[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AW4JY25GNVKG1MSCD3PNG2":3,"skill-same:01M7AW4JY25GNVKG1MSCD3PNG2":55},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7AW4JY25GNVKG1MSCD3PNG2","youtube-transcript-fetcher",null,"Extract full transcripts, timed captions, and spoken dialogue from YouTube videos by URL or ID via isolated subprocess JSON-RPC. Do not use for downloading raw video streams or modifying video media files.","SpectreDeath\u002FBrain-Harness","SpectreDeath","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F207463416?v=4","01M7AVGR1D4X8ADT47APKGVH2Z","JL","01M7AVGR2HSGD23BA5DBTJJTVN",0,"MIT","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-transcript-fetcher\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: youtube-transcript-fetcher\ndescription: Extract full transcripts, timed captions, and spoken dialogue from YouTube videos by URL or ID via isolated subprocess JSON-RPC. Do not use for downloading raw video streams or modifying video media files.\n---\n\n# YouTube Transcript Fetcher\n\n`youtube-transcript-fetcher` is a native Brain-Harness execution skill that extracts complete spoken transcripts, timestamped subtitle segments, and video dialogue from YouTube video URLs or 11-character video IDs. The engine executes inside a dedicated, isolated subprocess sandbox (`plugin.youtube_transcript_fetcher`), communicating over line-buffered JSON-RPC 2.0 standard I\u002FO streams.\n\nEvery execution follows three foundational pillars:\n1. **The Visual Brief** — Interactive HTML reports generated in `%TEMP%` featuring Mermaid data-flow topologies.\n2. **The Mandatory Checkpoint** — Human-in-the-loop gate (`RequestFeedback: true`) prior to executing large playlist batches or high-volume downstream summarizations.\n3. **Explicit Anti-Patterns** — Rigid behavioral boundaries preventing hallucinated URLs, unhandled caption disablements, and unbounded context blowout.\n\nSee [CARD.md](CARD.md) for the companion summary card, schema tables, and mandatory completion checklist.\n\n---\n\n## Semantic Intent Descriptors & Routing Triggers\n\nThe Agent Skill Knowledge Graph routes tasks to this skill when any of the following triggers or conceptual intents are detected:\n- **Primary Triggers**: `\"youtube transcript\"`, `\"fetch youtube captions\"`, `\"ingest youtube video\"`, `\"get video subtitles\"`, `\"youtube speech to text\"`\n- **Downstream Operations**: `\"summarize youtube video\"`, `\"extract dialogue from video\"`, `\"youtube video audio text\"`, `\"transcribe youtube url\"`\n- **Topological Predecessor To**: `prompt_pruning_layer`, `context_compiler`, `data-topology-mapper`\n\n---\n\n## Input & Output Schema Specifications\n\n### Input Schema\n| Parameter | Type | Required | Default | Description |\n|---|---|---|---|---|\n| `video_url` | `string` | No* | `\"\"` | Target YouTube URL (watch, shortened, embed, shorts, or live stream). |\n| `video_id` | `string` | No* | `\"\"` | Canonical 11-character YouTube video ID (e.g. `dQw4w9WgXcQ`). |\n| `languages` | `list[str]` | No | `[\"en\"]` | Priority list of ISO 639-1 language codes to attempt. |\n| `format` | `string` | No | `\"json\"` | Output format: `\"json\"` (timed segments list) or `\"text\"` (plain string). |\n| `preserve_formatting`| `boolean` | No | `false` | Whether to preserve HTML formatting tags (`\u003Ci>`, `\u003Cb>`) in caption segments. |\n\n*\\* Note: Either `video_url` or `video_id` must be provided.*\n\n### Output Schema (Success)\n```json\n{\n  \"status\": \"ok\",\n  \"video_id\": \"dQw4w9WgXcQ\",\n  \"format\": \"json\",\n  \"captions_available\": true,\n  \"segment_count\": 42,\n  \"transcript\": [\n    {\n      \"text\": \"We're no strangers to love\",\n      \"start\": 18.5,\n      \"duration\": 3.2\n    }\n  ],\n  \"raw_text\": \"We're no strangers to love You know the rules and so do I...\"\n}\n```\n\n### Output Schema (Captions Disabled \u002F Video Unavailable)\n```json\n{\n  \"status\": \"error\",\n  \"error\": \"Captions and transcripts are disabled for video 'dQw4w9WgXcQ'.\",\n  \"error_code\": \"TRANSCRIPTS_DISABLED\",\n  \"video_id\": \"dQw4w9WgXcQ\",\n  \"captions_available\": false\n}\n```\n\n---\n\n## Execution Sequence\n\n### Stage 1: URL & Video ID Normalization\nParse input parameters (`video_url` or `video_id`) using canonical regex pattern matching (`(?:v=|\\\u002F|youtu\\.be\\\u002F|embed\\\u002F|shorts\\\u002F)([a-zA-Z0-9_-]{11})`). Validate that a valid 11-character video ID is isolated before issuing any network requests.\n\n> **Completion criterion**: Verified 11-character video ID extracted without ambiguity.\n\n---\n\n### Stage 2: Subprocess Sandbox Dispatch & Availability Probe\nDispatch JSON-RPC request to `plugin.youtube_transcript_fetcher` across the standard I\u002FO pipe transport. Query `list_transcripts` or `fetch_transcript` to evaluate whether manual or auto-generated captions exist.\n\n> **Completion criterion**: Successful JSON-RPC handshake with the subprocess sandbox.\n\n---\n\n### Stage 3: The Visual Brief\nFor media audits or multi-video ingestion pipelines, generate a self-contained HTML report at `%TEMP%\u002Fyoutube-transcript-review-\u003Ctimestamp>.html` rendering a Mermaid sequence diagram showing the extraction topology, language availability, and segment token counts.\n\n```mermaid\ngraph LR\n    User[User \u002F Media Task] --> Normalizer[Video ID Normalizer]\n    Normalizer --> Sandbox[Isolated Subprocess Sandbox]\n    Sandbox --> JSONRPC[Line-Buffered JSON-RPC 2.0]\n    JSONRPC --> Engine[youtube-transcript-api Engine]\n    Engine --> Formatter[JSON Segments \u002F Plain Text]\n    Formatter --> Context[Context Compiler \u002F LLM Workspace]\n```\n\n> **Completion criterion**: Self-contained HTML report generated in `%TEMP%` and referenced.\n\n---\n\n### Stage 4: Mandatory Checkpoint Gate\nWhen processing video playlists, transcripts exceeding 20,000 words, or triggering high-volume downstream LLM summarization, author an `implementation_plan.md` artifact with `RequestFeedback: true`. STOP and await explicit user approval before mutating workspace files.\n\n> **Completion criterion**: Explicit user confirmation received before heavy memory ingestion.\n\n---\n\n### Stage 5: Transcript Ingestion & Token Optimization\nRetrieve the full transcript text or timed segment array. If the transcript length exceeds LLM token limits, apply deterministic middle-out pruning or chunking before appending into the agent conversation context.\n\n> **Completion criterion**: Clean, verified transcript structured into workspace target or memory.\n\n---\n\n### Stage 6: Recording & Walkthrough\nRecord completed extraction metrics (total words, segment count, video ID, execution latency) in `walkthrough.md` with clickable links to generated transcript summaries or artifacts.\n\n> **Completion criterion**: Comprehensive walkthrough artifact finalized and linked.\n\n---\n\n## Anti-Patterns\n\n- **Bare URL Hallucination** — Invoking LLM generation with speculative video content without fetching the ground-truth transcript. Always verify video ID and fetch ground-truth transcript.\n- **Unhandled Disabled Captions** — Crashing on TranscriptsDisabled or propagating unhandled tracebacks to the user. Always trap TranscriptsDisabled and report captions_available: false.\n- **Massive Memory Dumps** — Dumping raw 100,000+ word transcripts directly into chat context. Apply progressive tabular summarization and write full transcripts to disk artifacts.\n","# YouTube Transcript Fetcher\n\n`youtube-transcript-fetcher` is a native Brain-Harness execution skill that extracts complete spoken transcripts, timestamped subtitle segments, and video dialogue from YouTube video URLs or 11-character video IDs. The engine executes inside a dedicated, isolated subprocess sandbox (`plugin.youtube_transcript_fetcher`), communicating over line-buffered JSON-RPC 2.0 standard I\u002FO streams.\n\nEvery execution follows three foundational pillars:\n1. **The Visual Brief** — Interactive HTML reports generated in `%TEMP%` featuring Mermaid data-flow topologies.\n2. **The Mandatory Checkpoint** — Human-in-the-loop gate (`RequestFeedback: true`) prior to executing large playlist batches or high-volume downstream summarizations.\n3. **Explicit Anti-Patterns** — Rigid behavioral boundaries preventing hallucinated URLs, unhandled caption disablements, and unbounded context blowout.\n\nSee [CARD.md](CARD.md) for the companion summary card, schema tables, and mandatory completion checklist.\n\n---\n\n## Semantic Intent Descriptors & Routing Triggers\n\nThe Agent Skill Knowledge Graph routes tasks to this skill when any of the following triggers or conceptual intents are detected:\n- **Primary Triggers**: `\"youtube transcript\"`, `\"fetch youtube captions\"`, `\"ingest youtube video\"`, `\"get video subtitles\"`, `\"youtube speech to text\"`\n- **Downstream Operations**: `\"summarize youtube video\"`, `\"extract dialogue from video\"`, `\"youtube video audio text\"`, `\"transcribe youtube url\"`\n- **Topological Predecessor To**: `prompt_pruning_layer`, `context_compiler`, `data-topology-mapper`\n\n---\n\n## Input & Output Schema Specifications\n\n### Input Schema\n| Parameter | Type | Required | Default | Description |\n|---|---|---|---|---|\n| `video_url` | `string` | No* | `\"\"` | Target YouTube URL (watch, shortened, embed, shorts, or live stream). |\n| `video_id` | `string` | No* | `\"\"` | Canonical 11-character YouTube video ID (e.g. `dQw4w9WgXcQ`). |\n| `languages` | `list[str]` | No | `[\"en\"]` | Priority list of ISO 639-1 language codes to attempt. |\n| `format` | `string` | No | `\"json\"` | Output format: `\"json\"` (timed segments list) or `\"text\"` (plain string). |\n| `preserve_formatting`| `boolean` | No | `false` | Whether to preserve HTML formatting tags (`\u003Ci>`, `\u003Cb>`) in caption segments. |\n\n*\\* Note: Either `video_url` or `video_id` must be provided.*\n\n### Output Schema (Success)\n```json\n{\n  \"status\": \"ok\",\n  \"video_id\": \"dQw4w9WgXcQ\",\n  \"format\": \"json\",\n  \"captions_available\": true,\n  \"segment_count\": 42,\n  \"transcript\": [\n    {\n      \"text\": \"We're no strangers to love\",\n      \"start\": 18.5,\n      \"duration\": 3.2\n    }\n  ],\n  \"raw_text\": \"We're no strangers to love You know the rules and so do I...\"\n}\n```\n\n### Output Schema (Captions Disabled \u002F Video Unavailable)\n```json\n{\n  \"status\": \"error\",\n  \"error\": \"Captions and transcripts are disabled for video 'dQw4w9WgXcQ'.\",\n  \"error_code\": \"TRANSCRIPTS_DISABLED\",\n  \"video_id\": \"dQw4w9WgXcQ\",\n  \"captions_available\": false\n}\n```\n\n---\n\n## Execution Sequence\n\n### Stage 1: URL & Video ID Normalization\nParse input parameters (`video_url` or `video_id`) using canonical regex pattern matching (`(?:v=|\\\u002F|youtu\\.be\\\u002F|embed\\\u002F|shorts\\\u002F)([a-zA-Z0-9_-]{11})`). Validate that a valid 11-character video ID is isolated before issuing any network requests.\n\n> **Completion criterion**: Verified 11-character video ID extracted without ambiguity.\n\n---\n\n### Stage 2: Subprocess Sandbox Dispatch & Availability Probe\nDispatch JSON-RPC request to `plugin.youtube_transcript_fetcher` across the standard I\u002FO pipe transport. Query `list_transcripts` or `fetch_transcript` to evaluate whether manual or auto-generated captions exist.\n\n> **Completion criterion**: Successful JSON-RPC handshake with the subprocess sandbox.\n\n---\n\n### Stage 3: The Visual Brief\nFor media audits or multi-video ingestion pipelines, generate a self-contained HTML report at `%TEMP%\u002Fyoutube-transcript-review-\u003Ctimestamp>.html` rendering a Mermaid sequence diagram showing the extraction topology, language availability, and segment token counts.\n\n```mermaid\ngraph LR\n    User[User \u002F Media Task] --> Normalizer[Video ID Normalizer]\n    Normalizer --> Sandbox[Isolated Subprocess Sandbox]\n    Sandbox --> JSONRPC[Line-Buffered JSON-RPC 2.0]\n    JSONRPC --> Engine[youtube-transcript-api Engine]\n    Engine --> Formatter[JSON Segments \u002F Plain Text]\n    Formatter --> Context[Context Compiler \u002F LLM Workspace]\n```\n\n> **Completion criterion**: Self-contained HTML report generated in `%TEMP%` and referenced.\n\n---\n\n### Stage 4: Mandatory Checkpoint Gate\nWhen processing video playlists, transcripts exceeding 20,000 words, or triggering high-volume downstream LLM summarization, author an `implementation_plan.md` artifact with `RequestFeedback: true`. STOP and await explicit user approval before mutating workspace files.\n\n> **Completion criterion**: Explicit user confirmation received before heavy memory ingestion.\n\n---\n\n### Stage 5: Transcript Ingestion & Token Optimization\nRetrieve the full transcript text or timed segment array. If the transcript length exceeds LLM token limits, apply deterministic middle-out pruning or chunking before appending into the agent conversation context.\n\n> **Completion criterion**: Clean, verified transcript structured into workspace target or memory.\n\n---\n\n### Stage 6: Recording & Walkthrough\nRecord completed extraction metrics (total words, segment count, video ID, execution latency) in `walkthrough.md` with clickable links to generated transcript summaries or artifacts.\n\n> **Completion criterion**: Comprehensive walkthrough artifact finalized and linked.\n\n---\n\n## Anti-Patterns\n\n- **Bare URL Hallucination** — Invoking LLM generation with speculative video content without fetching the ground-truth transcript. Always verify video ID and fetch ground-truth transcript.\n- **Unhandled Disabled Captions** — Crashing on TranscriptsDisabled or propagating unhandled tracebacks to the user. Always trap TranscriptsDisabled and report captions_available: false.\n- **Massive Memory Dumps** — Dumping raw 100,000+ word transcripts directly into chat context. Apply progressive tabular summarization and write full transcripts to disk artifacts.\n",{"name":5,"description":7},"main","eff3b00e36d1d233ad4a4389605c82fbfa0326d3",".agents\u002Fskills\u002Fyoutube-transcript-fetcher","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness","https:\u002F\u002Fgithub.com\u002FSpectreDeath","I'm here to manage stress so I wouldn't expect earth shattering break throughs I'm just an enthusiast that likes making stuff. ","2026-11-15 05:32:58",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add SpectreDeath\u002FBrain-Harness --skill youtube-transcript-fetcher",{"tool":37,"command":38},"bunx","bunx skills add SpectreDeath\u002FBrain-Harness --skill youtube-transcript-fetcher",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SpectreDeath\u002FBrain-Harness --skill youtube-transcript-fetcher","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-transcript-fetcher\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"CARD.md","REFERENCE","参考文档",4313,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-transcript-fetcher\u002FCARD.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"config.default.yaml",302,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-transcript-fetcher\u002Fconfig.default.yaml",[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7E0W6FR68J2N9CXCZTAQJFX","ui-behavior-primitive-architect","Architect, audit, and verify zero-dependency headless UI behavior primitives, WebMCP agent bridges, WAI-ARIA\u002FSSR\u002FRTL tri-modal checks, and framework expert routing. Do not use for static CSS theme styling or backend database migrations.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fui-behavior-primitive-architect\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7E0VZ7JQNW34G271DENFGYP","trustgraph-ontology-governor","Govern knowledge graphs, SHACL-AF triple policies, OntologyRAG subclass validation, PROV-O dual named graphs, and Laya entropy decision scoring. Do not use for relational SQL queries or generic web scraping.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftrustgraph-ontology-governor\u002FSKILL.md",[],[],{"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},"01M7E0VQ6Z7R45Q8QAZ4MT39EK","shim-harness-governor","Govern universal CLI agent loops, 4-tier tool permissions, ancestor-symlink workspace sandboxes, deterministic-first command routing, collision-safe MCP namespacing, and layered skill loading. Do not use for static UI styling or external SQL analytics.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fshim-harness-governor\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7E0VC18NMP1QBSRJ3TPQ7MB","graphiti-zep-memory-governor","Govern bi-temporal knowledge graphs with Graphiti future-edge clamping, MinHash\u002FLSH entity dedup, RRF\u002FMMR reranking, and Zep typed ontologies. Do not use for static SQL joins or generic web crawling.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgraphiti-zep-memory-governor\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7E0V12ABE1RW3ZRCST8VH5Z","agora-mcp-workbench-architect","Architect, audit, and orchestrate Agora Workbench MCP servers, loopback sidecars, unified state graphs, gateway\u002Fdispatcher connectors, and policy-enforced data lakes. Do not use for static frontend CSS styling or non-MCP desktop GUI automation.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagora-mcp-workbench-architect\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7BFYG6QT3484VC57TZ19V7P","skill-eval-assurance-runner","Evaluate and assure agent skills using small-N Wilson confidence intervals, unbiased pass^k reliability, deterministic trajectory graders, preflight boundary honesty, and sealed digest verification. Do not use for subjective prose review or unconstrained production deployment.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-eval-assurance-runner\u002FSKILL.md",[],[]]