[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AW1WVF2MHTCEYAS9G04YSE":3,"skill-same:01M7AW1WVF2MHTCEYAS9G04YSE":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},"01M7AW1WVF2MHTCEYAS9G04YSE","repo-reader",null,"Introspect, reflect on, and extract architectural patterns, commit trajectories, and engineering heuristics from an attached Git repository. Do not use for simple file tree listing or destructive repository mutations.","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\u002Frepo-reader\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: repo-reader\ndescription: Introspect, reflect on, and extract architectural patterns, commit trajectories, and engineering heuristics from an attached Git repository. Do not use for simple file tree listing or destructive repository mutations.\n---\n\n# Repo Reader: Codebase Introspection & Repository Distillation Engine\n\n`repo-reader` is the repository-level cognitive introspection engine for Brain Harness. Operating atop `plugin.brain_bridge`, it mounts local Git repositories or remote GitHub\u002FGitLab repositories to analyze multi-language codebases, architectural seams, and historical Git commit trajectories—distilling them into grounded, decision-ready Knowledge Items (KIs).\n\nEvery repository reflection session follows a five-stage progression:\n\n```\n[1. Attach & Detect] → [2. 4-Axis Repo Matrix] → [3. Visual Repository Brief] → [4. Synthesis Checkpoint] → [5. KI Extraction & Lineage Commit]\n```\n\nSee [CARD.md](CARD.md) for the companion summary card, 4-axis repository prompt matrix, and invariants.\nConsult `\u002Fcrafting-skills` for skill craft standards, `\u002Fmind-reader` for foreign brain introspection, and `\u002Fepistemic-isnad-audit` for chain-of-custody provenance rules.\n\n---\n\n## 1. Attach & Format Detection\n\nMount the target repository using the `plugin.brain_bridge` entrypoint:\n\n1. **Invoke `brain_attach`**:\n   - `folder_path`: Target directory path or remote Git URL (e.g. `https:\u002F\u002Fgithub.com\u002Forg\u002Frepo.git`).\n   - `alias`: Descriptive mnemonic identifier (e.g., `upstream_repo`, `fastapi_core`).\n   - `read_commits`: `true` to extract Git commit history into cognitive trajectory chunks.\n   - `max_commits`: `50` to `100` commits.\n   - `attach_mode`: `\"lens\"` (read-only ephemeral introspection).\n2. **Handle Boundary & Archive Snapshots**:\n   - **External Workspace Paths**: If the target directory is outside the IDE workspace root and direct file tools return permission errors, use shell inspection commands (`run_command` with PowerShell\u002Fbash) anchored in the host workspace.\n   - **Nested Root & Non-Git Snapshots**: Detect if the repository is an unzipped archive snapshot without `.git` or contains a single nested subdirectory root. If `.git` is absent, gracefully pivot Axis 2 from Git commit trajectories to release notes, changelogs, and manifest evolution.\n3. **Verify Format Signature & Manifests**:\n   Confirm format signature (`git_repository`, `harness_instance`, `ide_memo`) and note detected languages and packaging manifests (`pyproject.toml`, `package.json`, `Cargo.toml`, `go.mod`, etc.).\n4. **Log Mount Volume**:\n   Confirm total chunks, code chunks, git commit trajectory chunks, detected branch, and vocabulary index size.\n\n> **Completion criterion**: Target repository mounted with `status: \"ok\"`, languages identified, and commit trajectories recorded.\n\n---\n\n## 2. 4-Axis Repository Introspection Matrix\n\nExecute four structured queries via `brain_query` across the mounted repository to interrogate its structural and historical surface:\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│               4-AXIS REPOSITORY INTROSPECTION               │\n├──────────────────────────────┬──────────────────────────────┤\n│ Axis 1: Architecture & Seams │ Axis 2: Commit Trajectories  │\n│ - IoC \u002F Service registry     │ - Historical bug fixes       │\n│ - Module boundaries & layers │ - Refactor evolution & diffs │\n├──────────────────────────────┼──────────────────────────────┤\n│ Axis 3: Engineering Standards│ Axis 4: Delta Innovations    │\n│ - Test patterns & fixtures   │ - Deep module designs        │\n│ - Typing, linting, CI rules  │ - Novel algorithms & tooling │\n└──────────────────────────────┴──────────────────────────────┘\n```\n\n1. **Axis 1 (Architectural Topography & Seams)**:\n   - Query: `\"What are the core architecture patterns, IoC service keys, entrypoints, and module boundaries?\"`\n   - Purpose: Surface component relationships, dependency flow, and interface contracts.\n2. **Axis 2 (Commit Evolution & Trajectories)**:\n   - Query: `\"What major refactors, breaking changes, or bug fixes occurred in recent commit history?\"`\n   - Purpose: Understand how the codebase evolved, what pitfalls were encountered, and how design decisions matured.\n3. **Axis 3 (Engineering Conventions & Verification Standards)**:\n   - Query: `\"What testing frameworks, typing standards, CI workflows, and coding conventions are enforced?\"`\n   - Purpose: Identify testing hygiene, error handling conventions, and verification gates.\n4. **Axis 4 (Delta Innovations & Reusable Assets)**:\n   - Query: `\"What unique algorithms, deep module implementations, or reusable abstractions exist in this repository?\"`\n   - Purpose: Extract reusable techniques, high-leverage primitives, and domain models.\n\n> **Completion criterion**: 4 query result batches harvested, sorted by cosine relevance, with exact source file and commit hash citations.\n\n### 2.1 Quantitative Scoring & Tiered Prioritization Matrix\n\nWhen comparing foreign harnesses or evaluating candidate capabilities against Brain Harness, apply the objective scoring formula:\n\n$$\\text{Total Score} = \\text{Usefulness} + (6 - \\text{Difficulty}) + \\text{Value} + \\text{Architectural Fit}$$\n\n*(Each scored 1–5; Difficulty is inverted so that easier adoptions score higher, Max: 20).*\n\nStructure candidate features into a 3-Tier Roadmap:\n- **Tier 1 (Immediate Quick Wins)**: Python-native, low-medium difficulty, direct service plugin fit (Weeks 1–2).\n- **Tier 2 (Strategic Safety & Observability)**: Structural invariants, DAG execution graphs, permission policies, session replays.\n- **Tier 3 (Horizon Bets)**: Alternative language runtimes, local model inference, peer-to-peer distributed meshes.\n\n---\n\n## 3. The Visual Repository Brief\n\nSynthesize the harvested architectural and commit insights into an interactive, standalone HTML report:\n\n1. **Output Location**: Write to `%TEMP%\\repo-reader-\u003Ctimestamp>.html` (Windows) or `\u002Ftmp\u002Frepo-reader-\u003Ctimestamp>.html` (Unix).\n2. **Visual Standards**:\n   - Use Tailwind CSS and Mermaid.js via CDN in dark mode (`#0d1117`).\n   - Include a Mermaid **Repository Architecture & Dependency DAG** showing core modules, bridges, and services.\n   - Display a **Commit Evolution & Refactor Timeline** highlighting pivotal architectural transitions.\n   - Provide a side-by-side matrix of **Architectural Strengths vs. Friction Areas**.\n3. **Delivery**: Surface the absolute file path with clickable links to the user.\n\n```html\n\u003C!-- Location: %TEMP%\\repo-reader-\u003Ctimestamp>.html -->\n\u003C!DOCTYPE html>\n\u003Chtml lang=\"en\">\n\u003Chead>\n  \u003Cmeta charset=\"UTF-8\">\n  \u003Ctitle>Repo Reader: Repository Introspection 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\">Repository Introspection Brief\u003C\u002Fh1>\n    \u003Cp class=\"text-sm text-gray-400 mt-1\">Multi-Language Codebase Analysis & Commit Trajectory Distillation\u003C\u002Fp>\n  \u003C\u002Fheader>\n  \u003C!-- Mermaid DAG & 4-Axis Repository Analysis Grid -->\n\u003C\u002Fbody>\n\u003C\u002Fhtml>\n```\n\n> **Completion criterion**: Standalone HTML brief generated in `%TEMP%` and delivered to user.\n\n---\n\n## 4. Synthesis Checkpoint\n\nPresent candidate architectural and engineering learnings to the user before committing persistent memory:\n\n1. Formulate atomic candidate Knowledge Items (KIs) with:\n   - **Title**: Actionable architecture pattern or engineering heuristic.\n   - **Context**: Problem space, language\u002Fframework context, and trigger conditions.\n   - **Distilled Learning**: Positive recommendation, seam choice, or mitigation strategy.\n   - **Provenance Link**: Exact file path, line coordinates, and Git commit hash in the source repo.\n2. Present candidate KIs via an interactive multi-select checkpoint (`ask_question`) or `RequestFeedback: true` proposal.\n3. Await user confirmation on which items to retain, adjust, or discard before writing files.\n\n> **Completion criterion**: User review checkpoint completed; approved items selected for commit.\n\n---\n\n## 5. KI Extraction & Lineage Commit\n\nPersist approved learnings into the host repository's knowledge directory:\n\n1. **Target Directory**: Write to `.harness\u002Fknowledge\u002F\u003Cki_id>\u002F` on the host.\n2. **Metadata Schema (`metadata.json`)**:\n   ```json\n   {\n     \"id\": \"ki_20260822_repo_01\",\n     \"title\": \"Typed Service Key Registration in Plugin Systems\",\n     \"source_target\": \"https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\",\n     \"detected_format\": \"git_repository\",\n     \"isnad\": {\n       \"decision_id\": \"dec_20260822_repo_01\",\n       \"claims\": [\n         {\n           \"assertion\": \"Typed ServiceKey[T] registration required for IoC containers\",\n           \"lineage\": [\n             {\"node_type\": \"primary_code\", \"uri\": \"src\u002Fkernel\u002Fcontext.py#L42-L68\", \"sha256_hash\": \"a1b2c3d4\", \"verified\": true}\n           ]\n         }\n       ],\n       \"status\": \"VERIFIED\"\n     },\n     \"tags\": [\"architecture\", \"ioc_container\", \"plugin_lifecycle\"]\n   }\n   ```\n3. **Artifact Summary**: Co-locate `summary.md` detailing the operational guideline and code examples.\n\n> **Completion criterion**: Approved KIs written with unbroken Isnad provenance links and commit citations.\n\n---\n\n## Anti-Patterns\n\n- **Surface Code Scanning** — Reading file listings without querying deep module implementations or commit evolution.\n- **Disconnected Commit Analysis** — Inspecting commit messages without correlating them to modified code files.\n- **Foreign Repository Mutation** — Attempting to write, commit, or alter files in the external mounted repository.\n- **Unanchored Seam Extrapolations** — Speculating on architectural intent without citing source lines and commit diffs.\n","# Repo Reader: Codebase Introspection & Repository Distillation Engine\n\n`repo-reader` is the repository-level cognitive introspection engine for Brain Harness. Operating atop `plugin.brain_bridge`, it mounts local Git repositories or remote GitHub\u002FGitLab repositories to analyze multi-language codebases, architectural seams, and historical Git commit trajectories—distilling them into grounded, decision-ready Knowledge Items (KIs).\n\nEvery repository reflection session follows a five-stage progression:\n\n```\n[1. Attach & Detect] → [2. 4-Axis Repo Matrix] → [3. Visual Repository Brief] → [4. Synthesis Checkpoint] → [5. KI Extraction & Lineage Commit]\n```\n\nSee [CARD.md](CARD.md) for the companion summary card, 4-axis repository prompt matrix, and invariants.\nConsult `\u002Fcrafting-skills` for skill craft standards, `\u002Fmind-reader` for foreign brain introspection, and `\u002Fepistemic-isnad-audit` for chain-of-custody provenance rules.\n\n---\n\n## 1. Attach & Format Detection\n\nMount the target repository using the `plugin.brain_bridge` entrypoint:\n\n1. **Invoke `brain_attach`**:\n   - `folder_path`: Target directory path or remote Git URL (e.g. `https:\u002F\u002Fgithub.com\u002Forg\u002Frepo.git`).\n   - `alias`: Descriptive mnemonic identifier (e.g., `upstream_repo`, `fastapi_core`).\n   - `read_commits`: `true` to extract Git commit history into cognitive trajectory chunks.\n   - `max_commits`: `50` to `100` commits.\n   - `attach_mode`: `\"lens\"` (read-only ephemeral introspection).\n2. **Handle Boundary & Archive Snapshots**:\n   - **External Workspace Paths**: If the target directory is outside the IDE workspace root and direct file tools return permission errors, use shell inspection commands (`run_command` with PowerShell\u002Fbash) anchored in the host workspace.\n   - **Nested Root & Non-Git Snapshots**: Detect if the repository is an unzipped archive snapshot without `.git` or contains a single nested subdirectory root. If `.git` is absent, gracefully pivot Axis 2 from Git commit trajectories to release notes, changelogs, and manifest evolution.\n3. **Verify Format Signature & Manifests**:\n   Confirm format signature (`git_repository`, `harness_instance`, `ide_memo`) and note detected languages and packaging manifests (`pyproject.toml`, `package.json`, `Cargo.toml`, `go.mod`, etc.).\n4. **Log Mount Volume**:\n   Confirm total chunks, code chunks, git commit trajectory chunks, detected branch, and vocabulary index size.\n\n> **Completion criterion**: Target repository mounted with `status: \"ok\"`, languages identified, and commit trajectories recorded.\n\n---\n\n## 2. 4-Axis Repository Introspection Matrix\n\nExecute four structured queries via `brain_query` across the mounted repository to interrogate its structural and historical surface:\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│               4-AXIS REPOSITORY INTROSPECTION               │\n├──────────────────────────────┬──────────────────────────────┤\n│ Axis 1: Architecture & Seams │ Axis 2: Commit Trajectories  │\n│ - IoC \u002F Service registry     │ - Historical bug fixes       │\n│ - Module boundaries & layers │ - Refactor evolution & diffs │\n├──────────────────────────────┼──────────────────────────────┤\n│ Axis 3: Engineering Standards│ Axis 4: Delta Innovations    │\n│ - Test patterns & fixtures   │ - Deep module designs        │\n│ - Typing, linting, CI rules  │ - Novel algorithms & tooling │\n└──────────────────────────────┴──────────────────────────────┘\n```\n\n1. **Axis 1 (Architectural Topography & Seams)**:\n   - Query: `\"What are the core architecture patterns, IoC service keys, entrypoints, and module boundaries?\"`\n   - Purpose: Surface component relationships, dependency flow, and interface contracts.\n2. **Axis 2 (Commit Evolution & Trajectories)**:\n   - Query: `\"What major refactors, breaking changes, or bug fixes occurred in recent commit history?\"`\n   - Purpose: Understand how the codebase evolved, what pitfalls were encountered, and how design decisions matured.\n3. **Axis 3 (Engineering Conventions & Verification Standards)**:\n   - Query: `\"What testing frameworks, typing standards, CI workflows, and coding conventions are enforced?\"`\n   - Purpose: Identify testing hygiene, error handling conventions, and verification gates.\n4. **Axis 4 (Delta Innovations & Reusable Assets)**:\n   - Query: `\"What unique algorithms, deep module implementations, or reusable abstractions exist in this repository?\"`\n   - Purpose: Extract reusable techniques, high-leverage primitives, and domain models.\n\n> **Completion criterion**: 4 query result batches harvested, sorted by cosine relevance, with exact source file and commit hash citations.\n\n### 2.1 Quantitative Scoring & Tiered Prioritization Matrix\n\nWhen comparing foreign harnesses or evaluating candidate capabilities against Brain Harness, apply the objective scoring formula:\n\n$$\\text{Total Score} = \\text{Usefulness} + (6 - \\text{Difficulty}) + \\text{Value} + \\text{Architectural Fit}$$\n\n*(Each scored 1–5; Difficulty is inverted so that easier adoptions score higher, Max: 20).*\n\nStructure candidate features into a 3-Tier Roadmap:\n- **Tier 1 (Immediate Quick Wins)**: Python-native, low-medium difficulty, direct service plugin fit (Weeks 1–2).\n- **Tier 2 (Strategic Safety & Observability)**: Structural invariants, DAG execution graphs, permission policies, session replays.\n- **Tier 3 (Horizon Bets)**: Alternative language runtimes, local model inference, peer-to-peer distributed meshes.\n\n---\n\n## 3. The Visual Repository Brief\n\nSynthesize the harvested architectural and commit insights into an interactive, standalone HTML report:\n\n1. **Output Location**: Write to `%TEMP%\\repo-reader-\u003Ctimestamp>.html` (Windows) or `\u002Ftmp\u002Frepo-reader-\u003Ctimestamp>.html` (Unix).\n2. **Visual Standards**:\n   - Use Tailwind CSS and Mermaid.js via CDN in dark mode (`#0d1117`).\n   - Include a Mermaid **Repository Architecture & Dependency DAG** showing core modules, bridges, and services.\n   - Display a **Commit Evolution & Refactor Timeline** highlighting pivotal architectural transitions.\n   - Provide a side-by-side matrix of **Architectural Strengths vs. Friction Areas**.\n3. **Delivery**: Surface the absolute file path with clickable links to the user.\n\n```html\n\u003C!-- Location: %TEMP%\\repo-reader-\u003Ctimestamp>.html -->\n\u003C!DOCTYPE html>\n\u003Chtml lang=\"en\">\n\u003Chead>\n  \u003Cmeta charset=\"UTF-8\">\n  \u003Ctitle>Repo Reader: Repository Introspection 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\">Repository Introspection Brief\u003C\u002Fh1>\n    \u003Cp class=\"text-sm text-gray-400 mt-1\">Multi-Language Codebase Analysis & Commit Trajectory Distillation\u003C\u002Fp>\n  \u003C\u002Fheader>\n  \u003C!-- Mermaid DAG & 4-Axis Repository Analysis Grid -->\n\u003C\u002Fbody>\n\u003C\u002Fhtml>\n```\n\n> **Completion criterion**: Standalone HTML brief generated in `%TEMP%` and delivered to user.\n\n---\n\n## 4. Synthesis Checkpoint\n\nPresent candidate architectural and engineering learnings to the user before committing persistent memory:\n\n1. Formulate atomic candidate Knowledge Items (KIs) with:\n   - **Title**: Actionable architecture pattern or engineering heuristic.\n   - **Context**: Problem space, language\u002Fframework context, and trigger conditions.\n   - **Distilled Learning**: Positive recommendation, seam choice, or mitigation strategy.\n   - **Provenance Link**: Exact file path, line coordinates, and Git commit hash in the source repo.\n2. Present candidate KIs via an interactive multi-select checkpoint (`ask_question`) or `RequestFeedback: true` proposal.\n3. Await user confirmation on which items to retain, adjust, or discard before writing files.\n\n> **Completion criterion**: User review checkpoint completed; approved items selected for commit.\n\n---\n\n## 5. KI Extraction & Lineage Commit\n\nPersist approved learnings into the host repository's knowledge directory:\n\n1. **Target Directory**: Write to `.harness\u002Fknowledge\u002F\u003Cki_id>\u002F` on the host.\n2. **Metadata Schema (`metadata.json`)**:\n   ```json\n   {\n     \"id\": \"ki_20260822_repo_01\",\n     \"title\": \"Typed Service Key Registration in Plugin Systems\",\n     \"source_target\": \"https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\",\n     \"detected_format\": \"git_repository\",\n     \"isnad\": {\n       \"decision_id\": \"dec_20260822_repo_01\",\n       \"claims\": [\n         {\n           \"assertion\": \"Typed ServiceKey[T] registration required for IoC containers\",\n           \"lineage\": [\n             {\"node_type\": \"primary_code\", \"uri\": \"src\u002Fkernel\u002Fcontext.py#L42-L68\", \"sha256_hash\": \"a1b2c3d4\", \"verified\": true}\n           ]\n         }\n       ],\n       \"status\": \"VERIFIED\"\n     },\n     \"tags\": [\"architecture\", \"ioc_container\", \"plugin_lifecycle\"]\n   }\n   ```\n3. **Artifact Summary**: Co-locate `summary.md` detailing the operational guideline and code examples.\n\n> **Completion criterion**: Approved KIs written with unbroken Isnad provenance links and commit citations.\n\n---\n\n## Anti-Patterns\n\n- **Surface Code Scanning** — Reading file listings without querying deep module implementations or commit evolution.\n- **Disconnected Commit Analysis** — Inspecting commit messages without correlating them to modified code files.\n- **Foreign Repository Mutation** — Attempting to write, commit, or alter files in the external mounted repository.\n- **Unanchored Seam Extrapolations** — Speculating on architectural intent without citing source lines and commit diffs.\n",{"name":5,"description":7},"main","eff3b00e36d1d233ad4a4389605c82fbfa0326d3",".agents\u002Fskills\u002Frepo-reader","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 repo-reader",{"tool":37,"command":38},"bunx","bunx skills add SpectreDeath\u002FBrain-Harness --skill repo-reader",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SpectreDeath\u002FBrain-Harness --skill repo-reader","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frepo-reader\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"CARD.md","REFERENCE","参考文档",3808,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frepo-reader\u002FCARD.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"config.default.yaml",287,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frepo-reader\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",[],[]]