[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AVM3SPC4KCGKF4NS0X77A9":3,"skill-same:01M7AVM3SPC4KCGKF4NS0X77A9":63},{"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},"01M7AVM3SPC4KCGKF4NS0X77A9","cellcog-multimodal",null,"Orchestrate any-to-any multimodal sub-agent delegation via CellCog to generate 3D models, video, audio, executive documents, or citation-backed deep research. Do not use for basic single-file text editing.","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\u002Fcellcog-multimodal\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cellcog-multimodal\ndescription: Orchestrate any-to-any multimodal sub-agent delegation via CellCog to generate 3D models, video, audio, executive documents, or citation-backed deep research. Do not use for basic single-file text editing.\n---\n\n# CellCog Multimodal Sub-Agent Delegation\n\n`cellcog-multimodal` is the authoritative execution blueprint for delegating non-code and cross-modality tasks (3D modeling, video generation, audio\u002Fmusic synthesis, executive PDF\u002Fslide creation, and multi-source deep research) to CellCog via `plugin.cellcog`.\n\nEvery delegation cycle follows a five-stage progression:\n\n```\n[1. Task Assessment] → [2. Prompt & Tag Protocol] → [3. The Visual Brief] → [4. Mandatory Checkpoint] → [5. Execution & Verification]\n```\n\nSee [CARD.md](CARD.md) for the skill summary card, quick-reference template, and completion criteria checklist.\nConsult [REFERENCE.md](REFERENCE.md) for copy-paste golden recipes across the top 5 modalities.\nConsult `\u002Fcrafting-skills` for authoring standards and `\u002Fepistemic-isnad-audit` for provenance tracking.\n\n---\n\n## 1. Task Assessment & Modality Selection\n\nEvaluate the user's generative request to select the target operating point (`chat_mode`, `chat_tier`):\n\n1. **Modality & Mode Mapping**:\n   - `chat_mode=\"agent\"`: Most tasks — 3D model generation (.GLB), video rendering, audio\u002Fpodcast synthesis, multi-tab Excel financial models, and code.\n   - `chat_mode=\"creative\"`: Design-taste work — interactive HTML dashboards, UI wireframes, brand identity kits, presentation slide decks, creative writing.\n   - `chat_mode=\"team\"`: Deep multi-source research ONLY — cross-validation, competitive matrices, and citation-backed synthesis.\n\n2. **Quality Tier Selection**:\n   - `chat_tier=\"flash\"`: Default fast\u002Feconomical tier for light asset generation, quick scripts, or preliminary drafts.\n   - `chat_tier=\"core\"`: Balanced tier for standard decks, spreadsheets, and illustrations.\n   - `chat_tier=\"max\"`: Maximum depth tier for production video rendering, 3D character rigging, complex data analysis, or legal drafting.\n\n> **Completion criterion**: Target modality identified, `chat_mode` and `chat_tier` selected with rationale.\n\n---\n\n## 2. Prompt Construction & Tag Protocol\n\nConstruct the delegation prompt using the dual tag protocol:\n\n1. **Input Grounding (`\u003CSHOW_FILE>`)**:\n   - Wrap reference files (PDFs, images, code files, CSV data, audio) in `\u003CSHOW_FILE>\u002Fabsolute\u002Fpath\u003C\u002FSHOW_FILE>` tags.\n   - *Security Invariant*: Never wrap credentials, `.env`, `.git`, or private keys in `\u003CSHOW_FILE>` tags.\n\n2. **Deterministic Output Path (`\u003CGENERATE_FILE>`)**:\n   - Wrap desired output file paths in `\u003CGENERATE_FILE>\u002Fworkspace\u002Foutput\u002Fartifact.ext\u003C\u002FGENERATE_FILE>` tags.\n   - This guarantees artifacts download directly to deterministic locations rather than ephemeral temp folders.\n\n3. **Explicit Artifact Declarations**:\n   - State exact file formats and deliverable types explicitly (e.g. \"Create an interactive HTML dashboard, a 60s summary video, and a formatted PDF\").\n\n> **Completion criterion**: Prompt assembled with verified absolute `\u003CSHOW_FILE>` inputs and `\u003CGENERATE_FILE>` output destinations.\n\n---\n\n## 3. The Visual Brief\n\nFor non-trivial multimodal pipelines, generate an interactive visual summary:\n\n1. **Location**: Write to `%TEMP%\\cellcog-delegation-\u003Ctimestamp>.html` (Windows) or `\u002Ftmp\u002Fcellcog-delegation-\u003Ctimestamp>.html` (Unix).\n2. **Topology Diagram**: Render a Mermaid graph displaying:\n   - Input files (`\u003CSHOW_FILE>`) $\\rightarrow$ CellCog Cloud Sub-Agent (`chat_mode` + `chat_tier`) $\\rightarrow$ Output Artifacts (`\u003CGENERATE_FILE>`).\n3. **Surface**: Deliver the absolute, clickable HTML file path to the user.\n\n> **Completion criterion**: Visual brief written to `%TEMP%` and presented to user.\n\n---\n\n## 4. Mandatory Checkpoint\n\nBefore dispatching expensive cloud sub-agent tasks, present the delegation plan:\n\n1. Create or update `implementation_plan.md` artifact detailing:\n   - Target modality and deliverables list.\n   - Selected `chat_mode` and `chat_tier`.\n   - List of attached reference files and target output paths.\n2. Set `RequestFeedback: true` in artifact metadata.\n3. **STOP and wait** for explicit user review and approval before executing the API call.\n\n> **Completion criterion**: Explicit user approval received for sub-agent execution.\n\n---\n\n## 5. Execution & Verification\n\nDispatch the task through the typed `plugin.cellcog` tools:\n\n1. **Invoke Plugin Entrypoint**:\n   - For general tasks: Call `cellcog_run(prompt=..., chat_mode=..., chat_tier=...)`.\n   - For deep research: Call `cellcog_research(topic=..., attachments=..., chat_tier=...)`.\n2. **Artifact Verification**:\n   - Confirm downloaded files exist at the specified `\u003CGENERATE_FILE>` paths.\n   - Verify file sizes and non-empty content.\n3. **Record in Walkthrough**:\n   - Update `walkthrough.md` with generated artifact paths and executive summary.\n\n> **Completion criterion**: All requested deliverables verified on disk and recorded in walkthrough.\n\n---\n\n## Anti-Patterns\n\n- **Modality Over-Specification** — Searching for 39 separate tools when `cellcog_run` with an explicit prompt and `chat_mode` handles all modalities seamlessly.\n- **Credential Exposure** — Wrapping `.env` files, SSH keys, or secrets inside `\u003CSHOW_FILE>` tags.\n- **Tier Waste** — Defaulting to `max` tier for simple icon or text generation that `flash` handles instantly.\n- **Missing Output Tags** — Omitting `\u003CGENERATE_FILE>` tags, resulting in downloaded files scattered across default cache folders.\n- **Unbounded Delegation** — Dispatching long-running cloud tasks without presenting the `implementation_plan.md` checkpoint.\n","# CellCog Multimodal Sub-Agent Delegation\n\n`cellcog-multimodal` is the authoritative execution blueprint for delegating non-code and cross-modality tasks (3D modeling, video generation, audio\u002Fmusic synthesis, executive PDF\u002Fslide creation, and multi-source deep research) to CellCog via `plugin.cellcog`.\n\nEvery delegation cycle follows a five-stage progression:\n\n```\n[1. Task Assessment] → [2. Prompt & Tag Protocol] → [3. The Visual Brief] → [4. Mandatory Checkpoint] → [5. Execution & Verification]\n```\n\nSee [CARD.md](CARD.md) for the skill summary card, quick-reference template, and completion criteria checklist.\nConsult [REFERENCE.md](REFERENCE.md) for copy-paste golden recipes across the top 5 modalities.\nConsult `\u002Fcrafting-skills` for authoring standards and `\u002Fepistemic-isnad-audit` for provenance tracking.\n\n---\n\n## 1. Task Assessment & Modality Selection\n\nEvaluate the user's generative request to select the target operating point (`chat_mode`, `chat_tier`):\n\n1. **Modality & Mode Mapping**:\n   - `chat_mode=\"agent\"`: Most tasks — 3D model generation (.GLB), video rendering, audio\u002Fpodcast synthesis, multi-tab Excel financial models, and code.\n   - `chat_mode=\"creative\"`: Design-taste work — interactive HTML dashboards, UI wireframes, brand identity kits, presentation slide decks, creative writing.\n   - `chat_mode=\"team\"`: Deep multi-source research ONLY — cross-validation, competitive matrices, and citation-backed synthesis.\n\n2. **Quality Tier Selection**:\n   - `chat_tier=\"flash\"`: Default fast\u002Feconomical tier for light asset generation, quick scripts, or preliminary drafts.\n   - `chat_tier=\"core\"`: Balanced tier for standard decks, spreadsheets, and illustrations.\n   - `chat_tier=\"max\"`: Maximum depth tier for production video rendering, 3D character rigging, complex data analysis, or legal drafting.\n\n> **Completion criterion**: Target modality identified, `chat_mode` and `chat_tier` selected with rationale.\n\n---\n\n## 2. Prompt Construction & Tag Protocol\n\nConstruct the delegation prompt using the dual tag protocol:\n\n1. **Input Grounding (`\u003CSHOW_FILE>`)**:\n   - Wrap reference files (PDFs, images, code files, CSV data, audio) in `\u003CSHOW_FILE>\u002Fabsolute\u002Fpath\u003C\u002FSHOW_FILE>` tags.\n   - *Security Invariant*: Never wrap credentials, `.env`, `.git`, or private keys in `\u003CSHOW_FILE>` tags.\n\n2. **Deterministic Output Path (`\u003CGENERATE_FILE>`)**:\n   - Wrap desired output file paths in `\u003CGENERATE_FILE>\u002Fworkspace\u002Foutput\u002Fartifact.ext\u003C\u002FGENERATE_FILE>` tags.\n   - This guarantees artifacts download directly to deterministic locations rather than ephemeral temp folders.\n\n3. **Explicit Artifact Declarations**:\n   - State exact file formats and deliverable types explicitly (e.g. \"Create an interactive HTML dashboard, a 60s summary video, and a formatted PDF\").\n\n> **Completion criterion**: Prompt assembled with verified absolute `\u003CSHOW_FILE>` inputs and `\u003CGENERATE_FILE>` output destinations.\n\n---\n\n## 3. The Visual Brief\n\nFor non-trivial multimodal pipelines, generate an interactive visual summary:\n\n1. **Location**: Write to `%TEMP%\\cellcog-delegation-\u003Ctimestamp>.html` (Windows) or `\u002Ftmp\u002Fcellcog-delegation-\u003Ctimestamp>.html` (Unix).\n2. **Topology Diagram**: Render a Mermaid graph displaying:\n   - Input files (`\u003CSHOW_FILE>`) $\\rightarrow$ CellCog Cloud Sub-Agent (`chat_mode` + `chat_tier`) $\\rightarrow$ Output Artifacts (`\u003CGENERATE_FILE>`).\n3. **Surface**: Deliver the absolute, clickable HTML file path to the user.\n\n> **Completion criterion**: Visual brief written to `%TEMP%` and presented to user.\n\n---\n\n## 4. Mandatory Checkpoint\n\nBefore dispatching expensive cloud sub-agent tasks, present the delegation plan:\n\n1. Create or update `implementation_plan.md` artifact detailing:\n   - Target modality and deliverables list.\n   - Selected `chat_mode` and `chat_tier`.\n   - List of attached reference files and target output paths.\n2. Set `RequestFeedback: true` in artifact metadata.\n3. **STOP and wait** for explicit user review and approval before executing the API call.\n\n> **Completion criterion**: Explicit user approval received for sub-agent execution.\n\n---\n\n## 5. Execution & Verification\n\nDispatch the task through the typed `plugin.cellcog` tools:\n\n1. **Invoke Plugin Entrypoint**:\n   - For general tasks: Call `cellcog_run(prompt=..., chat_mode=..., chat_tier=...)`.\n   - For deep research: Call `cellcog_research(topic=..., attachments=..., chat_tier=...)`.\n2. **Artifact Verification**:\n   - Confirm downloaded files exist at the specified `\u003CGENERATE_FILE>` paths.\n   - Verify file sizes and non-empty content.\n3. **Record in Walkthrough**:\n   - Update `walkthrough.md` with generated artifact paths and executive summary.\n\n> **Completion criterion**: All requested deliverables verified on disk and recorded in walkthrough.\n\n---\n\n## Anti-Patterns\n\n- **Modality Over-Specification** — Searching for 39 separate tools when `cellcog_run` with an explicit prompt and `chat_mode` handles all modalities seamlessly.\n- **Credential Exposure** — Wrapping `.env` files, SSH keys, or secrets inside `\u003CSHOW_FILE>` tags.\n- **Tier Waste** — Defaulting to `max` tier for simple icon or text generation that `flash` handles instantly.\n- **Missing Output Tags** — Omitting `\u003CGENERATE_FILE>` tags, resulting in downloaded files scattered across default cache folders.\n- **Unbounded Delegation** — Dispatching long-running cloud tasks without presenting the `implementation_plan.md` checkpoint.\n",{"name":5,"description":7},"main","eff3b00e36d1d233ad4a4389605c82fbfa0326d3",".agents\u002Fskills\u002Fcellcog-multimodal","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 cellcog-multimodal",{"tool":37,"command":38},"bunx","bunx skills add SpectreDeath\u002FBrain-Harness --skill cellcog-multimodal",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SpectreDeath\u002FBrain-Harness --skill cellcog-multimodal","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcellcog-multimodal\u002FSKILL.md",true,[45,51,55,59],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"CARD.md","REFERENCE","参考文档",3525,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcellcog-multimodal\u002FCARD.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"config.default.yaml",294,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcellcog-multimodal\u002Fconfig.default.yaml",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"README.md",1004,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcellcog-multimodal\u002FREADME.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"REFERENCE.md",4503,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcellcog-multimodal\u002FREFERENCE.md",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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",[],[]]