[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72SWXJRYETAHGYBFXAVRTV1":3,"skill-same:01M72SWXJRYETAHGYBFXAVRTV1":69},{"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":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":54,"updatedAt":55,"install":56,"resources":68},"01M72SWXJRYETAHGYBFXAVRTV1","media-ingest",null,"Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain.\nMulti-format handling with entity extraction and backlink propagation. Covers\nvideo-ingest, youtube-ingest, and book-ingest subtypes.","ltdrew\u002FAgent-brain-2","ltdrew","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F173687628?v=4","01M72SVABERGYY99JQPNV3FTTN","Logan Drew","01M72SVABZHAN29CHRV66Y48B8",1,"MIT","https:\u002F\u002Fgithub.com\u002Fltdrew\u002FAgent-brain-2\u002Fblob\u002Ffeat\u002Fbrain-first-convention\u002Fskills\u002Fmedia-ingest\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: media-ingest\nversion: 1.0.0\ndescription: |\n  Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain.\n  Multi-format handling with entity extraction and backlink propagation. Covers\n  video-ingest, youtube-ingest, and book-ingest subtypes.\ntriggers:\n  - \"watch this video\"\n  - \"process this YouTube link\"\n  - \"ingest this PDF\"\n  - \"save this podcast\"\n  - \"process this book\"\n  - \"what's in this screenshot\"\n  - \"check out this repo\"\ntools:\n  - search\n  - query\n  - get_page\n  - put_page\n  - add_link\n  - add_timeline_entry\n  - file_upload\nmutating: true\nwrites_pages: true\nwrites_to:\n  - concepts\u002F\n  - people\u002F\n  - companies\u002F\n  - sources\u002F\n---\n\n# Media Ingest Skill\n\nIngest video, audio, PDF, book, screenshot, and GitHub repo content into the brain.\n\n> **Filing rule:** Read `skills\u002F_brain-filing-rules.md` before creating any new page.\n\n## Contract\n\nThis skill guarantees:\n- Every ingested media item has a brain page with analysis (not just a transcript dump)\n- Transcripts (video\u002Faudio) saved in raw and human-readable formats\n- Entity extraction: every person and company mentioned gets back-linked\n- Raw source files preserved via `gbrain files upload-raw`\n- Filing by primary subject, not by media format\n\n> **Convention:** See `skills\u002Fconventions\u002Fquality.md` for Iron Law back-linking.\n\nEvery mention of a person or company with a brain page MUST create a back-link.\n\n## Phases\n\n### Phase 1: Identify format and fetch\n\n| Format | Action |\n|--------|--------|\n| YouTube\u002Fvideo URL | Fetch transcript (Whisper, transcription service, or captions) |\n| Audio file | Transcribe with available STT service |\n| PDF | Extract text (OCR if needed) |\n| Book PDF | Extract text, identify chapters\u002Fsections |\n| Screenshot\u002Fimage | OCR via vision model, extract text and entities |\n| GitHub repo | Clone, read README + key files, summarize architecture |\n\n### Phase 2: Upload raw source\n\nSave the original file for provenance: `gbrain files upload-raw \u003Cfile> --page \u003Cslug>`\n\n### Phase 3: Create brain page\n\nFile by primary subject (not format). Use this template:\n\n```markdown\n# {Title}\n\n**Source:** {URL or file path}\n**Format:** {video\u002Faudio\u002FPDF\u002Fbook\u002Fscreenshot\u002Frepo}\n**Created:** {date}\n\n## Summary\n{Key points, not a transcript dump}\n\n## Key Segments \u002F Highlights\n{For video\u002Faudio: timestamped highlights. For books: chapter summaries.}\n\n## People Mentioned\n{List with links to brain pages}\n\n## Companies Mentioned\n{List with links to brain pages}\n```\n\n### Phase 4: Entity extraction and propagation\n\nFor every person and company mentioned:\n1. Check brain for existing page\n2. Create\u002Fenrich if needed (delegate to enrich skill)\n3. Add back-link from entity page to this media page\n4. Add timeline entry on entity page\n\nA media item is NOT fully ingested until entity propagation is complete.\n\n### Phase 5: Sync\n\n`gbrain sync` to update the index.\n\n## Output Format\n\nBrain page created with summary, highlights, and entity cross-links. Report to user:\n\"Ingested {title}: {N} entities detected, {N} pages updated.\"\n\n## Anti-Patterns\n\n- Dumping raw transcripts without analysis\n- Skipping entity extraction (\"I'll do that separately\")\n- Filing by format (all videos in `media\u002Fvideos\u002F`) instead of by subject\n- Not preserving raw source files\n- Creating stub pages without meaningful content\n","# Media Ingest Skill\n\nIngest video, audio, PDF, book, screenshot, and GitHub repo content into the brain.\n\n> **Filing rule:** Read `skills\u002F_brain-filing-rules.md` before creating any new page.\n\n## Contract\n\nThis skill guarantees:\n- Every ingested media item has a brain page with analysis (not just a transcript dump)\n- Transcripts (video\u002Faudio) saved in raw and human-readable formats\n- Entity extraction: every person and company mentioned gets back-linked\n- Raw source files preserved via `gbrain files upload-raw`\n- Filing by primary subject, not by media format\n\n> **Convention:** See `skills\u002Fconventions\u002Fquality.md` for Iron Law back-linking.\n\nEvery mention of a person or company with a brain page MUST create a back-link.\n\n## Phases\n\n### Phase 1: Identify format and fetch\n\n| Format | Action |\n|--------|--------|\n| YouTube\u002Fvideo URL | Fetch transcript (Whisper, transcription service, or captions) |\n| Audio file | Transcribe with available STT service |\n| PDF | Extract text (OCR if needed) |\n| Book PDF | Extract text, identify chapters\u002Fsections |\n| Screenshot\u002Fimage | OCR via vision model, extract text and entities |\n| GitHub repo | Clone, read README + key files, summarize architecture |\n\n### Phase 2: Upload raw source\n\nSave the original file for provenance: `gbrain files upload-raw \u003Cfile> --page \u003Cslug>`\n\n### Phase 3: Create brain page\n\nFile by primary subject (not format). Use this template:\n\n```markdown\n# {Title}\n\n**Source:** {URL or file path}\n**Format:** {video\u002Faudio\u002FPDF\u002Fbook\u002Fscreenshot\u002Frepo}\n**Created:** {date}\n\n## Summary\n{Key points, not a transcript dump}\n\n## Key Segments \u002F Highlights\n{For video\u002Faudio: timestamped highlights. For books: chapter summaries.}\n\n## People Mentioned\n{List with links to brain pages}\n\n## Companies Mentioned\n{List with links to brain pages}\n```\n\n### Phase 4: Entity extraction and propagation\n\nFor every person and company mentioned:\n1. Check brain for existing page\n2. Create\u002Fenrich if needed (delegate to enrich skill)\n3. Add back-link from entity page to this media page\n4. Add timeline entry on entity page\n\nA media item is NOT fully ingested until entity propagation is complete.\n\n### Phase 5: Sync\n\n`gbrain sync` to update the index.\n\n## Output Format\n\nBrain page created with summary, highlights, and entity cross-links. Report to user:\n\"Ingested {title}: {N} entities detected, {N} pages updated.\"\n\n## Anti-Patterns\n\n- Dumping raw transcripts without analysis\n- Skipping entity extraction (\"I'll do that separately\")\n- Filing by format (all videos in `media\u002Fvideos\u002F`) instead of by subject\n- Not preserving raw source files\n- Creating stub pages without meaningful content\n",{"name":5,"tools":24,"version":32,"mutating":33,"triggers":34,"writes_to":42,"description":47,"writes_pages":33},[25,26,27,28,29,30,31],"search","query","get_page","put_page","add_link","add_timeline_entry","file_upload","1.0.0",true,[35,36,37,38,39,40,41],"watch this video","process this YouTube link","ingest this PDF","save this podcast","process this book","what's in this screenshot","check out this repo",[43,44,45,46],"concepts\u002F","people\u002F","companies\u002F","sources\u002F","Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain.\nMulti-format handling with entity extraction and backlink propagation. Covers\nvideo-ingest, youtube-ingest, and book-ingest subtypes.\n","feat\u002Fbrain-first-convention","f3dace916c3845569f26904591b95baf00237bf8","skills\u002Fmedia-ingest",0,"https:\u002F\u002Fgithub.com\u002Fltdrew\u002FAgent-brain-2","https:\u002F\u002Fgithub.com\u002Fltdrew","Account 2","2026-05-13 07:52:42",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":33},[58,61,64],{"tool":59,"command":60},"npx","npx skills add ltdrew\u002FAgent-brain-2 --skill media-ingest",{"tool":62,"command":63},"bunx","bunx skills add ltdrew\u002FAgent-brain-2 --skill media-ingest",{"tool":65,"command":66},"pnpm","pnpm dlx skills add ltdrew\u002FAgent-brain-2 --skill media-ingest","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fltdrew\u002FAgent-brain-2\u002Fblob\u002Ffeat\u002Fbrain-first-convention\u002Fskills\u002Fmedia-ingest\u002FSKILL.md",[],[70,77,83,90,97,104],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M72SYQK7HQ98AEY8Z8DBT3C0","signal-detector","Always-on ambient signal capture for the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fltdrew\u002FAgent-brain-2\u002Fblob\u002Ffeat\u002Fbrain-first-convention\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fsignal-detector\u002FSKILL.md",[],[],{"skillNo":78,"name":26,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M72SYPHM4TDK6ZRV4NWAGC3D","Look up brain pages in the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fltdrew\u002FAgent-brain-2\u002Fblob\u002Ffeat\u002Fbrain-first-convention\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fquery\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M72SYN2J4BGSFS613D80AJQX","context-now","ALWAYS-ON time-sensitivity discipline for the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fltdrew\u002FAgent-brain-2\u002Fblob\u002Ffeat\u002Fbrain-first-convention\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fcontext-now\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M72SYKY67RCNH8VH9R2N0ZZV","brain-ops","Core read\u002Fwrite cycle for the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fltdrew\u002FAgent-brain-2\u002Fblob\u002Ffeat\u002Fbrain-first-convention\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fbrain-ops\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},"01M72SYHEMGTDRWSERJWZR0XE2","webhook-transforms","Generic framework for converting external events (SMS, meetings, social mentions)\ninto brain-ingestible signals. Define a transform function, register a webhook URL,\nand incoming events get processed through the brain pipeline.","https:\u002F\u002Fgithub.com\u002Fltdrew\u002FAgent-brain-2\u002Fblob\u002Ffeat\u002Fbrain-first-convention\u002Fskills\u002Fwebhook-transforms\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},"01M72SYEE2B8F47TN01CAGQ4JG","testing","Skill validation framework. Validates every skill has SKILL.md with frontmatter,\nevery reference exists, every env var is declared. The testing contract for the\nskill system itself.","https:\u002F\u002Fgithub.com\u002Fltdrew\u002FAgent-brain-2\u002Fblob\u002Ffeat\u002Fbrain-first-convention\u002Fskills\u002Ftesting\u002FSKILL.md",[],[]]