[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AW2NP5DNB2S08MS23DMYK7":3,"skill-same:01M7AW2NP5DNB2S08MS23DMYK7":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},"01M7AW2NP5DNB2S08MS23DMYK7","sme-ann-backprop",null,"Formulate and execute Agentic Neural Network (ANN) textual backpropagation, momentum-smoothed updates, and 4-stage candidate validation to optimize multi-agent DAGs. Do not use for simple linear scripts or deterministic bugs.","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\u002Fsme-ann-backprop\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sme-ann-backprop\ndescription: Formulate and execute Agentic Neural Network (ANN) textual backpropagation, momentum-smoothed updates, and 4-stage candidate validation to optimize multi-agent DAGs. Do not use for simple linear scripts or deterministic bugs.\n---\n\n# SME ANN Backprop & Self-Evolving Workflow Engine\n\n`sme-ann-backprop` operationalizes Agentic Neural Network ($\\mathcal{ANN}$) textual backpropagation and candidate pool governance for Brain Harness. Distilled from the **SME Forensic Gateway (Lawnmower Man v3.0.1)**, it treats multi-agent workflow DAGs as layered networks where execution errors are backpropagated as structured textual gradients ($\\nabla_{\\text{text}}$), smoothed via momentum velocity buffers, and gated through a 4-stage validation filter before persistent pool insertion.\n\nEvery ANN self-optimization cycle follows a strict five-stage progression:\n\n```\n[1. Trajectory Analysis & Global Loss] → [2. Layerwise Local Gradients] → [3. Momentum Velocity Smoothing] → [4. 4-Stage Candidate Validation] → [5. Candidate Pool Commit & Routing]\n```\n\nSee [CARD.md](CARD.md) for the companion summary card, backpropagation formulas, and verification invariants.\nConsult `\u002Fcrafting-skills` for skill craft standards, `\u002Fdata-topology-mapper` for DAG blast radius mapping, and `\u002Fdeep-repo-auditor` for repository distillation.\n\n---\n\n## 1. Trajectory Analysis & Global Textual Loss ($G_{\\text{global}}$)\n\nInspect the execution transcript of a multi-agent or multi-step workflow to compute the global loss signal:\n\n1. **Loss Quantification**:\n   - Compute bounded loss score:\n     $$\\text{Loss}_{\\text{global}} = \\frac{\\text{Number of Failed Steps \u002F Layers}}{\\text{Total Trajectory Steps}} \\in [0.0, 1.0]$$\n2. **Layer Failure Localization**:\n   - Extract the specific layer indices $\\ell \\in [0, N-1]$ that raised exceptions, returned error observation payloads, or failed schema validation.\n3. **Inter-Layer Structural Suggestions**:\n   - Generate high-level routing suggestions and input rewiring instructions to isolate failed dependencies.\n\n> **Completion criterion**: `GlobalGradient` object emitted with verified loss score, failed layer indices, and structural recommendations.\n\n---\n\n## 2. Layerwise Local Textual Gradients ($G_{\\text{local},\\ell}$)\n\nFormulate local layerwise gradients for each active agent team block $f_{\\ell}$:\n\n1. **Combined Loss Computation**:\n   - Balance global trajectory feedback with local step outcome using mixing parameter $\\beta = 0.5$:\n     $$\\text{Loss}_{\\text{combined}} = \\beta \\cdot \\text{Loss}_{\\text{global}} + (1 - \\beta) \\cdot \\text{Loss}_{\\text{local}}$$\n2. **Node Prompt Refinement**:\n   - For failed nodes: Append explicit output schema constraints, parameter validation checks, and error-handling directives.\n   - For successful nodes: Optimize for conciseness and logical consistency.\n3. **Validator Node Insertion**:\n   - If structural gaps caused execution failure, insert downstream validation nodes (e.g. `node_validator` with static analysis or schema check roles).\n\n> **Completion criterion**: `LocalGradient` synthesized for each affected layer with prompt suggestions and node\u002Fedge updates.\n\n---\n\n## 3. Momentum Velocity Smoothing (`MomentumBuffer`)\n\nSmooth prompt and topological updates across iterations to eliminate oscillation:\n\n1. **Update Velocity Tracking**:\n   - Maintain historical gradient velocity per layer index $\\ell$:\n     $$G'_{t,\\ell} = \\alpha \\cdot G_{t,\\ell} + (1 - \\alpha) \\cdot G_{t-1,\\ell} \\quad (\\alpha = 0.7)$$\n2. **Prompt Merge & Stabilization**:\n   - Merge previous prompt improvements with incoming suggestions to prevent catastrophic forgetting of validated instructions.\n\n> **Completion criterion**: Momentum-smoothed local gradient $G'_{t,\\ell}$ produced.\n\n---\n\n## 4. 4-Stage Candidate Validation Filter\n\nGate candidate agent blocks ($f'_{\\ell}$) through 4 rigorous verification stages before pool insertion:\n\n1. **Stage 1 (Node Validation)**:\n   - Ensure all nodes declare valid agent identifiers, non-empty role prompts, and required capabilities.\n2. **Stage 2 (Edge Validation)**:\n   - Ensure all directed edges connect valid existing vertices; reject dangling links.\n3. **Stage 3 (Structural Acyclicity & Deduplication)**:\n   - Run cycle detection to guarantee strictly acyclic DAG execution.\n   - Verify candidate structure is unique and not already present in the existing pool.\n4. **Stage 4 (Performance Baseline)**:\n   - Confirm projected candidate loss is $\\le$ baseline performance threshold.\n\n> **Completion criterion**: 4-stage filter returns `is_valid: true`. If invalid, failure reason and rejected stage are reported.\n\n---\n\n## 5. Candidate Pool Commit & Dynamic Selection\n\nPersist validated candidate team blocks into SQLite WAL candidate pools:\n\n1. **Atomic Insertion**:\n   - Insert validated block into `candidate_pools` table ($F_{\\ell}$) with unique `block_id`, `layer_index`, `loss_score`, and JSON schema payload.\n2. **Dynamic $O(1)$ Team Selection**:\n   - Select candidate team block minimizing loss score or matching specific task context tags during runtime execution.\n\n> **Completion criterion**: Candidate block saved to SQLite WAL storage and ready for dynamic routing.\n\n---\n\n## In-File Reference & Formulas\n\n- **Global Loss**: $\\text{Loss}_{\\text{global}} = \\frac{|\\text{Failed Layers}|}{|\\text{Total Steps}|}$\n- **Combined Layer Loss**: $\\text{Loss}_{\\text{combined}} = \\beta \\cdot \\text{Loss}_{\\text{global}} + (1 - \\beta) \\cdot \\text{Loss}_{\\text{local}}$\n- **Momentum Smoothing**: $G'_{t} = \\alpha G_{t} + (1 - \\alpha) G_{t-1}$ where $\\alpha = 0.7$\n- **Candidate Pool**: $F_{\\ell} = \\{ f_{1}, f_{2}, \\dots, f_{k} \\}$ persisted in SQLite WAL `laboratory.db`\n\n---\n\n## The Three Foundational Pillars\n\n### 1. The Visual Brief\nSynthesize findings, structural matrices, and execution DAGs into a self-contained HTML visual brief written to `%TEMP%\\sme-ann-backprop-\u003Ctimestamp>.html` (or `\u002Ftmp\u002Fsme-ann-backprop-\u003Ctimestamp>.html` on Unix) loading Tailwind CSS and Mermaid.js via CDN. Present the absolute clickable path to the user for visual review.\n\n### 2. The Mandatory Checkpoint\nWhen proposing structural modifications, refactors, or execution pipelines, always author an `implementation_plan.md` artifact with `RequestFeedback: true`. The agent must **STOP and wait** for explicit human confirmation before executing mutating actions.\n\n### 3. Explicit Anti-Patterns\nRigid behavioral boundaries must be maintained to prevent catastrophic failure modes.\n\n---\n\n## Anti-Patterns\n\n- **Oscillatory Prompt Churn** — Applying raw gradient updates without momentum smoothing, causing prompts to thrash between conflicting instructions.\n- **Ungated Pool Pollution** — Committing candidate agent blocks without running the 4-stage validation filter.\n- **Circular Execution Deadlocks** — Allowing edge mutations that introduce cycles into agent execution DAGs.\n- **Unbounded Loss Metrics** — Using non-normalized loss scales instead of strictly bounded $[0.0, 1.0]$ loss metrics.\n","# SME ANN Backprop & Self-Evolving Workflow Engine\n\n`sme-ann-backprop` operationalizes Agentic Neural Network ($\\mathcal{ANN}$) textual backpropagation and candidate pool governance for Brain Harness. Distilled from the **SME Forensic Gateway (Lawnmower Man v3.0.1)**, it treats multi-agent workflow DAGs as layered networks where execution errors are backpropagated as structured textual gradients ($\\nabla_{\\text{text}}$), smoothed via momentum velocity buffers, and gated through a 4-stage validation filter before persistent pool insertion.\n\nEvery ANN self-optimization cycle follows a strict five-stage progression:\n\n```\n[1. Trajectory Analysis & Global Loss] → [2. Layerwise Local Gradients] → [3. Momentum Velocity Smoothing] → [4. 4-Stage Candidate Validation] → [5. Candidate Pool Commit & Routing]\n```\n\nSee [CARD.md](CARD.md) for the companion summary card, backpropagation formulas, and verification invariants.\nConsult `\u002Fcrafting-skills` for skill craft standards, `\u002Fdata-topology-mapper` for DAG blast radius mapping, and `\u002Fdeep-repo-auditor` for repository distillation.\n\n---\n\n## 1. Trajectory Analysis & Global Textual Loss ($G_{\\text{global}}$)\n\nInspect the execution transcript of a multi-agent or multi-step workflow to compute the global loss signal:\n\n1. **Loss Quantification**:\n   - Compute bounded loss score:\n     $$\\text{Loss}_{\\text{global}} = \\frac{\\text{Number of Failed Steps \u002F Layers}}{\\text{Total Trajectory Steps}} \\in [0.0, 1.0]$$\n2. **Layer Failure Localization**:\n   - Extract the specific layer indices $\\ell \\in [0, N-1]$ that raised exceptions, returned error observation payloads, or failed schema validation.\n3. **Inter-Layer Structural Suggestions**:\n   - Generate high-level routing suggestions and input rewiring instructions to isolate failed dependencies.\n\n> **Completion criterion**: `GlobalGradient` object emitted with verified loss score, failed layer indices, and structural recommendations.\n\n---\n\n## 2. Layerwise Local Textual Gradients ($G_{\\text{local},\\ell}$)\n\nFormulate local layerwise gradients for each active agent team block $f_{\\ell}$:\n\n1. **Combined Loss Computation**:\n   - Balance global trajectory feedback with local step outcome using mixing parameter $\\beta = 0.5$:\n     $$\\text{Loss}_{\\text{combined}} = \\beta \\cdot \\text{Loss}_{\\text{global}} + (1 - \\beta) \\cdot \\text{Loss}_{\\text{local}}$$\n2. **Node Prompt Refinement**:\n   - For failed nodes: Append explicit output schema constraints, parameter validation checks, and error-handling directives.\n   - For successful nodes: Optimize for conciseness and logical consistency.\n3. **Validator Node Insertion**:\n   - If structural gaps caused execution failure, insert downstream validation nodes (e.g. `node_validator` with static analysis or schema check roles).\n\n> **Completion criterion**: `LocalGradient` synthesized for each affected layer with prompt suggestions and node\u002Fedge updates.\n\n---\n\n## 3. Momentum Velocity Smoothing (`MomentumBuffer`)\n\nSmooth prompt and topological updates across iterations to eliminate oscillation:\n\n1. **Update Velocity Tracking**:\n   - Maintain historical gradient velocity per layer index $\\ell$:\n     $$G'_{t,\\ell} = \\alpha \\cdot G_{t,\\ell} + (1 - \\alpha) \\cdot G_{t-1,\\ell} \\quad (\\alpha = 0.7)$$\n2. **Prompt Merge & Stabilization**:\n   - Merge previous prompt improvements with incoming suggestions to prevent catastrophic forgetting of validated instructions.\n\n> **Completion criterion**: Momentum-smoothed local gradient $G'_{t,\\ell}$ produced.\n\n---\n\n## 4. 4-Stage Candidate Validation Filter\n\nGate candidate agent blocks ($f'_{\\ell}$) through 4 rigorous verification stages before pool insertion:\n\n1. **Stage 1 (Node Validation)**:\n   - Ensure all nodes declare valid agent identifiers, non-empty role prompts, and required capabilities.\n2. **Stage 2 (Edge Validation)**:\n   - Ensure all directed edges connect valid existing vertices; reject dangling links.\n3. **Stage 3 (Structural Acyclicity & Deduplication)**:\n   - Run cycle detection to guarantee strictly acyclic DAG execution.\n   - Verify candidate structure is unique and not already present in the existing pool.\n4. **Stage 4 (Performance Baseline)**:\n   - Confirm projected candidate loss is $\\le$ baseline performance threshold.\n\n> **Completion criterion**: 4-stage filter returns `is_valid: true`. If invalid, failure reason and rejected stage are reported.\n\n---\n\n## 5. Candidate Pool Commit & Dynamic Selection\n\nPersist validated candidate team blocks into SQLite WAL candidate pools:\n\n1. **Atomic Insertion**:\n   - Insert validated block into `candidate_pools` table ($F_{\\ell}$) with unique `block_id`, `layer_index`, `loss_score`, and JSON schema payload.\n2. **Dynamic $O(1)$ Team Selection**:\n   - Select candidate team block minimizing loss score or matching specific task context tags during runtime execution.\n\n> **Completion criterion**: Candidate block saved to SQLite WAL storage and ready for dynamic routing.\n\n---\n\n## In-File Reference & Formulas\n\n- **Global Loss**: $\\text{Loss}_{\\text{global}} = \\frac{|\\text{Failed Layers}|}{|\\text{Total Steps}|}$\n- **Combined Layer Loss**: $\\text{Loss}_{\\text{combined}} = \\beta \\cdot \\text{Loss}_{\\text{global}} + (1 - \\beta) \\cdot \\text{Loss}_{\\text{local}}$\n- **Momentum Smoothing**: $G'_{t} = \\alpha G_{t} + (1 - \\alpha) G_{t-1}$ where $\\alpha = 0.7$\n- **Candidate Pool**: $F_{\\ell} = \\{ f_{1}, f_{2}, \\dots, f_{k} \\}$ persisted in SQLite WAL `laboratory.db`\n\n---\n\n## The Three Foundational Pillars\n\n### 1. The Visual Brief\nSynthesize findings, structural matrices, and execution DAGs into a self-contained HTML visual brief written to `%TEMP%\\sme-ann-backprop-\u003Ctimestamp>.html` (or `\u002Ftmp\u002Fsme-ann-backprop-\u003Ctimestamp>.html` on Unix) loading Tailwind CSS and Mermaid.js via CDN. Present the absolute clickable path to the user for visual review.\n\n### 2. The Mandatory Checkpoint\nWhen proposing structural modifications, refactors, or execution pipelines, always author an `implementation_plan.md` artifact with `RequestFeedback: true`. The agent must **STOP and wait** for explicit human confirmation before executing mutating actions.\n\n### 3. Explicit Anti-Patterns\nRigid behavioral boundaries must be maintained to prevent catastrophic failure modes.\n\n---\n\n## Anti-Patterns\n\n- **Oscillatory Prompt Churn** — Applying raw gradient updates without momentum smoothing, causing prompts to thrash between conflicting instructions.\n- **Ungated Pool Pollution** — Committing candidate agent blocks without running the 4-stage validation filter.\n- **Circular Execution Deadlocks** — Allowing edge mutations that introduce cycles into agent execution DAGs.\n- **Unbounded Loss Metrics** — Using non-normalized loss scales instead of strictly bounded $[0.0, 1.0]$ loss metrics.\n",{"name":5,"description":7},"main","eff3b00e36d1d233ad4a4389605c82fbfa0326d3",".agents\u002Fskills\u002Fsme-ann-backprop","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 sme-ann-backprop",{"tool":37,"command":38},"bunx","bunx skills add SpectreDeath\u002FBrain-Harness --skill sme-ann-backprop",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SpectreDeath\u002FBrain-Harness --skill sme-ann-backprop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsme-ann-backprop\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"CARD.md","REFERENCE","参考文档",3249,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsme-ann-backprop\u002FCARD.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"config.default.yaml",292,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsme-ann-backprop\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",[],[]]