[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AVVQ95AJDR4RYVWH6C0GYX":3,"skill-same:01M7AVVQ95AJDR4RYVWH6C0GYX":73},{"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},"01M7AVVQ95AJDR4RYVWH6C0GYX","icm-workspace-architect",null,"Design, scaffold, audit, and restructure workspaces using Interpretable Context Methodology (ICM, arXiv:2603.16021). Binds folder hierarchy to context scoping (L0-L4), replaces framework code with plain contracts, and validates with the walk test. Do not use for real-time high-concurrency multi-user serving or mid-pipeline dynamic branching.","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\u002Ficm-workspace-architect\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: icm-workspace-architect\ndescription: Design, scaffold, audit, and restructure workspaces using Interpretable Context Methodology (ICM, arXiv:2603.16021). Binds folder hierarchy to context scoping (L0-L4), replaces framework code with plain contracts, and validates with the walk test. Do not use for real-time high-concurrency multi-user serving or mid-pipeline dynamic branching.\n---\n\n# ICM Workspace Architect\n\n`icm-workspace-architect` is the production architecture engine for designing and restructuring workspaces where the folder structure executes agent orchestration. Rooted in the research of Van Clief & McDermott (*Interpretable Context Methodology: Folder Structure as Agent Architecture*, arXiv:2603.16021), ICM replaces complex multi-agent orchestration frameworks with five-layer context hierarchies, plain markdown contracts, and auditable stage checks.\n\nEvery ICM architecture cycle follows a five-stage progression:\n\n```\n[1. Scope & Form Selection] ──► [2. Hierarchy & Contracts] ──► [3. Verification Tooling]\n                                                                     │\n                                                                     ▼\n[5. Finalization & Maintenance] ◄── [4. 8-Point Cold Walk Test] ◄────┘\n```\n\nSee [CARD.md](CARD.md) for the companion summary card, form taxonomy, and invariants checklist.\nConsult `\u002Fcrafting-skills` for craft standards and `\u002Fagent-skill-sdlc` for lifecycle validation.\n\n---\n\n## The 10 Mandatory Invariants\n\n1. **One folder, one job** — Each folder performs a single step or holds a single kind of entity, declaring its purpose within itself.\n2. **Small, stable entry file** — `AGENTS.md` at root answers \"where am I, where does everything live, where do I go for task X\" in \u003C60 lines.\n3. **Numbering encodes order** — Numbered prefixes (`01_`, `02_`) sequence work where order matters.\n4. **Every working folder has a contract** — A `CONTEXT.md` defining Inputs, Process, Outputs, and Check.\n5. **Factory vs. product split** — Reference materials (`_shared\u002F`, schemas, voice) live apart from working artifacts (`output\u002F`, records).\n6. **Every step ends at a check** — Each stage output must pass a verified check (`check.md` with `pass` or `fail: \u003Cwhy>`) before downstream execution.\n7. **Load only what the step needs** — Step context (entry + contract + references + inputs) must stay under ~8,000 tokens.\n8. **Plain text, linkable, queryable** — Markdown + YAML frontmatter with relative links that always resolve.\n9. **Status lives on disk** — State is reflected directly in filesystem artifacts and generated `_index.md` files.\n10. **Instantiate by copying** — New work units are copies of templates from `_templates\u002F`, never blank pages.\n\n---\n\n## 1. Scope & Form Selection\n\nDetermine operational mode and select the matching ICM form from the 3 primitives (Sequence, Shelf, Catalog):\n\n1. **Select Operational Mode**:\n   - **Build Mode**: Start from an interview or process description. Identify pauses (stage boundaries), invariant rules (factory references), and deliverables.\n   - **Restructure Mode**: Take an existing messy folder or repository. Inventory files without moving, classify into 5 roles (`catalog`, `contract`, `factory`, `product`, `dead`), check live referrers, and propose a migration plan.\n2. **Select the Form**:\n   - **Pipeline**: Sequential production line with handoffs where stage $N$ output is stage $N+1$ input.\n   - **Record Library**: Uniform records accumulating status (`_index.md` generated from frontmatter).\n   - **Knowledge Bundle**: Linked concepts, claims, and raw sources with verbatim quote checks.\n   - **Context Map**: Organizational graph of teams and processes linked by `consumes:` \u002F `produces:`.\n   - **System Map**: Codebase audit hierarchy with nouns, verbs, and an impact index.\n\n> **Completion gate**: Mode selected, repeating unit identified, and candidate form confirmed.\n\n---\n\n## 2. Hierarchy & Contract Authoring\n\nScaffold the five-layer context hierarchy (L0–L4) and author stage contracts:\n\n1. **Scaffold L0 & L1 Catalogs**:\n   - Write root `AGENTS.md` (\u003C60 lines) defining identity, routing table, and rules.\n   - Author pointers: `CLAUDE.md` (`@AGENTS.md`) and `GEMINI.md` (`@.\u002FAGENTS.md`).\n   - Author root `CONTEXT.md` mapping the overall pipeline or shelf schema.\n2. **Author L2 Stage Contracts**:\n   - Every working stage receives a `CONTEXT.md`:\n     - `## Inputs`: Backticked exact paths partitioned into `Working (this run)` and `Reference (every run)`.\n     - Explicit `Do NOT load:` statement deflecting irrelevant folders.\n     - `## Process`: Numbered, deterministic instructions (commands named explicitly).\n     - `## Outputs`: Specific file paths in `output\u002F`.\n     - `## Check`: Concrete check by person, script, or small model emitting `check.md`.\n3. **Scaffold L3 Factory & Templates**:\n   - Stable reference material in `_shared\u002Fvoice.md` or `_meta\u002Fschema.md`.\n   - Stamp templates in `_templates\u002F`.\n\n> **Completion gate**: L0–L4 hierarchy scaffolded; contracts carry inputs, process, outputs, and checks.\n\n---\n\n## 3. Verification & Guardrail Tooling\n\nDeploy deterministic standard-library verification scripts into the workspace's `_tools\u002F` or execute via Harness CLI:\n\n1. **Link & Input Verification (`icm_links.py`)**:\n   - Verify that every markdown link, frontmatter `.md` path, pointer import, and backticked contract input resolves cleanly:\n     ```bash\n     harness icm links .\n     ```\n2. **Frontmatter Index Generation (`icm_index.py`)**:\n   - Rebuild `_index.md` files across record folders from frontmatter metadata without hand-editing:\n     ```bash\n     harness icm index records\n     ```\n3. **Quote & Provenance Verification (`icm_quotes.py`)**:\n   - For knowledge bundles, verify verbatim quote matches against `sources\u002Fraw\u002F` and enforce `_meta\u002Fkeep-out.txt`:\n     ```bash\n     harness icm quotes .\n     ```\n\n> **Completion gate**: Verification scripts installed in `_tools\u002F` or CLI verified; zero broken links.\n\n---\n\n## 4. The 8-Point Cold Walk Test\n\nWalk the workspace cold as an agent with zero memory to ensure interpretability:\n\n1. **Where am I**: Can the agent answer its task location within `AGENTS.md` plus at most 2 reads?\n2. **Exact Inputs**: Does the active stage contract list exact, verifiable input paths?\n3. **Pure Disk Status**: Can system status be determined entirely from disk files and `check.md` verdicts?\n4. **No Content in Catalog**: Are routing files (`AGENTS.md`, `CONTEXT.md`) free of content payloads?\n5. **Single Source of Truth**: Does each fact live in exactly one home, linked rather than duplicated?\n6. **Resolving Links**: Does `harness icm links .` pass with zero broken references?\n7. **Token Budget Under 8k**: Does contract + references + inputs remain strictly under 8,000 tokens?\n8. **Broken Invariants Explained**: If an invariant is broken on purpose, is the reason documented?\n\n> **Completion gate**: All 8 points of the cold walk test confirmed passing.\n\n---\n\n## 5. Artifact Finalization & Maintenance\n\nHarden and maintain the working ICM workspace:\n\n1. **Audit Compliance**:\n   - Run the comprehensive audit command:\n     ```bash\n     harness icm audit . --json\n     ```\n   - Assert all 10 mandatory invariants pass with zero error-severity violations.\n2. **Continuous Hardening**:\n   - Fold stages that no longer require human checks.\n   - Script checks that never fail to eliminate manual bottlenecks.\n   - Split contracts that grow beyond the 8,000 token ceiling.\n\n> **Completion gate**: Audit passes clean; workspace operational and documented.\n\n---\n\n## The Visual Brief Pillar\n\nEvery ICM design or restructuring session must generate an interactive, self-contained HTML visual brief:\n1. **Target File Location**: Write to `%TEMP%\\\\icm-architect-visual-brief-\u003Ctimestamp>.html` (Windows) or `\u002Ftmp\u002Ficm-architect-visual-brief-\u003Ctimestamp>.html` (Unix).\n2. **Visual Standards**: Dark theme (`#0d1117`), Tailwind CSS, and Mermaid.js via CDN. Display the 5-layer hierarchy DAG, the 4-axis repository matrix, and the 10 invariants scorecard.\n3. **Delivery**: Surface the clickable file path to the user before workspace mutation.\n\n---\n\n## Mandatory Checkpoint Pillar\n\nPrevent premature execution and unreviewed state mutations:\n1. Present draft `implementation_plan.md` detailing target form, folder hierarchy, contracts, and migration maps.\n2. Set `RequestFeedback: true` in artifact metadata.\n3. **STOP and wait** for explicit user review and approval before creating or modifying workspace files.\n\n---\n\n## Anti-Patterns\n\n- **Orchestration Code Sprawl** — Writing complex Python multi-agent orchestration frameworks where simple numbered folders and plain files suffice.\n- **Bloated Routing Catalogs** — Stuffing background explanations and domain essays into `AGENTS.md` instead of keeping it strictly under 60 lines.\n- **Unchecked Stage Handoffs** — Allowing pipeline execution to proceed without a verified human or automated `check.md` verdict.\n- **Context Flooding** — Loading the entire workspace context into agent prompts instead of scoping strictly to the current stage (\u003C8,000 tokens).\n- **Hand-Edited Indexes** — Manually maintaining record summaries in `_index.md` instead of generating them deterministically from frontmatter.\n- **Blind Restructuring** — Moving or deleting files in an existing codebase without mapping live external referrers first.\n- **Duplicated Reference Truths** — Copying style guides or schemas into every stage folder instead of referencing a single home in `_shared\u002F`.\n- **Untracked Case Collisions** — Renaming files to `CONTEXT.md` on case-insensitive filesystems without checking for existing `context.md` files.\n","# ICM Workspace Architect\n\n`icm-workspace-architect` is the production architecture engine for designing and restructuring workspaces where the folder structure executes agent orchestration. Rooted in the research of Van Clief & McDermott (*Interpretable Context Methodology: Folder Structure as Agent Architecture*, arXiv:2603.16021), ICM replaces complex multi-agent orchestration frameworks with five-layer context hierarchies, plain markdown contracts, and auditable stage checks.\n\nEvery ICM architecture cycle follows a five-stage progression:\n\n```\n[1. Scope & Form Selection] ──► [2. Hierarchy & Contracts] ──► [3. Verification Tooling]\n                                                                     │\n                                                                     ▼\n[5. Finalization & Maintenance] ◄── [4. 8-Point Cold Walk Test] ◄────┘\n```\n\nSee [CARD.md](CARD.md) for the companion summary card, form taxonomy, and invariants checklist.\nConsult `\u002Fcrafting-skills` for craft standards and `\u002Fagent-skill-sdlc` for lifecycle validation.\n\n---\n\n## The 10 Mandatory Invariants\n\n1. **One folder, one job** — Each folder performs a single step or holds a single kind of entity, declaring its purpose within itself.\n2. **Small, stable entry file** — `AGENTS.md` at root answers \"where am I, where does everything live, where do I go for task X\" in \u003C60 lines.\n3. **Numbering encodes order** — Numbered prefixes (`01_`, `02_`) sequence work where order matters.\n4. **Every working folder has a contract** — A `CONTEXT.md` defining Inputs, Process, Outputs, and Check.\n5. **Factory vs. product split** — Reference materials (`_shared\u002F`, schemas, voice) live apart from working artifacts (`output\u002F`, records).\n6. **Every step ends at a check** — Each stage output must pass a verified check (`check.md` with `pass` or `fail: \u003Cwhy>`) before downstream execution.\n7. **Load only what the step needs** — Step context (entry + contract + references + inputs) must stay under ~8,000 tokens.\n8. **Plain text, linkable, queryable** — Markdown + YAML frontmatter with relative links that always resolve.\n9. **Status lives on disk** — State is reflected directly in filesystem artifacts and generated `_index.md` files.\n10. **Instantiate by copying** — New work units are copies of templates from `_templates\u002F`, never blank pages.\n\n---\n\n## 1. Scope & Form Selection\n\nDetermine operational mode and select the matching ICM form from the 3 primitives (Sequence, Shelf, Catalog):\n\n1. **Select Operational Mode**:\n   - **Build Mode**: Start from an interview or process description. Identify pauses (stage boundaries), invariant rules (factory references), and deliverables.\n   - **Restructure Mode**: Take an existing messy folder or repository. Inventory files without moving, classify into 5 roles (`catalog`, `contract`, `factory`, `product`, `dead`), check live referrers, and propose a migration plan.\n2. **Select the Form**:\n   - **Pipeline**: Sequential production line with handoffs where stage $N$ output is stage $N+1$ input.\n   - **Record Library**: Uniform records accumulating status (`_index.md` generated from frontmatter).\n   - **Knowledge Bundle**: Linked concepts, claims, and raw sources with verbatim quote checks.\n   - **Context Map**: Organizational graph of teams and processes linked by `consumes:` \u002F `produces:`.\n   - **System Map**: Codebase audit hierarchy with nouns, verbs, and an impact index.\n\n> **Completion gate**: Mode selected, repeating unit identified, and candidate form confirmed.\n\n---\n\n## 2. Hierarchy & Contract Authoring\n\nScaffold the five-layer context hierarchy (L0–L4) and author stage contracts:\n\n1. **Scaffold L0 & L1 Catalogs**:\n   - Write root `AGENTS.md` (\u003C60 lines) defining identity, routing table, and rules.\n   - Author pointers: `CLAUDE.md` (`@AGENTS.md`) and `GEMINI.md` (`@.\u002FAGENTS.md`).\n   - Author root `CONTEXT.md` mapping the overall pipeline or shelf schema.\n2. **Author L2 Stage Contracts**:\n   - Every working stage receives a `CONTEXT.md`:\n     - `## Inputs`: Backticked exact paths partitioned into `Working (this run)` and `Reference (every run)`.\n     - Explicit `Do NOT load:` statement deflecting irrelevant folders.\n     - `## Process`: Numbered, deterministic instructions (commands named explicitly).\n     - `## Outputs`: Specific file paths in `output\u002F`.\n     - `## Check`: Concrete check by person, script, or small model emitting `check.md`.\n3. **Scaffold L3 Factory & Templates**:\n   - Stable reference material in `_shared\u002Fvoice.md` or `_meta\u002Fschema.md`.\n   - Stamp templates in `_templates\u002F`.\n\n> **Completion gate**: L0–L4 hierarchy scaffolded; contracts carry inputs, process, outputs, and checks.\n\n---\n\n## 3. Verification & Guardrail Tooling\n\nDeploy deterministic standard-library verification scripts into the workspace's `_tools\u002F` or execute via Harness CLI:\n\n1. **Link & Input Verification (`icm_links.py`)**:\n   - Verify that every markdown link, frontmatter `.md` path, pointer import, and backticked contract input resolves cleanly:\n     ```bash\n     harness icm links .\n     ```\n2. **Frontmatter Index Generation (`icm_index.py`)**:\n   - Rebuild `_index.md` files across record folders from frontmatter metadata without hand-editing:\n     ```bash\n     harness icm index records\n     ```\n3. **Quote & Provenance Verification (`icm_quotes.py`)**:\n   - For knowledge bundles, verify verbatim quote matches against `sources\u002Fraw\u002F` and enforce `_meta\u002Fkeep-out.txt`:\n     ```bash\n     harness icm quotes .\n     ```\n\n> **Completion gate**: Verification scripts installed in `_tools\u002F` or CLI verified; zero broken links.\n\n---\n\n## 4. The 8-Point Cold Walk Test\n\nWalk the workspace cold as an agent with zero memory to ensure interpretability:\n\n1. **Where am I**: Can the agent answer its task location within `AGENTS.md` plus at most 2 reads?\n2. **Exact Inputs**: Does the active stage contract list exact, verifiable input paths?\n3. **Pure Disk Status**: Can system status be determined entirely from disk files and `check.md` verdicts?\n4. **No Content in Catalog**: Are routing files (`AGENTS.md`, `CONTEXT.md`) free of content payloads?\n5. **Single Source of Truth**: Does each fact live in exactly one home, linked rather than duplicated?\n6. **Resolving Links**: Does `harness icm links .` pass with zero broken references?\n7. **Token Budget Under 8k**: Does contract + references + inputs remain strictly under 8,000 tokens?\n8. **Broken Invariants Explained**: If an invariant is broken on purpose, is the reason documented?\n\n> **Completion gate**: All 8 points of the cold walk test confirmed passing.\n\n---\n\n## 5. Artifact Finalization & Maintenance\n\nHarden and maintain the working ICM workspace:\n\n1. **Audit Compliance**:\n   - Run the comprehensive audit command:\n     ```bash\n     harness icm audit . --json\n     ```\n   - Assert all 10 mandatory invariants pass with zero error-severity violations.\n2. **Continuous Hardening**:\n   - Fold stages that no longer require human checks.\n   - Script checks that never fail to eliminate manual bottlenecks.\n   - Split contracts that grow beyond the 8,000 token ceiling.\n\n> **Completion gate**: Audit passes clean; workspace operational and documented.\n\n---\n\n## The Visual Brief Pillar\n\nEvery ICM design or restructuring session must generate an interactive, self-contained HTML visual brief:\n1. **Target File Location**: Write to `%TEMP%\\\\icm-architect-visual-brief-\u003Ctimestamp>.html` (Windows) or `\u002Ftmp\u002Ficm-architect-visual-brief-\u003Ctimestamp>.html` (Unix).\n2. **Visual Standards**: Dark theme (`#0d1117`), Tailwind CSS, and Mermaid.js via CDN. Display the 5-layer hierarchy DAG, the 4-axis repository matrix, and the 10 invariants scorecard.\n3. **Delivery**: Surface the clickable file path to the user before workspace mutation.\n\n---\n\n## Mandatory Checkpoint Pillar\n\nPrevent premature execution and unreviewed state mutations:\n1. Present draft `implementation_plan.md` detailing target form, folder hierarchy, contracts, and migration maps.\n2. Set `RequestFeedback: true` in artifact metadata.\n3. **STOP and wait** for explicit user review and approval before creating or modifying workspace files.\n\n---\n\n## Anti-Patterns\n\n- **Orchestration Code Sprawl** — Writing complex Python multi-agent orchestration frameworks where simple numbered folders and plain files suffice.\n- **Bloated Routing Catalogs** — Stuffing background explanations and domain essays into `AGENTS.md` instead of keeping it strictly under 60 lines.\n- **Unchecked Stage Handoffs** — Allowing pipeline execution to proceed without a verified human or automated `check.md` verdict.\n- **Context Flooding** — Loading the entire workspace context into agent prompts instead of scoping strictly to the current stage (\u003C8,000 tokens).\n- **Hand-Edited Indexes** — Manually maintaining record summaries in `_index.md` instead of generating them deterministically from frontmatter.\n- **Blind Restructuring** — Moving or deleting files in an existing codebase without mapping live external referrers first.\n- **Duplicated Reference Truths** — Copying style guides or schemas into every stage folder instead of referencing a single home in `_shared\u002F`.\n- **Untracked Case Collisions** — Renaming files to `CONTEXT.md` on case-insensitive filesystems without checking for existing `context.md` files.\n",{"name":5,"description":7},"main","eff3b00e36d1d233ad4a4389605c82fbfa0326d3",".agents\u002Fskills\u002Ficm-workspace-architect","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 icm-workspace-architect",{"tool":37,"command":38},"bunx","bunx skills add SpectreDeath\u002FBrain-Harness --skill icm-workspace-architect",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SpectreDeath\u002FBrain-Harness --skill icm-workspace-architect","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ficm-workspace-architect\u002FSKILL.md",true,[45,51,55,61,65,69],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"CARD.md","REFERENCE","参考文档",3484,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ficm-workspace-architect\u002FCARD.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"config.default.yaml",667,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ficm-workspace-architect\u002Fconfig.default.yaml",{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"scripts\u002Ficm_index.py","SCRIPT","脚本",1508,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ficm-workspace-architect\u002Fscripts\u002Ficm_index.py",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"scripts\u002Ficm_links.py",2000,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ficm-workspace-architect\u002Fscripts\u002Ficm_links.py",{"path":66,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":67,"sourceHtmlUrl":68},"scripts\u002Ficm_quotes.py",2160,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ficm-workspace-architect\u002Fscripts\u002Ficm_quotes.py",{"path":70,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Ficm_viz.py",2978,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ficm-workspace-architect\u002Fscripts\u002Ficm_viz.py",[74,81,88,95,102,109],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"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":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"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",[],[]]