[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AH5GSN8K96ZJ8BAYP8FTW7":3,"skill-same:01M7AH5GSN8K96ZJ8BAYP8FTW7":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7AH5GSN8K96ZJ8BAYP8FTW7","video-review-os",null,"Review, tag, cut, and reframe video with Video Review OS — a local-first pipeline that turns raw footage into reviewable clip drafts, edit assemblies, captions, and vertical renders. Use when the user wants to process footage, find a moment across their library, tag or bucket clips, build a short from existing material, fix caption timing, or reframe horizontal video for vertical. Also use when they mention raw\u002F, projects\u002F, clips.json, tags.json, perception.json, assemblies.json, or the review dashboard.","cgallic\u002Fvideo-review-os","cgallic","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4923619?v=4","01M7AH55QB9XQMSW2473JP356H","01M7AH55RHXGKBT007W96YBACY",7,"MIT","https:\u002F\u002Fgithub.com\u002Fcgallic\u002Fvideo-review-os\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fvideo-review-os\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: video-review-os\ndescription: Review, tag, cut, and reframe video with Video Review OS — a local-first pipeline that turns raw footage into reviewable clip drafts, edit assemblies, captions, and vertical renders. Use when the user wants to process footage, find a moment across their library, tag or bucket clips, build a short from existing material, fix caption timing, or reframe horizontal video for vertical. Also use when they mention raw\u002F, projects\u002F, clips.json, tags.json, perception.json, assemblies.json, or the review dashboard.\nlicense: MIT\n---\n\n# Video Review OS\n\nA local-first video pipeline. Footage goes in; reviewable artifacts come out. Every\nstage writes a JSON artifact you can read, and nothing is ever published.\n\n## Before anything else\n\nRun `video-review-os providers`. It prints every pluggable capability and which\nimplementation is active. **Nothing here is tied to a particular AI vendor** — transcription,\ntagging, storyboard, copy, and visual perception are all named providers resolved from\n`config.toml`. If the user asks to \"use model X\", that is a config edit\n(`provider = \"openai-compatible\"` plus a `base_url`), never a code change.\n\n## The pipeline\n\n```\nscan → ingest → transcribe → select-clips → scenes → perceive → tag\n     → captions → silence → storyboard → assemble → render-assemblies → approve\n```\n\n`video-review-os run-once` walks the whole thing over the watch folder. Individual\ncommands take a project id or path, so you can re-run one stage without redoing the rest.\n\n| Command | Writes | What it gives you |\n| --- | --- | --- |\n| `ingest \u003Cfile>` | `source.json` | ffprobe facts + content hash |\n| `transcribe \u003Cp>` | `transcript.json` | words with timings (+ optional speakers) |\n| `select-clips \u003Cp>` | `clips.json` | candidate ranges with keep\u002Ftrim\u002Freview\u002Freject |\n| `scenes \u003Cp>` | `scenes\u002F`, `scenes.json` | representative stills per clip |\n| `perceive \u003Cp>` | `perception.json` | visual attributes + subject-aware reframe window |\n| `tag \u003Cp>` | `tags.json` | source bucket + per-clip topics and visual attributes |\n| `captions \u003Cp>` | `captions\u002F` | SRT\u002FVTT shaped for readability |\n| `assemble \u003Cp>` | `assemblies.json` | concrete multi-range edit drafts |\n| `render-assemblies \u003Cp>` | `renders\u002F` | single-pass MP4s |\n| `dashboard` | `dashboard\u002F` | static review surface (`serve` for the editor) |\n\n## Rules you must not break\n\n1. **`reject` is radioactive.** A rejected clip is never assembled, rendered, or queued.\n   Not via a library pin, not via a filter, not via an override.\n2. **Providers are never trusted.** Any hosted output is sanitized to known enum values\n   and degrades to the deterministic fallback. A provider failure must never abort a run.\n3. **Approval is a signature.** Anything that changes what renders — a range, a card, a\n   reframe window — changes `assembly_signature` and invalidates prior approvals. Never\n   work around this to preserve an approval.\n4. **Human overrides survive regeneration.** Corrections live in sidecars keyed by content\n   hash (`tag_overrides.json`, `assembly_edits.json`), never by array index.\n5. **No auto-publish, ever.** The pipeline ends at approved local renders and manual queue\n   files. Do not add upload adapters or platform APIs.\n6. **Schema bumps.** Change an artifact's shape, bump its `schema_version`.\n\n## Working with the artifacts\n\nRead them; don't guess. `clips.json` has the decision and score per candidate,\n`perception.json` has what the pixels showed, `tags.json` joins both. When a user asks\n\"why was this clip rejected\", the answer is in `clips.json`'s gate reasons — quote it.\n\nFor deeper work on specific areas, load the companion skills: `video-perception` for\nvisual analysis and reframing, `video-tagging` for tags, buckets, and library search.\n\n## Setup\n\n```bash\npip install -e .            # or: pip install video-review-os\nvideo-review-os init-config # writes config.toml with every option documented\n```\n\nOptional extras: `[whisper]` or `[faster-whisper]` for local transcription, `[hosted]`\nfor any HTTP provider. ffmpeg and ffprobe must be on PATH.\n","# Video Review OS\n\nA local-first video pipeline. Footage goes in; reviewable artifacts come out. Every\nstage writes a JSON artifact you can read, and nothing is ever published.\n\n## Before anything else\n\nRun `video-review-os providers`. It prints every pluggable capability and which\nimplementation is active. **Nothing here is tied to a particular AI vendor** — transcription,\ntagging, storyboard, copy, and visual perception are all named providers resolved from\n`config.toml`. If the user asks to \"use model X\", that is a config edit\n(`provider = \"openai-compatible\"` plus a `base_url`), never a code change.\n\n## The pipeline\n\n```\nscan → ingest → transcribe → select-clips → scenes → perceive → tag\n     → captions → silence → storyboard → assemble → render-assemblies → approve\n```\n\n`video-review-os run-once` walks the whole thing over the watch folder. Individual\ncommands take a project id or path, so you can re-run one stage without redoing the rest.\n\n| Command | Writes | What it gives you |\n| --- | --- | --- |\n| `ingest \u003Cfile>` | `source.json` | ffprobe facts + content hash |\n| `transcribe \u003Cp>` | `transcript.json` | words with timings (+ optional speakers) |\n| `select-clips \u003Cp>` | `clips.json` | candidate ranges with keep\u002Ftrim\u002Freview\u002Freject |\n| `scenes \u003Cp>` | `scenes\u002F`, `scenes.json` | representative stills per clip |\n| `perceive \u003Cp>` | `perception.json` | visual attributes + subject-aware reframe window |\n| `tag \u003Cp>` | `tags.json` | source bucket + per-clip topics and visual attributes |\n| `captions \u003Cp>` | `captions\u002F` | SRT\u002FVTT shaped for readability |\n| `assemble \u003Cp>` | `assemblies.json` | concrete multi-range edit drafts |\n| `render-assemblies \u003Cp>` | `renders\u002F` | single-pass MP4s |\n| `dashboard` | `dashboard\u002F` | static review surface (`serve` for the editor) |\n\n## Rules you must not break\n\n1. **`reject` is radioactive.** A rejected clip is never assembled, rendered, or queued.\n   Not via a library pin, not via a filter, not via an override.\n2. **Providers are never trusted.** Any hosted output is sanitized to known enum values\n   and degrades to the deterministic fallback. A provider failure must never abort a run.\n3. **Approval is a signature.** Anything that changes what renders — a range, a card, a\n   reframe window — changes `assembly_signature` and invalidates prior approvals. Never\n   work around this to preserve an approval.\n4. **Human overrides survive regeneration.** Corrections live in sidecars keyed by content\n   hash (`tag_overrides.json`, `assembly_edits.json`), never by array index.\n5. **No auto-publish, ever.** The pipeline ends at approved local renders and manual queue\n   files. Do not add upload adapters or platform APIs.\n6. **Schema bumps.** Change an artifact's shape, bump its `schema_version`.\n\n## Working with the artifacts\n\nRead them; don't guess. `clips.json` has the decision and score per candidate,\n`perception.json` has what the pixels showed, `tags.json` joins both. When a user asks\n\"why was this clip rejected\", the answer is in `clips.json`'s gate reasons — quote it.\n\nFor deeper work on specific areas, load the companion skills: `video-perception` for\nvisual analysis and reframing, `video-tagging` for tags, buckets, and library search.\n\n## Setup\n\n```bash\npip install -e .            # or: pip install video-review-os\nvideo-review-os init-config # writes config.toml with every option documented\n```\n\nOptional extras: `[whisper]` or `[faster-whisper]` for local transcription, `[hosted]`\nfor any HTTP provider. ffmpeg and ffprobe must be on PATH.\n",{"name":5,"license":14,"description":7},"main","33907d118b243cc1988fa66a19483a494e35d988","plugin\u002Fskills\u002Fvideo-review-os",4,"https:\u002F\u002Fgithub.com\u002Fcgallic\u002Fvideo-review-os","https:\u002F\u002Fgithub.com\u002Fcgallic","wwww.connorgallic.com","2026-07-30 23:30:55",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add cgallic\u002Fvideo-review-os --skill video-review-os",{"tool":37,"command":38},"bunx","bunx skills add cgallic\u002Fvideo-review-os --skill video-review-os",{"tool":40,"command":41},"pnpm","pnpm dlx skills add cgallic\u002Fvideo-review-os --skill video-review-os","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcgallic\u002Fvideo-review-os\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fvideo-review-os\u002FSKILL.md",true,[],[46,53,60],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M7AH5QWAYX7B2Q14580AKNB3","video-tagging","Tag, bucket, and search video clips in Video Review OS. Use when working with tags.json, content buckets, event\u002Fperformer\u002Fvenue tags, per-clip topics, the shared clip library, cross-project search, or when a user asks to find footage by what it shows or what was said. Also use when correcting a wrong tag or explaining how a bucket was chosen.","https:\u002F\u002Fgithub.com\u002Fcgallic\u002Fvideo-review-os\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fvideo-tagging\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M7AH5C31FBS1B0A76MYJCK37","video-review-os-plugins","Write a custom provider for Video Review OS — a new transcription, diarization, copy, tagging, storyboard, or visual perception backend — and register it without forking the repo. Use when the user wants to plug in their own model, endpoint, or local runtime, asks how the provider registry works, wants to swap which AI serves a stage, or gets \"unknown provider\" behaviour.","https:\u002F\u002Fgithub.com\u002Fcgallic\u002Fvideo-review-os\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fvideo-review-os-plugins\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M7AH573VFEDVNJEC95JVQGJZ","video-perception","Analyze what a video clip's pixels show and reframe horizontal footage for vertical output. Use when working with perception.json, shot type, scene type, camera motion, exposure, on-screen text, saliency, subject tracking, auto-reframe, 9:16 conversion, or when configuring a vision model for Video Review OS. Also use when the user asks why a clip was flagged as needing reframe, or wants to plug a different vision model into the pipeline.","https:\u002F\u002Fgithub.com\u002Fcgallic\u002Fvideo-review-os\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fvideo-perception\u002FSKILL.md",[],[]]