[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AVH0KS4JPFDBES4PB33DQ3":3,"skill-same:01M7AVH0KS4JPFDBES4PB33DQ3":61},{"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},"01M7AVH0KS4JPFDBES4PB33DQ3","agent-desktop-operator",null,"Operate desktop applications across Windows, macOS, and Linux using accessibility tree snapshot maps, qualified ref allocation, and 2D delivery-retry recovery. Do not use for DOM-only web scraping or pixel-matching OCR.","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\u002Fagent-desktop-operator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agent-desktop-operator\ndescription: Operate desktop applications across Windows, macOS, and Linux using accessibility tree snapshot maps, qualified ref allocation, and 2D delivery-retry recovery. Do not use for DOM-only web scraping or pixel-matching OCR.\n---\n\n# Agent Desktop Operator: OS Accessibility Computer Use Engine\n\n`agent-desktop-operator` equips AI coding agents with direct desktop GUI operation across Windows, macOS, and Linux through native OS accessibility trees (UI Automation on Windows, AXUIElement on macOS, and AT-SPI on Linux) without screenshots or fragile pixel matching.\n\nSee [CARD.md](CARD.md) for the companion summary card, vocabulary definitions, and invariants checklist.\nConsult [config.default.yaml](config.default.yaml) for baseline operational budgets and timeout thresholds.\n\n---\n\n## The 5-Stage Observe-Drill-Act-Verify Loop\n\n```\n[1. Preflight Status] ──► [2. Skeleton Mapping] ──► [3. Subtree Drill-Down]\n                                                             │\n                                                             ▼\n[5. Verify & 2D Recovery] ◄── [4. Semantic Action Dispatch] ◄┘\n```\n\n---\n\n## 1. Preflight Status & Surface Discovery\n\nBefore interacting with desktop windows, verify runtime permissions and surface capabilities:\n\n1. **Query Platform Status**:\n   - Run `agent-desktop status` (or `desktop_status` via IoC service).\n   - Check that `permissions_granted` is true and note `supported_surfaces` (`window`, `menu`, `dialog`, `sheet`, `alert`).\n2. **Handle Elevation & Sandboxing**:\n   - On Windows, UI Automation interacts with standard and elevated windows under appropriate privilege levels.\n   - On macOS, confirm Accessibility grant under System Settings > Privacy & Security > Accessibility.\n\n> **Completion criterion**: Runtime reports `ok: true`, OS accessibility API active, and surface types enumerated.\n\n---\n\n## 2. Skeleton Mapping for Dense Applications\n\nLarge applications can contain thousands of accessible nodes. Never read the entire application tree at full depth in a single turn:\n\n1. **Generate Shallow Skeleton**:\n   - Run `agent-desktop snapshot --skeleton --app \"AppName\" -i --compact`.\n   - `--skeleton` clamps branch depth while recording `children_count` on truncated branches.\n   - `-i` filters to interactive actionable elements only.\n   - `--compact` strips redundant geometry for token efficiency.\n2. **Respect Web-Wrapper Bypass**:\n   - In Chromium and Electron applications (window class `Chrome_WidgetWin_1`), anonymous transparent container wrappers consume zero logical depth budget, preventing web views from exhausting observation quotas.\n3. **Never Skeleton Focused Surfaces**:\n   - When inspecting popovers, dropdowns, or system sheets, pass `--surface menu` or `--surface sheet` directly without `--skeleton`.\n\n> **Completion criterion**: Shallow skeleton snapshot generated with root-level navigation refs and candidate branch ref tokens.\n\n---\n\n## 3. Subtree Drill-Down\n\nOnce candidate containers are identified from the skeleton, drill down to reveal leaf actionable controls:\n\n1. **Execute Root Drill**:\n   - Run `agent-desktop snapshot --root '@s8f3k2p9:e3' -i --compact`.\n   - Drilling expands the selected subtree and dynamically allocates fresh refs within the *same* `snapshot_id`.\n   - Refs outside the drilled subtree remain valid; previous refs inside the expanded branch are superseded.\n2. **PowerShell Quote Syntax**:\n   - In PowerShell, always quote the ref: `'@s8f3k2p9:e3'`. A bare `@token` triggers PowerShell argument splatting.\n\n> **Completion criterion**: Subtree expanded into leaf actionable refs without invalidating the parent snapshot context.\n\n---\n\n## 4. Semantic Action Dispatch\n\nAct on qualified element references using headless semantic actions before resorting to physical pointer movement:\n\n1. **Verify Qualified Ref Token (Rule 12)**:\n   - Validate that the target matches `@\u003Csnapshot_id>:e\u003CN>`. Reject bare `@e8` tokens to prevent stale mutation.\n2. **Execute Headless Semantic Actions**:\n   - Preferred commands: `click`, `set-value`, `type`, `select`, `toggle`, `check`, `uncheck`, `expand`, `collapse`.\n   - Headless actions dispatch directly via the OS accessibility API without pointer repositioning or focus stealing.\n3. **Headed Fallback for Custom Canvas Elements**:\n   - When an application control lacks semantic action patterns, pass `--headed mouse-click` to simulate physical cursor positioning and hardware events.\n\n> **Completion criterion**: Action dispatched with structured activation steps and parsed 2D disposition metadata.\n\n---\n\n## 5. Verify & 2D Disposition Recovery\n\nInspect action envelopes to confirm delivery and handle stale states deterministically:\n\n1. **Evaluate 2D Outcome Matrix**:\n   - **`DeliveryDisposition`**: `NotDelivered`, `DeliveryUncertain`, `DeliveredUnverified`, or `DeliveredVerified`.\n   - **`RetryDisposition`**: `Safe`, `Unsafe`, or `Unknown`.\n   - **Transaction Rollback Rule**: If delivery is `DeliveryUncertain` or retry is `Unsafe`, trigger transaction rollback (Rule 8) and take a fresh observation.\n2. **Handle Standard Error Refusals**:\n   - `STALE_REF`: The UI changed; re-drill the region or take a new snapshot. Never retry the stale ref.\n   - `AMBIGUOUS_TARGET`: An identical twin appeared or uniqueness was lost; retake snapshot with higher timeout or target an adjacent unique anchor.\n   - `TIMEOUT` (`resolution_identity_unknown`): Live read delayed; safe to retry.\n3. **Dynamic State Waiting**:\n   - After asynchronous actions, call `agent-desktop wait --element '@s:eN' --timeout-ms 5000` or `wait --window \"Title\"` instead of inserting arbitrary time sleeps.\n\n> **Completion criterion**: Action verified via subsequent observation or safely rolled back upon uncertain delivery.\n\n---\n\n## The Three Foundational Pillars\n\n### 1. The Visual Brief Pillar\nEvery major desktop introspection session renders an interactive HTML visual brief in `%TEMP%` displaying the hierarchical accessibility tree, surface boundaries, and active ref allocations with Tailwind CSS and Mermaid diagrams.\n\n### 2. The Mandatory Checkpoint Pillar\nThe agent must never execute destructive or non-idempotent desktop mutations without verifying qualified ref tokens (`@\u003Csnapshot_id>:e\u003CN>`) and checking `is_retry_safe` disposition gates before dispatch.\n\n### 3. Evidence Tri-State & Subprocess Isolation\nNever collapse `Unknown` into `Absent` or boolean `False`. A failed property read or timed-out subtree must withhold uniqueness claims (`CaptureProof`) rather than assuming an element is unique, executing behind isolated subprocess transports with Rule 14 pipe drainage.\n\n---\n\n## Anti-Patterns\n\n- **Bare Ref Splatting** — Passing `@e12` instead of qualified `'@s8f3k2p9:e12'` in PowerShell, triggering argument splatting and command failure.\n- **Fixed Sleep Polling** — Inserting arbitrary `time.sleep()` after actions instead of using condition-based `agent-desktop wait`.\n- **Skeletonizing Focused Surfaces** — Applying `--skeleton` to menus or modal dialogs, which are already focused and compact.\n- **Double-Clicking Uncertain Actions** — Repeating an action whose delivery was `DeliveryUncertain` without checking `is_retry_safe`.\n- **Pixel-Matching Fragility** — Attempting coordinate OCR or visual screenshot diffing when native semantic accessibility trees are available.\n- **Leaking Subprocess Transports** — Omitting `finally` block pipe drainage on async subprocess CLI runners (Rule 14 & Rule 53).\n","# Agent Desktop Operator: OS Accessibility Computer Use Engine\n\n`agent-desktop-operator` equips AI coding agents with direct desktop GUI operation across Windows, macOS, and Linux through native OS accessibility trees (UI Automation on Windows, AXUIElement on macOS, and AT-SPI on Linux) without screenshots or fragile pixel matching.\n\nSee [CARD.md](CARD.md) for the companion summary card, vocabulary definitions, and invariants checklist.\nConsult [config.default.yaml](config.default.yaml) for baseline operational budgets and timeout thresholds.\n\n---\n\n## The 5-Stage Observe-Drill-Act-Verify Loop\n\n```\n[1. Preflight Status] ──► [2. Skeleton Mapping] ──► [3. Subtree Drill-Down]\n                                                             │\n                                                             ▼\n[5. Verify & 2D Recovery] ◄── [4. Semantic Action Dispatch] ◄┘\n```\n\n---\n\n## 1. Preflight Status & Surface Discovery\n\nBefore interacting with desktop windows, verify runtime permissions and surface capabilities:\n\n1. **Query Platform Status**:\n   - Run `agent-desktop status` (or `desktop_status` via IoC service).\n   - Check that `permissions_granted` is true and note `supported_surfaces` (`window`, `menu`, `dialog`, `sheet`, `alert`).\n2. **Handle Elevation & Sandboxing**:\n   - On Windows, UI Automation interacts with standard and elevated windows under appropriate privilege levels.\n   - On macOS, confirm Accessibility grant under System Settings > Privacy & Security > Accessibility.\n\n> **Completion criterion**: Runtime reports `ok: true`, OS accessibility API active, and surface types enumerated.\n\n---\n\n## 2. Skeleton Mapping for Dense Applications\n\nLarge applications can contain thousands of accessible nodes. Never read the entire application tree at full depth in a single turn:\n\n1. **Generate Shallow Skeleton**:\n   - Run `agent-desktop snapshot --skeleton --app \"AppName\" -i --compact`.\n   - `--skeleton` clamps branch depth while recording `children_count` on truncated branches.\n   - `-i` filters to interactive actionable elements only.\n   - `--compact` strips redundant geometry for token efficiency.\n2. **Respect Web-Wrapper Bypass**:\n   - In Chromium and Electron applications (window class `Chrome_WidgetWin_1`), anonymous transparent container wrappers consume zero logical depth budget, preventing web views from exhausting observation quotas.\n3. **Never Skeleton Focused Surfaces**:\n   - When inspecting popovers, dropdowns, or system sheets, pass `--surface menu` or `--surface sheet` directly without `--skeleton`.\n\n> **Completion criterion**: Shallow skeleton snapshot generated with root-level navigation refs and candidate branch ref tokens.\n\n---\n\n## 3. Subtree Drill-Down\n\nOnce candidate containers are identified from the skeleton, drill down to reveal leaf actionable controls:\n\n1. **Execute Root Drill**:\n   - Run `agent-desktop snapshot --root '@s8f3k2p9:e3' -i --compact`.\n   - Drilling expands the selected subtree and dynamically allocates fresh refs within the *same* `snapshot_id`.\n   - Refs outside the drilled subtree remain valid; previous refs inside the expanded branch are superseded.\n2. **PowerShell Quote Syntax**:\n   - In PowerShell, always quote the ref: `'@s8f3k2p9:e3'`. A bare `@token` triggers PowerShell argument splatting.\n\n> **Completion criterion**: Subtree expanded into leaf actionable refs without invalidating the parent snapshot context.\n\n---\n\n## 4. Semantic Action Dispatch\n\nAct on qualified element references using headless semantic actions before resorting to physical pointer movement:\n\n1. **Verify Qualified Ref Token (Rule 12)**:\n   - Validate that the target matches `@\u003Csnapshot_id>:e\u003CN>`. Reject bare `@e8` tokens to prevent stale mutation.\n2. **Execute Headless Semantic Actions**:\n   - Preferred commands: `click`, `set-value`, `type`, `select`, `toggle`, `check`, `uncheck`, `expand`, `collapse`.\n   - Headless actions dispatch directly via the OS accessibility API without pointer repositioning or focus stealing.\n3. **Headed Fallback for Custom Canvas Elements**:\n   - When an application control lacks semantic action patterns, pass `--headed mouse-click` to simulate physical cursor positioning and hardware events.\n\n> **Completion criterion**: Action dispatched with structured activation steps and parsed 2D disposition metadata.\n\n---\n\n## 5. Verify & 2D Disposition Recovery\n\nInspect action envelopes to confirm delivery and handle stale states deterministically:\n\n1. **Evaluate 2D Outcome Matrix**:\n   - **`DeliveryDisposition`**: `NotDelivered`, `DeliveryUncertain`, `DeliveredUnverified`, or `DeliveredVerified`.\n   - **`RetryDisposition`**: `Safe`, `Unsafe`, or `Unknown`.\n   - **Transaction Rollback Rule**: If delivery is `DeliveryUncertain` or retry is `Unsafe`, trigger transaction rollback (Rule 8) and take a fresh observation.\n2. **Handle Standard Error Refusals**:\n   - `STALE_REF`: The UI changed; re-drill the region or take a new snapshot. Never retry the stale ref.\n   - `AMBIGUOUS_TARGET`: An identical twin appeared or uniqueness was lost; retake snapshot with higher timeout or target an adjacent unique anchor.\n   - `TIMEOUT` (`resolution_identity_unknown`): Live read delayed; safe to retry.\n3. **Dynamic State Waiting**:\n   - After asynchronous actions, call `agent-desktop wait --element '@s:eN' --timeout-ms 5000` or `wait --window \"Title\"` instead of inserting arbitrary time sleeps.\n\n> **Completion criterion**: Action verified via subsequent observation or safely rolled back upon uncertain delivery.\n\n---\n\n## The Three Foundational Pillars\n\n### 1. The Visual Brief Pillar\nEvery major desktop introspection session renders an interactive HTML visual brief in `%TEMP%` displaying the hierarchical accessibility tree, surface boundaries, and active ref allocations with Tailwind CSS and Mermaid diagrams.\n\n### 2. The Mandatory Checkpoint Pillar\nThe agent must never execute destructive or non-idempotent desktop mutations without verifying qualified ref tokens (`@\u003Csnapshot_id>:e\u003CN>`) and checking `is_retry_safe` disposition gates before dispatch.\n\n### 3. Evidence Tri-State & Subprocess Isolation\nNever collapse `Unknown` into `Absent` or boolean `False`. A failed property read or timed-out subtree must withhold uniqueness claims (`CaptureProof`) rather than assuming an element is unique, executing behind isolated subprocess transports with Rule 14 pipe drainage.\n\n---\n\n## Anti-Patterns\n\n- **Bare Ref Splatting** — Passing `@e12` instead of qualified `'@s8f3k2p9:e12'` in PowerShell, triggering argument splatting and command failure.\n- **Fixed Sleep Polling** — Inserting arbitrary `time.sleep()` after actions instead of using condition-based `agent-desktop wait`.\n- **Skeletonizing Focused Surfaces** — Applying `--skeleton` to menus or modal dialogs, which are already focused and compact.\n- **Double-Clicking Uncertain Actions** — Repeating an action whose delivery was `DeliveryUncertain` without checking `is_retry_safe`.\n- **Pixel-Matching Fragility** — Attempting coordinate OCR or visual screenshot diffing when native semantic accessibility trees are available.\n- **Leaking Subprocess Transports** — Omitting `finally` block pipe drainage on async subprocess CLI runners (Rule 14 & Rule 53).\n",{"name":5,"description":7},"main","eff3b00e36d1d233ad4a4389605c82fbfa0326d3",".agents\u002Fskills\u002Fagent-desktop-operator","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 agent-desktop-operator",{"tool":37,"command":38},"bunx","bunx skills add SpectreDeath\u002FBrain-Harness --skill agent-desktop-operator",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SpectreDeath\u002FBrain-Harness --skill agent-desktop-operator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-desktop-operator\u002FSKILL.md",true,[45,51,55],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"CARD.md","REFERENCE","参考文档",3459,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-desktop-operator\u002FCARD.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"config.default.yaml",396,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-desktop-operator\u002Fconfig.default.yaml",{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"scripts\u002Fdesktop_operator_engine.py","SCRIPT","脚本",13959,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-desktop-operator\u002Fscripts\u002Fdesktop_operator_engine.py",[62,69,76,83,90,97],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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",[],[]]