[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AVRHWJGEBJFKM5KDMB0RKC":3,"skill-same:01M7AVRHWJGEBJFKM5KDMB0RKC":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},"01M7AVRHWJGEBJFKM5KDMB0RKC","elephant-goldfish-governor",null,"Govern AI agent design and review workflows using the Elephant-Goldfish bifurcated context architecture, artifact-first spec drafting, 5-stage antagonistic review gates, and living spec drift detection. Do not use for superficial prompt drafting, single-turn ungrounded chat, or small one-line bug fixes.","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\u002Felephant-goldfish-governor\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: elephant-goldfish-governor\ndescription: Govern AI agent design and review workflows using the Elephant-Goldfish bifurcated context architecture, artifact-first spec drafting, 5-stage antagonistic review gates, and living spec drift detection. Do not use for superficial prompt drafting, single-turn ungrounded chat, or small one-line bug fixes.\n---\n\n# Elephant-Goldfish Governor — Spec-Driven Architecture & Zero-Context Review\n\n`elephant-goldfish-governor` operationalizes the Elephant-Goldfish Model (EGM) within the Brain Harness. It enforces bifurcated cognitive contexts: pairing a deep-context drafting partner (The Elephant) with isolated, zero-context subagent reviewers (The Goldfish) to eliminate hallucination cascades, confirmation bias, and conversational context pollution.\n\nSee [CARD.md](CARD.md) for companion summary card, stage progression table, and invariants checklist.\nConsult [config.default.yaml](config.default.yaml) for baseline operational budgets and timeout thresholds.\n\n---\n\n## The 5-Stage EGM Governance Progression\n\n```\n[1. Upstream Concept Ideation & Multi-Lens Brainstorm]\n                       │\n                       ▼\n[2. Sectional Spec Drafting & Semantic Boundary Isolation]\n  ├── FeatureRange (High-altitude architecture & simplicity)\n  └── DetailedRange (Low-altitude signatures, tests & rollout)\n                       │\n                       ▼\n[3. Five-Stage Antagonistic Goldfish Review Pipeline]\n  ├── Stage 5: Initial Zoom Out Review (Simplicity & YAGNI)\n  ├── Stage 6: Naive Comprehension Test (Self-containment)\n  ├── Stage 7: Technical Critic Review (Scale & failure modes)\n  ├── Stage 8: Intermediate Zoom Out (Creep regression check)\n  └── Stage 9: Implementation Readiness (Concreteness & tests)\n                       │\n                       ▼\n[4. In-Thread Finding Remediation & Tri-State Gating]\n  └── Resolve blockers\u002Fmajors in Elephant context before coding\n                       │\n                       ▼\n[5. Continuous Living Spec Drift Detection & AST Auditing]\n  └── Compare checked-in docs\u002Fdesigns\u002F*.md vs live codebase symbols\n```\n\n---\n\n## 1. Upstream Concept Ideation & Multi-Lens Brainstorm\n\nTransform raw concepts into anchored working hypotheses without premature implementation:\n\n1. **Conduct Open-Ended Clarification**:\n   - Interview the engineer across multiple conversational turns to extract the core hypothesis, constraints, and non-goals.\n   - Strictly prohibit multiple-choice crutches during exploratory ideation.\n2. **Spawn Multi-Lens Goldfish Brainstorm Swarm**:\n   - Dispatch parallel zero-context reviewers across 6 lenses: Skeptical Architect, UX\u002FErgonomics, Performance\u002FScale, Security\u002FFailure, Codebase Reuse, and Structural Integrity.\n   - Aggregate, deduplicate, and compile findings into `concepts_brief.md`.\n3. **Artifact-First Delivery**:\n   - Never dump brainstorm summaries into the chat window. Write directly to `concepts_brief.md` and present clean path references.\n\n> **Completion criterion**: Working hypothesis anchored, 6-lens brainstorm executed, and verified `concepts_brief.md` emitted to disk.\n\n---\n\n## 2. Sectional Spec Drafting & Semantic Boundary Isolation\n\nCompile verified briefs into disciplined technical specifications with strict altitude control:\n\n1. **Establish Semantic Range Boundaries**:\n   - `FeatureRange`: High-level architecture, user journeys, root problem focus, simplicity (YAGNI), and rejected alternatives.\n   - `DetailedRange`: Concrete file paths, class\u002Ffunction signatures, error types, test cases, and phased rollout plans.\n2. **Iterative Section Drafting**:\n   - Draft the specification section by section into `docs\u002Fdesigns\u002F\u003Cfeature>.md`, pausing after each section for human feedback.\n   - Prevent the \"Weeds Syndrome\" by strictly barring implementation code from high-level architecture sections.\n\n> **Completion criterion**: Specification compiled into `docs\u002Fdesigns\u002F\u003Cfeature>.md` with clean semantic boundary isolation between FeatureRange and DetailedRange.\n\n---\n\n## 3. Five-Stage Antagonistic Goldfish Review Pipeline\n\nExecute sequential zero-context verification with specialized rubrics:\n\n1. **Initial Zoom Out Review (Stage 5)**:\n   - Evaluate root-problem focus, YAGNI, simplicity, and codebase reuse against `zoom-out-standard.md`.\n2. **Naive Comprehension Test (Stage 6)**:\n   - Verify self-containment with an isolated reader subagent without prior context or tribal knowledge.\n3. **Technical Critic Review (Stage 7)**:\n   - Stress-test system design, race conditions, scaling limits, and edge cases against `feature-spec-standard.md`.\n4. **Intermediate Zoom Out (Stage 8)**:\n   - Re-audit additions made during Comprehension and Critic stages to eliminate newly introduced scope creep.\n5. **Implementation Readiness Test (Stage 9)**:\n   - Audit exact file paths, symbol signatures, test fixtures, and migration plans against `implementation-readiness-standard.md`.\n\n> **Completion criterion**: All 5 review stages executed with normalized findings grouped into Blocker, Major, and Nit severities.\n\n---\n\n## 4. In-Thread Finding Remediation & Tri-State Gating\n\nEnforce human-in-the-loop decision rights and immediate spec patching:\n\n1. **Tri-State Checkpoint Gates**:\n   - At each review phase, present standard choices: proceed to next stage, resolve findings with agent in-thread, edit manually, or pause.\n2. **In-Thread Resolution**:\n   - The primary Elephant agent evaluates findings, drafts concrete text patches, and applies approved edits directly to the design document.\n   - Recalculate line boundaries after patches are applied.\n\n> **Completion criterion**: All blockers and major findings resolved and confirmed by the human engineer before implementation begins.\n\n---\n\n## 5. Continuous Living Spec Drift Detection & AST Auditing\n\nPrevent specification rot by treating checked-in designs as living ground-truth contracts:\n\n1. **AST Codebase Extraction**:\n   - Scan target source directories for classes, functions, dataclasses, and routes mentioned in `docs\u002Fdesigns\u002F*.md`.\n2. **Differential Drift Categorization**:\n   - Classify discrepancies into 4 categories:\n     - `Missing Features`: Logic promised in the spec but absent in code.\n     - `Incomplete Models`: Dataclasses\u002Fstructs missing declared fields.\n     - `Logic Shortcuts`: Hardcoded stubs or mocks replacing dynamic flows.\n     - `Architectural Divergence`: Unauthorized libraries or misplaced logic.\n3. **Emit Actionable Drift Reports**:\n   - Produce `{YYYY-MM-DD}_DRIFT_REPORT.md` reporting strictly divergences without reciting conforming code.\n\n> **Completion criterion**: Comprehensive differential drift report generated identifying all discrepancies between checked-in specs and codebase reality.\n\n---\n\n## The Three Foundational Pillars\n\n### 1. Asymmetric Cognitive Context Bifurcation\nNever allow the same LLM context that drafts code to validate its own work. Split development into a deep-context author (Elephant) and zero-context isolated reviewers (Goldfish).\n\n### 2. Artifact-First Delivery & Altitude Boundaries\nBanish chat dumps. Emitting large specs or review logs into chat panes causes context bloat and user fatigue. Partition documents into high-altitude architecture (`FeatureRange`) and low-altitude implementation (`DetailedRange`).\n\n### 3. Living Ground-Truth Specifications\nDesign specifications checked into `docs\u002Fdesigns\u002F` are permanent engineering contracts. Regularly audit code against specs via automated AST drift detection to guarantee architectural fidelity.\n\n---\n\n## Anti-Patterns\n\n- **Single-Thread Self-Review** — Allowing the authoring agent to review its own design in the same conversational context without fresh subagents.\n- **Chat Dump Spew** — Dumping multi-page specifications or lengthy review logs directly into the chat pane instead of persistent markdown artifacts.\n- **Altitude Inversion (Weeds Syndrome)** — Smuggling helper functions, raw SQL queries, or loop variables into high-level architecture sections before validating root problem fit.\n- **Sycophantic Glazing** — Reviewers praising proposals with empty flattery (\"great idea\", \"brilliant approach\") instead of leading with technical failure modes.\n- **Specification Rot Abandonment** — Allowing checked-in design documents to decay as code evolves without running automated drift detection.\n- **Silent Reviewer Swallowing** — Treating timed-out or failed reviewer subagents as passing with zero findings instead of marking them as `not run`.\n\n","# Elephant-Goldfish Governor — Spec-Driven Architecture & Zero-Context Review\n\n`elephant-goldfish-governor` operationalizes the Elephant-Goldfish Model (EGM) within the Brain Harness. It enforces bifurcated cognitive contexts: pairing a deep-context drafting partner (The Elephant) with isolated, zero-context subagent reviewers (The Goldfish) to eliminate hallucination cascades, confirmation bias, and conversational context pollution.\n\nSee [CARD.md](CARD.md) for companion summary card, stage progression table, and invariants checklist.\nConsult [config.default.yaml](config.default.yaml) for baseline operational budgets and timeout thresholds.\n\n---\n\n## The 5-Stage EGM Governance Progression\n\n```\n[1. Upstream Concept Ideation & Multi-Lens Brainstorm]\n                       │\n                       ▼\n[2. Sectional Spec Drafting & Semantic Boundary Isolation]\n  ├── FeatureRange (High-altitude architecture & simplicity)\n  └── DetailedRange (Low-altitude signatures, tests & rollout)\n                       │\n                       ▼\n[3. Five-Stage Antagonistic Goldfish Review Pipeline]\n  ├── Stage 5: Initial Zoom Out Review (Simplicity & YAGNI)\n  ├── Stage 6: Naive Comprehension Test (Self-containment)\n  ├── Stage 7: Technical Critic Review (Scale & failure modes)\n  ├── Stage 8: Intermediate Zoom Out (Creep regression check)\n  └── Stage 9: Implementation Readiness (Concreteness & tests)\n                       │\n                       ▼\n[4. In-Thread Finding Remediation & Tri-State Gating]\n  └── Resolve blockers\u002Fmajors in Elephant context before coding\n                       │\n                       ▼\n[5. Continuous Living Spec Drift Detection & AST Auditing]\n  └── Compare checked-in docs\u002Fdesigns\u002F*.md vs live codebase symbols\n```\n\n---\n\n## 1. Upstream Concept Ideation & Multi-Lens Brainstorm\n\nTransform raw concepts into anchored working hypotheses without premature implementation:\n\n1. **Conduct Open-Ended Clarification**:\n   - Interview the engineer across multiple conversational turns to extract the core hypothesis, constraints, and non-goals.\n   - Strictly prohibit multiple-choice crutches during exploratory ideation.\n2. **Spawn Multi-Lens Goldfish Brainstorm Swarm**:\n   - Dispatch parallel zero-context reviewers across 6 lenses: Skeptical Architect, UX\u002FErgonomics, Performance\u002FScale, Security\u002FFailure, Codebase Reuse, and Structural Integrity.\n   - Aggregate, deduplicate, and compile findings into `concepts_brief.md`.\n3. **Artifact-First Delivery**:\n   - Never dump brainstorm summaries into the chat window. Write directly to `concepts_brief.md` and present clean path references.\n\n> **Completion criterion**: Working hypothesis anchored, 6-lens brainstorm executed, and verified `concepts_brief.md` emitted to disk.\n\n---\n\n## 2. Sectional Spec Drafting & Semantic Boundary Isolation\n\nCompile verified briefs into disciplined technical specifications with strict altitude control:\n\n1. **Establish Semantic Range Boundaries**:\n   - `FeatureRange`: High-level architecture, user journeys, root problem focus, simplicity (YAGNI), and rejected alternatives.\n   - `DetailedRange`: Concrete file paths, class\u002Ffunction signatures, error types, test cases, and phased rollout plans.\n2. **Iterative Section Drafting**:\n   - Draft the specification section by section into `docs\u002Fdesigns\u002F\u003Cfeature>.md`, pausing after each section for human feedback.\n   - Prevent the \"Weeds Syndrome\" by strictly barring implementation code from high-level architecture sections.\n\n> **Completion criterion**: Specification compiled into `docs\u002Fdesigns\u002F\u003Cfeature>.md` with clean semantic boundary isolation between FeatureRange and DetailedRange.\n\n---\n\n## 3. Five-Stage Antagonistic Goldfish Review Pipeline\n\nExecute sequential zero-context verification with specialized rubrics:\n\n1. **Initial Zoom Out Review (Stage 5)**:\n   - Evaluate root-problem focus, YAGNI, simplicity, and codebase reuse against `zoom-out-standard.md`.\n2. **Naive Comprehension Test (Stage 6)**:\n   - Verify self-containment with an isolated reader subagent without prior context or tribal knowledge.\n3. **Technical Critic Review (Stage 7)**:\n   - Stress-test system design, race conditions, scaling limits, and edge cases against `feature-spec-standard.md`.\n4. **Intermediate Zoom Out (Stage 8)**:\n   - Re-audit additions made during Comprehension and Critic stages to eliminate newly introduced scope creep.\n5. **Implementation Readiness Test (Stage 9)**:\n   - Audit exact file paths, symbol signatures, test fixtures, and migration plans against `implementation-readiness-standard.md`.\n\n> **Completion criterion**: All 5 review stages executed with normalized findings grouped into Blocker, Major, and Nit severities.\n\n---\n\n## 4. In-Thread Finding Remediation & Tri-State Gating\n\nEnforce human-in-the-loop decision rights and immediate spec patching:\n\n1. **Tri-State Checkpoint Gates**:\n   - At each review phase, present standard choices: proceed to next stage, resolve findings with agent in-thread, edit manually, or pause.\n2. **In-Thread Resolution**:\n   - The primary Elephant agent evaluates findings, drafts concrete text patches, and applies approved edits directly to the design document.\n   - Recalculate line boundaries after patches are applied.\n\n> **Completion criterion**: All blockers and major findings resolved and confirmed by the human engineer before implementation begins.\n\n---\n\n## 5. Continuous Living Spec Drift Detection & AST Auditing\n\nPrevent specification rot by treating checked-in designs as living ground-truth contracts:\n\n1. **AST Codebase Extraction**:\n   - Scan target source directories for classes, functions, dataclasses, and routes mentioned in `docs\u002Fdesigns\u002F*.md`.\n2. **Differential Drift Categorization**:\n   - Classify discrepancies into 4 categories:\n     - `Missing Features`: Logic promised in the spec but absent in code.\n     - `Incomplete Models`: Dataclasses\u002Fstructs missing declared fields.\n     - `Logic Shortcuts`: Hardcoded stubs or mocks replacing dynamic flows.\n     - `Architectural Divergence`: Unauthorized libraries or misplaced logic.\n3. **Emit Actionable Drift Reports**:\n   - Produce `{YYYY-MM-DD}_DRIFT_REPORT.md` reporting strictly divergences without reciting conforming code.\n\n> **Completion criterion**: Comprehensive differential drift report generated identifying all discrepancies between checked-in specs and codebase reality.\n\n---\n\n## The Three Foundational Pillars\n\n### 1. Asymmetric Cognitive Context Bifurcation\nNever allow the same LLM context that drafts code to validate its own work. Split development into a deep-context author (Elephant) and zero-context isolated reviewers (Goldfish).\n\n### 2. Artifact-First Delivery & Altitude Boundaries\nBanish chat dumps. Emitting large specs or review logs into chat panes causes context bloat and user fatigue. Partition documents into high-altitude architecture (`FeatureRange`) and low-altitude implementation (`DetailedRange`).\n\n### 3. Living Ground-Truth Specifications\nDesign specifications checked into `docs\u002Fdesigns\u002F` are permanent engineering contracts. Regularly audit code against specs via automated AST drift detection to guarantee architectural fidelity.\n\n---\n\n## Anti-Patterns\n\n- **Single-Thread Self-Review** — Allowing the authoring agent to review its own design in the same conversational context without fresh subagents.\n- **Chat Dump Spew** — Dumping multi-page specifications or lengthy review logs directly into the chat pane instead of persistent markdown artifacts.\n- **Altitude Inversion (Weeds Syndrome)** — Smuggling helper functions, raw SQL queries, or loop variables into high-level architecture sections before validating root problem fit.\n- **Sycophantic Glazing** — Reviewers praising proposals with empty flattery (\"great idea\", \"brilliant approach\") instead of leading with technical failure modes.\n- **Specification Rot Abandonment** — Allowing checked-in design documents to decay as code evolves without running automated drift detection.\n- **Silent Reviewer Swallowing** — Treating timed-out or failed reviewer subagents as passing with zero findings instead of marking them as `not run`.\n\n",{"name":5,"description":7},"main","eff3b00e36d1d233ad4a4389605c82fbfa0326d3",".agents\u002Fskills\u002Felephant-goldfish-governor","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 elephant-goldfish-governor",{"tool":37,"command":38},"bunx","bunx skills add SpectreDeath\u002FBrain-Harness --skill elephant-goldfish-governor",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SpectreDeath\u002FBrain-Harness --skill elephant-goldfish-governor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Felephant-goldfish-governor\u002FSKILL.md",true,[45,51,55,61],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"CARD.md","REFERENCE","参考文档",3745,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Felephant-goldfish-governor\u002FCARD.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"config.default.yaml",1015,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Felephant-goldfish-governor\u002Fconfig.default.yaml",{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"scripts\u002Felephant_goldfish_engine.py","SCRIPT","脚本",11607,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Felephant-goldfish-governor\u002Fscripts\u002Felephant_goldfish_engine.py",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"tests\u002Ftest_elephant_goldfish_skill.py",5213,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Felephant-goldfish-governor\u002Ftests\u002Ftest_elephant_goldfish_skill.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",[],[]]