[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AVXMZTR6BZ0MTF7XDQJHTW":3,"skill-same:01M7AVXMZTR6BZ0MTF7XDQJHTW":65},{"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},"01M7AVXMZTR6BZ0MTF7XDQJHTW","multimedia-intelligence-forge",null,"Ingest, transcribe, and distill multimedia lectures, technical videos, and literature into deep agent skills and cryptographically verified Knowledge Vault items. Do not use for generic audio\u002Fvideo editing or entertainment media consumption.","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\u002Fmultimedia-intelligence-forge\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: multimedia-intelligence-forge\ndescription: Ingest, transcribe, and distill multimedia lectures, technical videos, and literature into deep agent skills and cryptographically verified Knowledge Vault items. Do not use for generic audio\u002Fvideo editing or entertainment media consumption.\n---\n\n# Multimedia Intelligence Forge: Audio, Video & Knowledge Distillation\n\n`multimedia-intelligence-forge` is an authoritative composite meta-skill that transforms unstructured multimedia assets—YouTube lectures, technical keynotes, conference recordings, and multimedia literature—into production-grade, architecturally deepened agent skills and cryptographically verified Knowledge Vault items.\n\nIt coordinates five specialized capabilities:\n1. **Subprocess Transcript Ingestion** ([`youtube-transcript-fetcher`](..\u002Fyoutube-transcript-fetcher\u002FSKILL.md))\n2. **Dual-Lens Cognitive Distillation** ([`media-mind-forge`](..\u002Fmedia-mind-forge\u002FSKILL.md))\n3. **End-to-End Deep Skill Synthesis** ([`deep-skill-forge`](..\u002Fdeep-skill-forge\u002FSKILL.md))\n4. **Cryptographic Isnad Verification** ([`epistemic-isnad-audit`](..\u002Fepistemic-isnad-audit\u002FSKILL.md))\n5. **Epistemic Memory Promotion & Vault Retention** ([`epistemic-memory-lifecycle`](..\u002Fepistemic-memory-lifecycle\u002FSKILL.md))\n\nSee [CARD.md](CARD.md) for the companion summary card, 5-stage progression matrix, and invariants checklist.\nConsult `\u002Fmedia-mind-forge` for dual-lens extraction heuristics, `\u002Fepistemic-isnad-audit` for cryptographic claim verification, and [multimodal-distillation.md](references\u002Fmultimodal-distillation.md) for multimodal distillation heuristics.\n\n---\n\n## The 5-Stage Multimedia Distillation Progression\n\n```\n[1. Transcript Ingestion] ──► [2. Dual-Lens Distillation] ──► [3. Consolidated Master Checkpoint]\n                                                                          │\n                                                                          ▼\n[5. Epistemic Vault Commit] ◄── [4. Deep Skill Scaffolding & Repair] ◄────┘\n```\n\n---\n\n## 1. Multimedia Ingestion & Subprocess Transcription\n\nFetch and normalize spoken transcripts or written media via isolated subprocess pipes without shell injection vulnerabilities:\n\n1. **Subprocess Audio\u002FTranscript Acquisition (Rule 5 & Rule 15)**:\n   - Extract full timed captions or transcripts via isolated JSON-RPC runners.\n   - Prevent argument injection by passing sanitized video IDs\u002FURLs directly to subprocess argv lists.\n2. **Deterministic Pre-LLM Normalization (Rule 9)**:\n   - Deduplicate filler phrases, vocal tics, and sponsor breaks.\n   - Segment long-form transcripts into semantically coherent chapters anchored by timestamps.\n3. **Primary Source Hashing**:\n   - Compute the SHA-256 digest of the raw transcript text for immutable lineage tracking.\n\n> **Completion criterion**: Clean, timestamp-segmented transcript generated with SHA-256 digest recorded.\n\n---\n\n## 2. Dual-Lens Cognitive Distillation\n\nApply the Dual-Lens Cognitive Distillation protocol (Rule 41), strictly bifurcating the raw material into two distinct output streams:\n\n1. **Lens A: Epistemic Introspection (Ground-Truth Beliefs)**:\n   - Extract core mental models, conceptual axioms, and philosophical heuristics.\n   - Pin each claim directly to an exact timestamp or line quote (chain-of-custody lineage).\n2. **Lens B: Procedural Skill Synthesis (Shu-Ha-Ri Execution)**:\n   - Extract operational stages, binary completion criteria, diagnostic interview questions, and anti-patterns.\n3. **Cognitive Salvage (Rule 42)**:\n   - Cleanse extracted JSON schemas through multi-pass repair (strip fences, fix trailing commas, unquote keys).\n\n> **Completion criterion**: Epistemic claims and procedural skill blueprints extracted and validated.\n\n---\n\n## 3. Visual Brief & Consolidated Checkpoint\n\nSynthesize and present findings to the user before mutating persistent state:\n\n1. **Interactive HTML Visual Brief**:\n   - Render a dark-themed visual summary in `%TEMP%` showing transcript metrics, extracted mental models, and target skill architecture.\n2. **Consolidated Master Checkpoint**:\n   - Author `implementation_plan.md` with `RequestFeedback: true` detailing both proposed Knowledge Items and new agent skill files.\n   - Await explicit user approval before proceeding to file creation.\n\n> **Completion criterion**: Interactive HTML visual brief rendered and user sign-off obtained at master checkpoint.\n\n---\n\n## 4. Deep Skill Scaffolding & Bounded Self-Repair\n\nGenerate the complete production skill package following deep-module standards:\n\n1. **Slotted & Frozen Dataclass Domain Models (Rule 12)**:\n   - Author `@dataclass(slots=True, frozen=True)` schemas with `__post_init__` invariant guards.\n2. **Craft Standards Specification**:\n   - Generate `SKILL.md` (bounded description 100-350 chars with negative boundary, Rule 44).\n   - Generate `CARD.md` with single-pipe ASCII borders and blocking checklist invariants (Rule 37).\n   - Generate `config.default.yaml` for 3-tier zero-fork configuration.\n3. **Bounded In-Flight Self-Repair**:\n   - Execute contract tests in-flight; repair syntax or schema failures automatically up to 3 attempts.\n\n> **Completion criterion**: Compliant skill package scaffolded with 100% passing tests within $\\le 3$ repair attempts.\n\n---\n\n## 5. Epistemic Isnad Lineage & Knowledge Vault Commit\n\nCommit ground-truth learnings to persistent memory according to repository invariants:\n\n1. **Canonical Dual-File Directory Format (Rule 40)**:\n   - Write `.harness\u002Fknowledge\u002F\u003Cki_id>\u002Fmetadata.json` (SHA-256, source URI, claims, verification status).\n   - Write `.harness\u002Fknowledge\u002F\u003Cki_id>\u002Fsummary.md` (distilled narrative, mental models, decision heuristics).\n2. **Ecosystem Context Map Registration**:\n   - Register forged skills in `CONTEXT-MAP.md` under their appropriate domain.\n3. **Skill Knowledge Graph Indexing**:\n   - Index the new skill nodes and dependency edges into `skill_knowledge_graph`.\n\n> **Completion criterion**: Canonical dual-file Knowledge Vault item committed, CONTEXT-MAP.md updated, and skill graph indexed.\n\n---\n\n## The Three Foundational Pillars\n\n### 1. The Visual Brief Pillar\nEvery distillation run renders an interactive HTML visual brief in `%TEMP%` displaying speech timelines, isnad claim matrices, and synthesized skill component graphs.\n\n### 2. The Mandatory Checkpoint Pillar\nThe agent must never author skill files or mutate persistent memory without first presenting `implementation_plan.md` with `RequestFeedback: true` and awaiting explicit user confirmation.\n\n### 3. Explicit Anti-Patterns\nRigid architectural boundaries prevent ungrounded transcript hallucinations, flat vault pollution, and unbounded repair loops.\n\n---\n\n## Anti-Patterns\n\n- **Ungrounded Transcript Hallucination** — Distilling claims or heuristics without verbatim quote evidence or timestamp references.\n- **Single-File Vault Pollution** — Dumping single flat JSON files into `.harness\u002Fknowledge\u002F` instead of the canonical dual-file directory (`metadata.json` + `summary.md`).\n- **Collapsing Dual-Lens Seams** — Blending epistemic belief models and executable procedural skills into an undifferentiated prose blob.\n- **Unbounded Repair Thrashing** — Retrying failing contract tests in an infinite loop without an explicit circuit breaker limit of 3 attempts.\n- **Unverified Shell Redirection** — Piping transcript downloads through bare shell redirects instead of safe subprocess UTF-8 streams.\n- **Missing Negative Deflection Boundary** — Scaffolding skills without explicit `Do not use for...` constraints in frontmatter descriptions.\n","# Multimedia Intelligence Forge: Audio, Video & Knowledge Distillation\n\n`multimedia-intelligence-forge` is an authoritative composite meta-skill that transforms unstructured multimedia assets—YouTube lectures, technical keynotes, conference recordings, and multimedia literature—into production-grade, architecturally deepened agent skills and cryptographically verified Knowledge Vault items.\n\nIt coordinates five specialized capabilities:\n1. **Subprocess Transcript Ingestion** ([`youtube-transcript-fetcher`](..\u002Fyoutube-transcript-fetcher\u002FSKILL.md))\n2. **Dual-Lens Cognitive Distillation** ([`media-mind-forge`](..\u002Fmedia-mind-forge\u002FSKILL.md))\n3. **End-to-End Deep Skill Synthesis** ([`deep-skill-forge`](..\u002Fdeep-skill-forge\u002FSKILL.md))\n4. **Cryptographic Isnad Verification** ([`epistemic-isnad-audit`](..\u002Fepistemic-isnad-audit\u002FSKILL.md))\n5. **Epistemic Memory Promotion & Vault Retention** ([`epistemic-memory-lifecycle`](..\u002Fepistemic-memory-lifecycle\u002FSKILL.md))\n\nSee [CARD.md](CARD.md) for the companion summary card, 5-stage progression matrix, and invariants checklist.\nConsult `\u002Fmedia-mind-forge` for dual-lens extraction heuristics, `\u002Fepistemic-isnad-audit` for cryptographic claim verification, and [multimodal-distillation.md](references\u002Fmultimodal-distillation.md) for multimodal distillation heuristics.\n\n---\n\n## The 5-Stage Multimedia Distillation Progression\n\n```\n[1. Transcript Ingestion] ──► [2. Dual-Lens Distillation] ──► [3. Consolidated Master Checkpoint]\n                                                                          │\n                                                                          ▼\n[5. Epistemic Vault Commit] ◄── [4. Deep Skill Scaffolding & Repair] ◄────┘\n```\n\n---\n\n## 1. Multimedia Ingestion & Subprocess Transcription\n\nFetch and normalize spoken transcripts or written media via isolated subprocess pipes without shell injection vulnerabilities:\n\n1. **Subprocess Audio\u002FTranscript Acquisition (Rule 5 & Rule 15)**:\n   - Extract full timed captions or transcripts via isolated JSON-RPC runners.\n   - Prevent argument injection by passing sanitized video IDs\u002FURLs directly to subprocess argv lists.\n2. **Deterministic Pre-LLM Normalization (Rule 9)**:\n   - Deduplicate filler phrases, vocal tics, and sponsor breaks.\n   - Segment long-form transcripts into semantically coherent chapters anchored by timestamps.\n3. **Primary Source Hashing**:\n   - Compute the SHA-256 digest of the raw transcript text for immutable lineage tracking.\n\n> **Completion criterion**: Clean, timestamp-segmented transcript generated with SHA-256 digest recorded.\n\n---\n\n## 2. Dual-Lens Cognitive Distillation\n\nApply the Dual-Lens Cognitive Distillation protocol (Rule 41), strictly bifurcating the raw material into two distinct output streams:\n\n1. **Lens A: Epistemic Introspection (Ground-Truth Beliefs)**:\n   - Extract core mental models, conceptual axioms, and philosophical heuristics.\n   - Pin each claim directly to an exact timestamp or line quote (chain-of-custody lineage).\n2. **Lens B: Procedural Skill Synthesis (Shu-Ha-Ri Execution)**:\n   - Extract operational stages, binary completion criteria, diagnostic interview questions, and anti-patterns.\n3. **Cognitive Salvage (Rule 42)**:\n   - Cleanse extracted JSON schemas through multi-pass repair (strip fences, fix trailing commas, unquote keys).\n\n> **Completion criterion**: Epistemic claims and procedural skill blueprints extracted and validated.\n\n---\n\n## 3. Visual Brief & Consolidated Checkpoint\n\nSynthesize and present findings to the user before mutating persistent state:\n\n1. **Interactive HTML Visual Brief**:\n   - Render a dark-themed visual summary in `%TEMP%` showing transcript metrics, extracted mental models, and target skill architecture.\n2. **Consolidated Master Checkpoint**:\n   - Author `implementation_plan.md` with `RequestFeedback: true` detailing both proposed Knowledge Items and new agent skill files.\n   - Await explicit user approval before proceeding to file creation.\n\n> **Completion criterion**: Interactive HTML visual brief rendered and user sign-off obtained at master checkpoint.\n\n---\n\n## 4. Deep Skill Scaffolding & Bounded Self-Repair\n\nGenerate the complete production skill package following deep-module standards:\n\n1. **Slotted & Frozen Dataclass Domain Models (Rule 12)**:\n   - Author `@dataclass(slots=True, frozen=True)` schemas with `__post_init__` invariant guards.\n2. **Craft Standards Specification**:\n   - Generate `SKILL.md` (bounded description 100-350 chars with negative boundary, Rule 44).\n   - Generate `CARD.md` with single-pipe ASCII borders and blocking checklist invariants (Rule 37).\n   - Generate `config.default.yaml` for 3-tier zero-fork configuration.\n3. **Bounded In-Flight Self-Repair**:\n   - Execute contract tests in-flight; repair syntax or schema failures automatically up to 3 attempts.\n\n> **Completion criterion**: Compliant skill package scaffolded with 100% passing tests within $\\le 3$ repair attempts.\n\n---\n\n## 5. Epistemic Isnad Lineage & Knowledge Vault Commit\n\nCommit ground-truth learnings to persistent memory according to repository invariants:\n\n1. **Canonical Dual-File Directory Format (Rule 40)**:\n   - Write `.harness\u002Fknowledge\u002F\u003Cki_id>\u002Fmetadata.json` (SHA-256, source URI, claims, verification status).\n   - Write `.harness\u002Fknowledge\u002F\u003Cki_id>\u002Fsummary.md` (distilled narrative, mental models, decision heuristics).\n2. **Ecosystem Context Map Registration**:\n   - Register forged skills in `CONTEXT-MAP.md` under their appropriate domain.\n3. **Skill Knowledge Graph Indexing**:\n   - Index the new skill nodes and dependency edges into `skill_knowledge_graph`.\n\n> **Completion criterion**: Canonical dual-file Knowledge Vault item committed, CONTEXT-MAP.md updated, and skill graph indexed.\n\n---\n\n## The Three Foundational Pillars\n\n### 1. The Visual Brief Pillar\nEvery distillation run renders an interactive HTML visual brief in `%TEMP%` displaying speech timelines, isnad claim matrices, and synthesized skill component graphs.\n\n### 2. The Mandatory Checkpoint Pillar\nThe agent must never author skill files or mutate persistent memory without first presenting `implementation_plan.md` with `RequestFeedback: true` and awaiting explicit user confirmation.\n\n### 3. Explicit Anti-Patterns\nRigid architectural boundaries prevent ungrounded transcript hallucinations, flat vault pollution, and unbounded repair loops.\n\n---\n\n## Anti-Patterns\n\n- **Ungrounded Transcript Hallucination** — Distilling claims or heuristics without verbatim quote evidence or timestamp references.\n- **Single-File Vault Pollution** — Dumping single flat JSON files into `.harness\u002Fknowledge\u002F` instead of the canonical dual-file directory (`metadata.json` + `summary.md`).\n- **Collapsing Dual-Lens Seams** — Blending epistemic belief models and executable procedural skills into an undifferentiated prose blob.\n- **Unbounded Repair Thrashing** — Retrying failing contract tests in an infinite loop without an explicit circuit breaker limit of 3 attempts.\n- **Unverified Shell Redirection** — Piping transcript downloads through bare shell redirects instead of safe subprocess UTF-8 streams.\n- **Missing Negative Deflection Boundary** — Scaffolding skills without explicit `Do not use for...` constraints in frontmatter descriptions.\n",{"name":5,"description":7},"main","eff3b00e36d1d233ad4a4389605c82fbfa0326d3",".agents\u002Fskills\u002Fmultimedia-intelligence-forge","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 multimedia-intelligence-forge",{"tool":37,"command":38},"bunx","bunx skills add SpectreDeath\u002FBrain-Harness --skill multimedia-intelligence-forge",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SpectreDeath\u002FBrain-Harness --skill multimedia-intelligence-forge","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmultimedia-intelligence-forge\u002FSKILL.md",true,[45,51,55,59],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"CARD.md","REFERENCE","参考文档",3695,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmultimedia-intelligence-forge\u002FCARD.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"config.default.yaml",758,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmultimedia-intelligence-forge\u002Fconfig.default.yaml",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fmultimodal-distillation.md",1089,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmultimedia-intelligence-forge\u002Freferences\u002Fmultimodal-distillation.md",{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"scripts\u002Fmultimedia_distiller.py","SCRIPT","脚本",8599,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmultimedia-intelligence-forge\u002Fscripts\u002Fmultimedia_distiller.py",[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"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",[],[]]