tools for every project mutation. Do not use shell or file\n   editing tools to change `project.json`, assets, timeline JSON, or renders.\n3. Read and reversible write operations can proceed directly. Anything that\n   removes content, changes timing substantially, spends money, renders, or\n   publishes needs explicit approval.\n4. Prefer one clear operation at a time when the user is reviewing edits.\n   Use `video_propose_timeline_ops` for multi-op plans before applying them.\n5. Never trim mid-word. When transcript timing exists, snap edit boundaries to\n   word or sentence boundaries and preserve 30-200 ms of context unless the\n   user asks for frame-tight cuts.\n6. Keep audio continuity deliberate. After visual transitions longer than\n   500 ms, set the clip audio seam to `cut` unless the user asks to preserve\n   source audio under the transition.\n7. Subtitles come after structural edits. Make cuts, reframes, overlays, and\n   narration decisions first, then add or refresh captions.\n8. For generated images or video, use existing project assets as references\n   when the user asks to keep identity, layout, or product appearance stable.\n9. Surface cost in plain language after generation or render work. Do not stop\n   because of cost unless the user asks for a budget limit.\n10. Verify before publish. Use render verification and mention any degraded\n    transitions, missing media, loudness issues, or caption drift.\n11. Preflight storyboard duration against the project template before approval:\n    `ugc-ad` allows 15 seconds, themed templates allow 60 seconds, and `custom`\n    is unlimited. If the confirmed edit is longer, explain the mismatch and use\n    `video_set_project_template` or trim it before `video_approve_storyboard`.\n    `video_select_template` is only for HTML\u002FMotion gallery templates and does\n    not change this ceiling.\n12. A vivid photo sequence needs a designed visual treatment, not only generic\n    zoom keyframes. Analyze each photo and adjacent footage, choose one coherent\n    vivid-overlay or gallery-template family, vary content-aware motion, and\n    inspect composited frames. Keep the supplied photos recognizable; generate\n    derived or replacement imagery only when the user asks and approves cost.\n13. If image\u002Fvideo generation fails, report the provider error. Do not silently\n    substitute a placeholder, unrelated asset, or unmaterialized AI scene.\n\n## Project directory contract\n\nEvery Video Mode project on disk uses this layout. Honor it when picking\nwork directories for ad-hoc tool calls (e.g. `mcp__ffmpeg-processing__*`)\nand when describing where files live to the user:\n\n```\n\u003CprojectDir>\u002F\n  project.json          # journal + storyboard + timeline + asset registry\n  assets\u002F               # ALL source \u002F working media\n                        #   - generated images (Seedream \u002F Imagen \u002F GPT-Image)\n                        #   - generated videos (Veo \u002F Seedance \u002F Runway)\n                        #   - generated voiceover (TTS) and music\n                        #   - generated b-roll, lipsync renders\n                        #   - user uploads and reference images\n                        #   - any ffmpeg intermediate the agent produces\n                        # The runtime steers media MCP outputs here automatically.\n  sources\u002F              # imported original captures before processing\n  cache\u002F                # render cache (per-scene + per-clip previews)\n  output\u002F               # ONLY the final rendered video + its caption .srt\n                        # Do not write anything else here.\n```\n\nIf you call `mcp__ffmpeg-processing__*` for an ad-hoc transform (trim,\nconcat, audio normalize, frame extract), pass `work_dir` as\n`\u003CprojectDir>\u002Fassets` so the result lands with the rest of the working\nmedia. Reach `\u003CprojectDir>` via `video_get_project_summary` if you don't\nalready have it from earlier in the turn.\n\n## Tool Selection\n\n- `video_get_project_summary`: first read of every turn.\n- `video_set_project_template`: change the duration-governing project template;\n  use it for an approved long-form edit that cannot pass the current ceiling.\n- `video_describe_scene`: user asks what is in a scene or wants an edit scoped\n  to a scene.\n- `video_add_scene`, `video_remove_scene`, `video_reorder_scenes`: storyboard\n  structure changes.\n- `video_set_duration`, `video_set_transition`, `video_set_timeline_bookend`,\n  `video_set_clip_audio_seam`: timeline timing and boundary polish.\n- `video_propose_timeline_ops`: batch edits, auto-cuts, pacing changes, source\n  capture insertion, or recipe-driven operation sets.\n- `video_apply_timeline_op`: one reviewed timeline operation.\n- `video_set_caption`, `video_add_captions`: caption content and style.\n- `video_generate_voiceover`, `video_generate_music`: narration or music plans.\n- `mcp__media__media_generate_image` and `mcp__media__media_generate_video`:\n  asset generation. Ask before calls because they can spend money. The output\n  file is auto-registered as a project asset by the runtime — you do not need\n  to call any follow-up tool to attach it to the library. Mention to the user\n  that the new asset is in the project's Assets panel and offer to attach it\n  to a specific scene with `video_attach_asset` (with sceneId) when the\n  context implies a target scene.\n- `video_analyze_image`, `video_list_overlay_presets`,\n  `video_inspect_timeline_frames`: the minimum loop for vivid, cinematic, or\n  style-matched photo slides. Prefer a consistent overlay\u002Fframe family plus\n  subject-aware motion over three repeated scale-only moves.\n- `video_reframe`: aspect-ratio adaptation.\n- `video_render`, `video_verify_render`, `video_publish_to`: finalization path.\n\n## Approval Copy\n\nWhen asking for approval, be concrete:\n\n- Say what will change.\n- Name the affected scene, clip, track, aspect ratio, or destination.\n- Mention likely cost for generation\u002Frender work when available.\n- Keep the approval text short enough to fit a card.\n\nGood examples:\n\n- \"Generate 4 reference images for Scene 2 using the product hero asset?\"\n- \"Trim clip `clip-voice-1` from 12.4s to 18.9s and journal undo data?\"\n- \"Render a 9:16 draft locally with burned-in captions?\"\n\n## Response Discipline\n\nAfter tool use, summarize the result, not the implementation. If an edit was\njournaled, mention that undo is available. If a requested operation cannot be\ndone with the current tools, say which project fact is missing and ask for the\nsmallest next input.\n",{"name":5,"description":7},"main","aaca138d7c3773be662941b4081c8d97ea40019c","skills\u002Fvideo-editing",4,"https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar","https:\u002F\u002Fgithub.com\u002Fbravew","2026-11-14 10:00:31",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add bravew\u002FNeumar --skill video-editing",{"tool":37,"command":38},"bunx","bunx skills add bravew\u002FNeumar --skill video-editing",{"tool":40,"command":41},"pnpm","pnpm dlx skills add bravew\u002FNeumar --skill video-editing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-editing\u002FSKILL.md",true,[45,51,55,59,63],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"rubric.yaml","REFERENCE","参考文档",711,"https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-editing\u002Frubric.yaml",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"tasks\u002Fgeneration-failure.md",332,"https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-editing\u002Ftasks\u002Fgeneration-failure.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"tasks\u002Flong-montage.md",368,"https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-editing\u002Ftasks\u002Flong-montage.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"tasks\u002Fplain-trim-bypass.md",237,"https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-editing\u002Ftasks\u002Fplain-trim-bypass.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"tasks\u002Fvivid-photo-outro.md",369,"https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-editing\u002Ftasks\u002Fvivid-photo-outro.md",[68,75,82,89,97,104],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7ACYSWTPZHXD0B5ETTFRGDT","yt-dlp","A robust CLI wrapper for yt-dlp to download videos, playlists, and audio from YouTube and thousands of other sites. Supports format selection, quality control, metadata embedding, and cookie authentication.","https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fyt-dlp\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7ACYREEK21KR5F1NVQFN001","weather","Get current weather and forecasts (no API key required).","https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fweather\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7ACYJVVTAVCDX4VH75S62XR","video-edit","Conversational video editing workflow for cuts, transcript-based edits, overlays, captions, subtitle burn-in, and render planning with ffmpeg. Use when the user asks to edit video by instruction, cut silence or words, add subtitles, add overlays, transcribe video, or render a final clip.","https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-edit\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7ACYC5X6V4A4EW0C3NRQX0K","skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7ACY9JKHWXA21JCXJ8VMSVY","ship","Full shipping workflow: test, review, version, changelog, and PR creation.\nUse when: preparing to ship code, creating releases, merging PRs.","https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fship\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7ACY4SSZ1ZYC0NEBBJSADKQ","security-audit","Application security audit covering OWASP Top 10, STRIDE threat modeling, and secrets archaeology.\nUse when: security review, pre-launch audit, dependency scanning.","https:\u002F\u002Fgithub.com\u002Fbravew\u002FNeumar\u002Fblob\u002Fmain\u002Fskills\u002Fsecurity-audit\u002FSKILL.md",[],[]]