[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AVRSSJQ9FTWK01646Z98MW":3,"skill-same:01M7AVRSSJQ9FTWK01646Z98MW":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},"01M7AVRSSJQ9FTWK01646Z98MW","epistemic-isnad-audit",null,"Verify unbroken chain-of-custody lineage for facts, dependencies, and architectural decisions before writing to persistent state or memory. Do not use for unverified hearsay or speculative knowledge commits.","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\u002Fepistemic-isnad-audit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: epistemic-isnad-audit\ndescription: Verify unbroken chain-of-custody lineage for facts, dependencies, and architectural decisions before writing to persistent state or memory. Do not use for unverified hearsay or speculative knowledge commits.\n---\n\n# Epistemic Isnad Audit Engine\n\nThe `epistemic-isnad-audit` engine operationalizes the classical Islamic *Isnad* (chain of custody) methodology combined with Neo-Confucian *Empty Mind* extraction. It mandates cryptographic-grade traceability for all factual assertions, ensuring no hallucinated, unanchored, or speculative claims enter long-term architectural records (`.context\u002Fdecisions.md`, memory engines, or kernel manifests).\n\nEvery isnad audit follows a strict five-stage progression:\n\n```\n[1. Pure Extraction (Empty Mind)] → [2. Isnad Lineage Tracing] → [3. Visual Lineage Brief (Temp HTML)] → [4. Verification Checkpoint] → [5. Structured Isnad Commit]\n```\n\nSee [CARD.md](CARD.md) for the quick-reference summary card, lineage schemas, and completion criteria.\nConsult `\u002Fcrafting-skills` for the underlying design standard and three foundational pillars.\n\n---\n\n## 1. Pure Extraction (Zhu Xi Empty Mind)\n\nIsolate and extract factual assertions from raw context without adding evaluative judgments, speculative inferences, or confirmation bias:\n\n1. **Raw Claim Segmentation**: Deconstruct candidate proposals into atomic factual propositions (e.g., \"Module X imports Module Y\", \"Service key Z requires generic type T\").\n2. **Suspension of Evaluation**: Record each statement in its raw descriptive state prior to synthesis or critique.\n3. **Extraction Table**: Produce an unannotated claim inventory.\n\n> **Completion criterion**: Discrete list of atomic claims extracted with zero interpretive commentary.\n\n---\n\n## 2. Isnad Lineage Tracing (Chain of Custody Resolution)\n\nMap every extracted claim to an unbroken chain of custody terminating at a primary workspace node:\n\n1. **Lineage Node Types**:\n   - **Primary Code Source**: Exact file path and line slice (`[service.py:L40-L65](file:\u002F\u002F\u002Fd:\u002Fpath\u002Fto\u002Fservice.py#L40-L65)`).\n   - **Tool Execution**: Deterministic command \u002F tool result (`run_command` output, `pytest` exit code).\n   - **Declarative Manifest**: Grounded schema file (`pyproject.toml`, `plugin.json`).\n2. **Lineage Audit Table**:\n   ```markdown\n   | Claim ID | Proposition | Primary Source \u002F Tool Event | Lineage Status |\n   | :--- | :--- | :--- | :--- |\n   | `C-101` | ServiceKey requires generic parameter | `src\u002Fharness\u002Fkernel\u002Fservice.py#L12-L30` | `VERIFIED` |\n   | `C-102` | Subprocess isolation is enabled by default | `src\u002Fharness\u002Fplugins\u002Floader.py#L88-L104` | `VERIFIED` |\n   | `C-103` | Memory engine auto-indexes on startup | `None (Inferred)` | `HYPOTHESIS [UNVERIFIED]` |\n   ```\n3. **Ungrounded Claim Isolation**: Any claim without a direct primary node is strictly labeled `HYPOTHESIS [UNVERIFIED]`.\n\n> **Completion criterion**: 100% of claims classified as either `VERIFIED` with file URIs or `HYPOTHESIS [UNVERIFIED]`.\n\n---\n\n## 3. The Visual Lineage Brief\n\nSynthesize the audited claims and their provenance trees into an interactive HTML report:\n\n1. **Target Path**: Write to `%TEMP%\\isnad-audit-\u003Ctimestamp>.html` (Windows) or `\u002Ftmp\u002Fisnad-audit-\u003Ctimestamp>.html` (Unix).\n2. **Visual Standards**:\n   - Load Tailwind CSS and Mermaid.js via CDN in a sleek dark theme (`#0d1117`).\n   - Render a Mermaid **Lineage DAG** mapping assertions back to file sources and test receipts.\n   - Highlight unverified hypotheses in warning yellow (`#d29922`) and verified nodes in green (`#238636`).\n3. **Surface**: Deliver the absolute, clickable HTML file path to the user.\n\n```html\n\u003C!-- Location: %TEMP%\\isnad-audit-\u003Ctimestamp>.html -->\n\u003C!DOCTYPE html>\n\u003Chtml lang=\"en\">\n\u003Chead>\n  \u003Cmeta charset=\"UTF-8\">\n  \u003Ctitle>Isnad Epistemic Audit Brief\u003C\u002Ftitle>\n  \u003Cscript src=\"https:\u002F\u002Fcdn.tailwindcss.com\">\u003C\u002Fscript>\n  \u003Cscript src=\"https:\u002F\u002Fcdn.jsdelivr.net\u002Fnpm\u002Fmermaid@10\u002Fdist\u002Fmermaid.min.js\">\u003C\u002Fscript>\n  \u003Cscript>mermaid.initialize({startOnLoad:true, theme:'dark'});\u003C\u002Fscript>\n\u003C\u002Fhead>\n\u003Cbody class=\"bg-[#0d1117] text-[#c9d1d9] p-8 max-w-6xl mx-auto font-sans\">\n  \u003Cheader class=\"border-b border-[#30363d] pb-4 mb-6\">\n    \u003Ch1 class=\"text-2xl font-bold text-white\">Epistemic Isnad Chain of Custody\u003C\u002Fh1>\n    \u003Cp class=\"text-sm text-gray-400 mt-1\">Provable Provenance & Factual Lineage Graph\u003C\u002Fp>\n  \u003C\u002Fheader>\n  \u003C!-- Interactive Lineage DAG and Audit Matrix -->\n\u003C\u002Fbody>\n\u003C\u002Fhtml>\n```\n\n> **Completion criterion**: Self-contained HTML report written to `%TEMP%` and delivered to user.\n\n---\n\n## 4. Verification Checkpoint (Grounding Resolution)\n\nResolve unverified hypotheses before allowing state mutation:\n\n1. For each `HYPOTHESIS [UNVERIFIED]`, execute targeted inspection tools (`view_file`, `grep_search`, `run_command`).\n2. If confirmed, promote to `VERIFIED` with exact file\u002Fline links.\n3. If ungrounded or contradicted, discard the claim from the decision set.\n4. Set `RequestFeedback: true` in the `implementation_plan.md` artifact and pause for user review.\n\n> **Completion criterion**: Zero unverified hypotheses remaining in the active plan; user approval received.\n\n---\n\n## 5. Structured Isnad Commit\n\nEmit the verified decision record with its complete provenance block to `.context\u002Fdecisions.md` or persistent memory:\n\n```markdown\n## Decision: [Decision Title]\n\n- **Timestamp**: YYYY-MM-DDTHH:MM:SSZ\n- **Status**: ACCEPTED\n- **Summary**: Concise description of verified architectural decision.\n\n### Isnad Lineage Block\n```json\n{\n  \"decision_id\": \"dec_20260819_01\",\n  \"claims\": [\n    {\n      \"assertion\": \"Service registration requires generic ServiceKey[T]\",\n      \"lineage\": [\n        {\"node\": \"primary_code\", \"uri\": \"file:\u002F\u002F\u002Fsrc\u002Fharness\u002Fkernel\u002Fservice.py#L42-L68\"},\n        {\"node\": \"verification_test\", \"uri\": \"file:\u002F\u002F\u002Ftests\u002Fkernel\u002Ftest_service.py#L15-L35\"}\n      ]\n    }\n  ]\n}\n```\n```\n\n> **Completion criterion**: Structured Isnad record written to persistent store with 100% verified links.\n\n---\n\n## Anti-Patterns\n\n- **Floating Assertions** — Stating facts or architectural guarantees without citing concrete source lines or tool outputs.\n- **Inference Conflation** — Treating logical inferences or plausible assumptions as established ground truth.\n- **Stale Lineage Pointers** — Citing out-of-date line ranges without verifying against the current workspace state.\n- **Unanchored Memory Commits** — Writing unverified decisions into persistent memory or documentation.\n","# Epistemic Isnad Audit Engine\n\nThe `epistemic-isnad-audit` engine operationalizes the classical Islamic *Isnad* (chain of custody) methodology combined with Neo-Confucian *Empty Mind* extraction. It mandates cryptographic-grade traceability for all factual assertions, ensuring no hallucinated, unanchored, or speculative claims enter long-term architectural records (`.context\u002Fdecisions.md`, memory engines, or kernel manifests).\n\nEvery isnad audit follows a strict five-stage progression:\n\n```\n[1. Pure Extraction (Empty Mind)] → [2. Isnad Lineage Tracing] → [3. Visual Lineage Brief (Temp HTML)] → [4. Verification Checkpoint] → [5. Structured Isnad Commit]\n```\n\nSee [CARD.md](CARD.md) for the quick-reference summary card, lineage schemas, and completion criteria.\nConsult `\u002Fcrafting-skills` for the underlying design standard and three foundational pillars.\n\n---\n\n## 1. Pure Extraction (Zhu Xi Empty Mind)\n\nIsolate and extract factual assertions from raw context without adding evaluative judgments, speculative inferences, or confirmation bias:\n\n1. **Raw Claim Segmentation**: Deconstruct candidate proposals into atomic factual propositions (e.g., \"Module X imports Module Y\", \"Service key Z requires generic type T\").\n2. **Suspension of Evaluation**: Record each statement in its raw descriptive state prior to synthesis or critique.\n3. **Extraction Table**: Produce an unannotated claim inventory.\n\n> **Completion criterion**: Discrete list of atomic claims extracted with zero interpretive commentary.\n\n---\n\n## 2. Isnad Lineage Tracing (Chain of Custody Resolution)\n\nMap every extracted claim to an unbroken chain of custody terminating at a primary workspace node:\n\n1. **Lineage Node Types**:\n   - **Primary Code Source**: Exact file path and line slice (`[service.py:L40-L65](file:\u002F\u002F\u002Fd:\u002Fpath\u002Fto\u002Fservice.py#L40-L65)`).\n   - **Tool Execution**: Deterministic command \u002F tool result (`run_command` output, `pytest` exit code).\n   - **Declarative Manifest**: Grounded schema file (`pyproject.toml`, `plugin.json`).\n2. **Lineage Audit Table**:\n   ```markdown\n   | Claim ID | Proposition | Primary Source \u002F Tool Event | Lineage Status |\n   | :--- | :--- | :--- | :--- |\n   | `C-101` | ServiceKey requires generic parameter | `src\u002Fharness\u002Fkernel\u002Fservice.py#L12-L30` | `VERIFIED` |\n   | `C-102` | Subprocess isolation is enabled by default | `src\u002Fharness\u002Fplugins\u002Floader.py#L88-L104` | `VERIFIED` |\n   | `C-103` | Memory engine auto-indexes on startup | `None (Inferred)` | `HYPOTHESIS [UNVERIFIED]` |\n   ```\n3. **Ungrounded Claim Isolation**: Any claim without a direct primary node is strictly labeled `HYPOTHESIS [UNVERIFIED]`.\n\n> **Completion criterion**: 100% of claims classified as either `VERIFIED` with file URIs or `HYPOTHESIS [UNVERIFIED]`.\n\n---\n\n## 3. The Visual Lineage Brief\n\nSynthesize the audited claims and their provenance trees into an interactive HTML report:\n\n1. **Target Path**: Write to `%TEMP%\\isnad-audit-\u003Ctimestamp>.html` (Windows) or `\u002Ftmp\u002Fisnad-audit-\u003Ctimestamp>.html` (Unix).\n2. **Visual Standards**:\n   - Load Tailwind CSS and Mermaid.js via CDN in a sleek dark theme (`#0d1117`).\n   - Render a Mermaid **Lineage DAG** mapping assertions back to file sources and test receipts.\n   - Highlight unverified hypotheses in warning yellow (`#d29922`) and verified nodes in green (`#238636`).\n3. **Surface**: Deliver the absolute, clickable HTML file path to the user.\n\n```html\n\u003C!-- Location: %TEMP%\\isnad-audit-\u003Ctimestamp>.html -->\n\u003C!DOCTYPE html>\n\u003Chtml lang=\"en\">\n\u003Chead>\n  \u003Cmeta charset=\"UTF-8\">\n  \u003Ctitle>Isnad Epistemic Audit Brief\u003C\u002Ftitle>\n  \u003Cscript src=\"https:\u002F\u002Fcdn.tailwindcss.com\">\u003C\u002Fscript>\n  \u003Cscript src=\"https:\u002F\u002Fcdn.jsdelivr.net\u002Fnpm\u002Fmermaid@10\u002Fdist\u002Fmermaid.min.js\">\u003C\u002Fscript>\n  \u003Cscript>mermaid.initialize({startOnLoad:true, theme:'dark'});\u003C\u002Fscript>\n\u003C\u002Fhead>\n\u003Cbody class=\"bg-[#0d1117] text-[#c9d1d9] p-8 max-w-6xl mx-auto font-sans\">\n  \u003Cheader class=\"border-b border-[#30363d] pb-4 mb-6\">\n    \u003Ch1 class=\"text-2xl font-bold text-white\">Epistemic Isnad Chain of Custody\u003C\u002Fh1>\n    \u003Cp class=\"text-sm text-gray-400 mt-1\">Provable Provenance & Factual Lineage Graph\u003C\u002Fp>\n  \u003C\u002Fheader>\n  \u003C!-- Interactive Lineage DAG and Audit Matrix -->\n\u003C\u002Fbody>\n\u003C\u002Fhtml>\n```\n\n> **Completion criterion**: Self-contained HTML report written to `%TEMP%` and delivered to user.\n\n---\n\n## 4. Verification Checkpoint (Grounding Resolution)\n\nResolve unverified hypotheses before allowing state mutation:\n\n1. For each `HYPOTHESIS [UNVERIFIED]`, execute targeted inspection tools (`view_file`, `grep_search`, `run_command`).\n2. If confirmed, promote to `VERIFIED` with exact file\u002Fline links.\n3. If ungrounded or contradicted, discard the claim from the decision set.\n4. Set `RequestFeedback: true` in the `implementation_plan.md` artifact and pause for user review.\n\n> **Completion criterion**: Zero unverified hypotheses remaining in the active plan; user approval received.\n\n---\n\n## 5. Structured Isnad Commit\n\nEmit the verified decision record with its complete provenance block to `.context\u002Fdecisions.md` or persistent memory:\n\n```markdown\n## Decision: [Decision Title]\n\n- **Timestamp**: YYYY-MM-DDTHH:MM:SSZ\n- **Status**: ACCEPTED\n- **Summary**: Concise description of verified architectural decision.\n\n### Isnad Lineage Block\n```json\n{\n  \"decision_id\": \"dec_20260819_01\",\n  \"claims\": [\n    {\n      \"assertion\": \"Service registration requires generic ServiceKey[T]\",\n      \"lineage\": [\n        {\"node\": \"primary_code\", \"uri\": \"file:\u002F\u002F\u002Fsrc\u002Fharness\u002Fkernel\u002Fservice.py#L42-L68\"},\n        {\"node\": \"verification_test\", \"uri\": \"file:\u002F\u002F\u002Ftests\u002Fkernel\u002Ftest_service.py#L15-L35\"}\n      ]\n    }\n  ]\n}\n```\n```\n\n> **Completion criterion**: Structured Isnad record written to persistent store with 100% verified links.\n\n---\n\n## Anti-Patterns\n\n- **Floating Assertions** — Stating facts or architectural guarantees without citing concrete source lines or tool outputs.\n- **Inference Conflation** — Treating logical inferences or plausible assumptions as established ground truth.\n- **Stale Lineage Pointers** — Citing out-of-date line ranges without verifying against the current workspace state.\n- **Unanchored Memory Commits** — Writing unverified decisions into persistent memory or documentation.\n",{"name":5,"description":7},"main","eff3b00e36d1d233ad4a4389605c82fbfa0326d3",".agents\u002Fskills\u002Fepistemic-isnad-audit","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 epistemic-isnad-audit",{"tool":37,"command":38},"bunx","bunx skills add SpectreDeath\u002FBrain-Harness --skill epistemic-isnad-audit",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SpectreDeath\u002FBrain-Harness --skill epistemic-isnad-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fepistemic-isnad-audit\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"CARD.md","REFERENCE","参考文档",4569,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fepistemic-isnad-audit\u002FCARD.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"config.default.yaml",297,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fepistemic-isnad-audit\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",[],[]]