[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M713B8HRTT5ZK6PDBAFA8TGP":3,"skill-same:01M713B8HRTT5ZK6PDBAFA8TGP":52},{"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":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M713B8HRTT5ZK6PDBAFA8TGP","norvidize",null,"Extract and audit claims for norvid tracking system","FDU-INS\u002FInsurance-Skills","FDU-INS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F167067594?v=4","01M6XEYMRS4CVJMZ834YWE66BV","FDU-Insurance","01M6XEYMXPDA34HFM0ZE6AY78G",82,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fnorvidize\u002FSKILL.md",[],[5,19,20,21,22,23,24],"audit","system","tracking","extract","claims","for","2026-11-10 10:12:30",false,"---\nname: norvidize\ndescription: Extract and audit claims for norvid tracking system\n---\n\n# Norvidize Skill\n\n\u003C\u003C\u003C\u003C\u003C\u003C\u003C HEAD\nExtract claims from documentation, code, and tests into a claim tracking system\nbased on multicomputational irreducibility -- claims that cannot be reduced to\nsimpler forms without losing verification guarantees.\n=======\nExtract claims from documentation, code, and tests into the norvid claim tracking system.\n>>>>>>> origin\u002Fmain\n\n## When to Use\n\n- After completing a significant feature\n- When auditing documentation accuracy\n- Before releases to ensure claims match reality\n- When docs\u002Ftests\u002Fspecs diverge from implementation\n\n\u003C\u003C\u003C\u003C\u003C\u003C\u003C HEAD\n=======\n## Claim Registry Location\n\n```\ncrates\u002Fbasin-norvid\u002Fsrc\u002Fclaims.rs\n```\n\n>>>>>>> origin\u002Fmain\n## Assurance Levels (lowest to highest)\n\n| Level | Meaning | Evidence Required |\n|-------|---------|-------------------|\n| Mentioned | Just referenced somewhere | Any doc |\n\u003C\u003C\u003C\u003C\u003C\u003C\u003C HEAD\n| Designed | Has design doc | Design markdown |\n| Specified | Has formal spec | Spec file |\n| Implemented | Code exists | Source file + symbol |\n| Tested | Has passing tests | Test file + test name |\n| Proven | Has formal proof | Proof file + theorem |\n=======\n| Designed | Has design doc | docs\u002Fdesign\u002F*.md |\n| Specified | Has sigil spec | *.sigil file |\n| Implemented | Code exists | Rust file + symbol |\n| Tested | Has passing tests | Test file + test name |\n| Proven | Has Lean proof | Lean file + theorem |\n>>>>>>> origin\u002Fmain\n\n## Claim Categories\n\n- **Feature**: User-visible functionality\n- **Property**: System guarantee (linearizability, durability)\n- **Guarantee**: Promise to users\n- **Optimization**: Performance improvement\n- **Invariant**: Internal system invariant\n- **Decision**: Architectural choice with rationale\n- **Omission**: Deliberate non-feature\n\n\u003C\u003C\u003C\u003C\u003C\u003C\u003C HEAD\n## Covariant Claim Structure\n\nClaims form a presheaf over the assurance poset: higher assurance levels\npull back evidence from lower levels. A Tested claim covariantly transports\nits Designed evidence forward.\n\n```\nMentioned -> Designed -> Specified -> Implemented -> Tested -> Proven\n```\n\nEach arrow preserves evidence (covariant functor from assurance levels to evidence sets).\n=======\n## Evidence Types\n\n```rust\n\u002F\u002F Documentation\nEvidence::doc(\"docs\u002FCLAIMS.md\")\n\n\u002F\u002F Rust implementation\nEvidence::rust(\"crates\u002Ffoo\u002Fsrc\u002Fbar.rs\", \"SymbolName\")\n\n\u002F\u002F Test file\nEvidence::test(\"crates\u002Ffoo\u002Fsrc\u002Fbar.rs\", \"test_prefix\")\n\n\u002F\u002F Sigil specification\nEvidence::sigil(\"sigil\u002Fspecs\u002Ffoo.sigil\")\n\n\u002F\u002F External (benchmark, paper)\nEvidence::external(\"benchmarks\u002Fharnesses\u002Fredis\u002Fsrc\u002Fmain.rs\")\n```\n\n## Adding Claims\n\n```rust\nregistry.register(\n    Claim::new(\"CLM_UNIQUE_ID\", \"Short description\")\n        .with_category(Category::Feature)\n        .with_component(Component::Slate)\n        .with_assurance(Assurance::Implemented)\n        .with_evidence(Assurance::Designed, Evidence::doc(\"docs\u002Fdesign\u002Ffoo.md\"))\n        .with_evidence(Assurance::Implemented, Evidence::rust(\"crates\u002Fslate\u002Fsrc\u002Flib.rs\", \"FooStruct\"))\n);\n```\n>>>>>>> origin\u002Fmain\n\n## Extraction Process\n\n### 1. Find Candidate Claims\n\n\u003C\u003C\u003C\u003C\u003C\u003C\u003C HEAD\nScan sources for claim candidates:\n\n```bash\ngrep -r \"CLAIM\\|GUARANTEE\\|INVARIANT\" docs\u002F\ngrep -r \"#\\[test\\]\" -A 2 src\u002F | grep \"fn test_\"\ngrep -r \"ops\u002Fs\\|latency\\|throughput\" docs\u002F\n```\n\n### 2. Categorize by Irreducibility\n\n- **Irreducible claims**: Cannot be verified by simpler means (need full test execution)\n- **Reducible claims**: Can be statically verified (type checking, linting)\n- **Compositional claims**: Verified by composing sub-claim verifications\n\n### 3. Verify Evidence Paths\n\nBefore adding at Tested\u002FImplemented level, verify paths exist.\n\n### 4. Downgrade Strategy\n\nIf evidence path is uncertain, downgrade assurance level.\nUpgrade later when evidence is confirmed.\n\n## Anti-Patterns\n\n- Don't add Tested claims without verifying paths\n- Don't skip Designed level -- even Tested claims should have design evidence\n- Don't guess component names\n=======\nScan these sources for claim candidates:\n\n```bash\n# Explicit claims in docs\ngrep -r \"CLM-\\|CLAIM\\|GUARANTEE\\|INVARIANT\" docs\u002F\n\n# Test names suggest guarantees\ngrep -r \"#\\[test\\]\" -A 2 crates\u002F | grep \"fn test_\"\n\n# Performance claims\ngrep -r \"ops\u002Fs\\|latency\\|throughput\" docs\u002F\n\n# Sigil specs\nfind sigil\u002F -name \"*.sigil\" -exec grep -l \"claim\\|invariant\\|property\" {} \\;\n```\n\n### 2. Categorize and Deduplicate\n\nGroup into tiers:\n- **Tier 1 (SPEC_*)**: Claims with sigil specs - highest value\n- **Tier 2 (TEST_*)**: Claims with test evidence\n- **Tier 3**: Design-level claims (docs only)\n\n### 3. Verify Evidence Paths\n\nBefore adding at Tested\u002FImplemented level, verify paths exist:\n\n```bash\n# Check file exists\ntest -f \"crates\u002Fbasin-redis\u002Fsrc\u002Fcrdt.rs\" && echo \"OK\"\n\n# Check symbol exists\ngrep -l \"EntityStore\" crates\u002Fbasin-meta\u002Fsrc\u002Findexes\u002F*.rs\n```\n\n### 4. Add to Registry\n\nAdd claims to `claims.rs` in appropriate section:\n- SPEC_* claims near line 1720\n- TEST_* claims after specs\n- PERF_* claims in performance section\n- Product claims (CLM_STASH, etc.) with products\n\n## CI Verification\n\nThe CI test filters claims at Tested\u002FProven level and verifies:\n1. Evidence file exists\n2. Symbol\u002Ftest found in file\n\n```bash\n# Run verification\ngraft test -p basin-norvid test_all_claims_verified\n```\n\n## Common Path Mappings\n\n| Old\u002FWrong Path | Correct Path |\n|----------------|--------------|\n| `crates\u002Fstash\u002F` | `crates\u002Fbasin-redis\u002F` |\n| `crates\u002Fshelf\u002F` | `crates\u002Fbasin-mesh\u002F` or `crates\u002Fspool-core\u002F` |\n| `crates\u002Fbasin-jepsen\u002F` | `tests\u002Fbasin-jepsen\u002F` |\n| `products\u002Fnfs\u002Ftests\u002F` | `crates\u002Fnfs\u002Ftests\u002F` |\n\n## Downgrade Strategy\n\nIf evidence path is uncertain, downgrade to Designed level:\n\n```rust\n\u002F\u002F Was Tested but can't verify path\n.with_assurance(Assurance::Designed)\n.with_evidence(Assurance::Designed, Evidence::doc(\"docs\u002FCLAIMS.md\"))\n```\n\nUpgrade later when evidence is confirmed.\n\n## Parallel Audit Pattern\n\nFor bulk verification, spawn sonnet agents:\n\n```\nTask: Audit PERF_* claims\n- Check benchmark files exist\n- Verify they actually measure what claim says\n- Report which claims have valid evidence\n\nTask: Audit product claims (CLM_STASH, etc.)\n- Find actual test locations\n- Verify symbol names\n- Report path corrections needed\n```\n\n## Anti-Patterns\n\n- **Don't add Tested claims without verifying paths** - CI will fail\n- **Don't embed large values in claim IDs** - Keep IDs short like `CLM_STASH`\n- **Don't skip Designed level** - Even Tested claims should have design evidence\n- **Don't guess component names** - Check `Component` enum in identity.rs\n\n## Quick Reference\n\n```bash\n# Find existing claims\ngrep -n \"Claim::new\" crates\u002Fbasin-norvid\u002Fsrc\u002Fclaims.rs | head -20\n\n# Check CI status\ngraft test -p basin-norvid test_all_claims_verified 2>&1 | grep -E \"FAILED|passed\"\n\n# Find test files for a crate\nfind crates\u002Fbasin-meta -name \"*.rs\" -exec grep -l \"#\\[test\\]\" {} \\;\n\n# Count claims by category\ngrep -E \"Category::\" crates\u002Fbasin-norvid\u002Fsrc\u002Fclaims.rs | sort | uniq -c\n```\n>>>>>>> origin\u002Fmain\n","# Norvidize Skill\n\n\u003C\u003C\u003C\u003C\u003C\u003C\u003C HEAD\nExtract claims from documentation, code, and tests into a claim tracking system\nbased on multicomputational irreducibility -- claims that cannot be reduced to\nsimpler forms without losing verification guarantees.\n=======\nExtract claims from documentation, code, and tests into the norvid claim tracking system.\n>>>>>>> origin\u002Fmain\n\n## When to Use\n\n- After completing a significant feature\n- When auditing documentation accuracy\n- Before releases to ensure claims match reality\n- When docs\u002Ftests\u002Fspecs diverge from implementation\n\n\u003C\u003C\u003C\u003C\u003C\u003C\u003C HEAD\n=======\n## Claim Registry Location\n\n```\ncrates\u002Fbasin-norvid\u002Fsrc\u002Fclaims.rs\n```\n\n>>>>>>> origin\u002Fmain\n## Assurance Levels (lowest to highest)\n\n| Level | Meaning | Evidence Required |\n|-------|---------|-------------------|\n| Mentioned | Just referenced somewhere | Any doc |\n\u003C\u003C\u003C\u003C\u003C\u003C\u003C HEAD\n| Designed | Has design doc | Design markdown |\n| Specified | Has formal spec | Spec file |\n| Implemented | Code exists | Source file + symbol |\n| Tested | Has passing tests | Test file + test name |\n| Proven | Has formal proof | Proof file + theorem |\n=======\n| Designed | Has design doc | docs\u002Fdesign\u002F*.md |\n| Specified | Has sigil spec | *.sigil file |\n| Implemented | Code exists | Rust file + symbol |\n| Tested | Has passing tests | Test file + test name |\n| Proven | Has Lean proof | Lean file + theorem |\n>>>>>>> origin\u002Fmain\n\n## Claim Categories\n\n- **Feature**: User-visible functionality\n- **Property**: System guarantee (linearizability, durability)\n- **Guarantee**: Promise to users\n- **Optimization**: Performance improvement\n- **Invariant**: Internal system invariant\n- **Decision**: Architectural choice with rationale\n- **Omission**: Deliberate non-feature\n\n\u003C\u003C\u003C\u003C\u003C\u003C\u003C HEAD\n## Covariant Claim Structure\n\nClaims form a presheaf over the assurance poset: higher assurance levels\npull back evidence from lower levels. A Tested claim covariantly transports\nits Designed evidence forward.\n\n```\nMentioned -> Designed -> Specified -> Implemented -> Tested -> Proven\n```\n\nEach arrow preserves evidence (covariant functor from assurance levels to evidence sets).\n=======\n## Evidence Types\n\n```rust\n\u002F\u002F Documentation\nEvidence::doc(\"docs\u002FCLAIMS.md\")\n\n\u002F\u002F Rust implementation\nEvidence::rust(\"crates\u002Ffoo\u002Fsrc\u002Fbar.rs\", \"SymbolName\")\n\n\u002F\u002F Test file\nEvidence::test(\"crates\u002Ffoo\u002Fsrc\u002Fbar.rs\", \"test_prefix\")\n\n\u002F\u002F Sigil specification\nEvidence::sigil(\"sigil\u002Fspecs\u002Ffoo.sigil\")\n\n\u002F\u002F External (benchmark, paper)\nEvidence::external(\"benchmarks\u002Fharnesses\u002Fredis\u002Fsrc\u002Fmain.rs\")\n```\n\n## Adding Claims\n\n```rust\nregistry.register(\n    Claim::new(\"CLM_UNIQUE_ID\", \"Short description\")\n        .with_category(Category::Feature)\n        .with_component(Component::Slate)\n        .with_assurance(Assurance::Implemented)\n        .with_evidence(Assurance::Designed, Evidence::doc(\"docs\u002Fdesign\u002Ffoo.md\"))\n        .with_evidence(Assurance::Implemented, Evidence::rust(\"crates\u002Fslate\u002Fsrc\u002Flib.rs\", \"FooStruct\"))\n);\n```\n>>>>>>> origin\u002Fmain\n\n## Extraction Process\n\n### 1. Find Candidate Claims\n\n\u003C\u003C\u003C\u003C\u003C\u003C\u003C HEAD\nScan sources for claim candidates:\n\n```bash\ngrep -r \"CLAIM\\|GUARANTEE\\|INVARIANT\" docs\u002F\ngrep -r \"#\\[test\\]\" -A 2 src\u002F | grep \"fn test_\"\ngrep -r \"ops\u002Fs\\|latency\\|throughput\" docs\u002F\n```\n\n### 2. Categorize by Irreducibility\n\n- **Irreducible claims**: Cannot be verified by simpler means (need full test execution)\n- **Reducible claims**: Can be statically verified (type checking, linting)\n- **Compositional claims**: Verified by composing sub-claim verifications\n\n### 3. Verify Evidence Paths\n\nBefore adding at Tested\u002FImplemented level, verify paths exist.\n\n### 4. Downgrade Strategy\n\nIf evidence path is uncertain, downgrade assurance level.\nUpgrade later when evidence is confirmed.\n\n## Anti-Patterns\n\n- Don't add Tested claims without verifying paths\n- Don't skip Designed level -- even Tested claims should have design evidence\n- Don't guess component names\n=======\nScan these sources for claim candidates:\n\n```bash\n# Explicit claims in docs\ngrep -r \"CLM-\\|CLAIM\\|GUARANTEE\\|INVARIANT\" docs\u002F\n\n# Test names suggest guarantees\ngrep -r \"#\\[test\\]\" -A 2 crates\u002F | grep \"fn test_\"\n\n# Performance claims\ngrep -r \"ops\u002Fs\\|latency\\|throughput\" docs\u002F\n\n# Sigil specs\nfind sigil\u002F -name \"*.sigil\" -exec grep -l \"claim\\|invariant\\|property\" {} \\;\n```\n\n### 2. Categorize and Deduplicate\n\nGroup into tiers:\n- **Tier 1 (SPEC_*)**: Claims with sigil specs - highest value\n- **Tier 2 (TEST_*)**: Claims with test evidence\n- **Tier 3**: Design-level claims (docs only)\n\n### 3. Verify Evidence Paths\n\nBefore adding at Tested\u002FImplemented level, verify paths exist:\n\n```bash\n# Check file exists\ntest -f \"crates\u002Fbasin-redis\u002Fsrc\u002Fcrdt.rs\" && echo \"OK\"\n\n# Check symbol exists\ngrep -l \"EntityStore\" crates\u002Fbasin-meta\u002Fsrc\u002Findexes\u002F*.rs\n```\n\n### 4. Add to Registry\n\nAdd claims to `claims.rs` in appropriate section:\n- SPEC_* claims near line 1720\n- TEST_* claims after specs\n- PERF_* claims in performance section\n- Product claims (CLM_STASH, etc.) with products\n\n## CI Verification\n\nThe CI test filters claims at Tested\u002FProven level and verifies:\n1. Evidence file exists\n2. Symbol\u002Ftest found in file\n\n```bash\n# Run verification\ngraft test -p basin-norvid test_all_claims_verified\n```\n\n## Common Path Mappings\n\n| Old\u002FWrong Path | Correct Path |\n|----------------|--------------|\n| `crates\u002Fstash\u002F` | `crates\u002Fbasin-redis\u002F` |\n| `crates\u002Fshelf\u002F` | `crates\u002Fbasin-mesh\u002F` or `crates\u002Fspool-core\u002F` |\n| `crates\u002Fbasin-jepsen\u002F` | `tests\u002Fbasin-jepsen\u002F` |\n| `products\u002Fnfs\u002Ftests\u002F` | `crates\u002Fnfs\u002Ftests\u002F` |\n\n## Downgrade Strategy\n\nIf evidence path is uncertain, downgrade to Designed level:\n\n```rust\n\u002F\u002F Was Tested but can't verify path\n.with_assurance(Assurance::Designed)\n.with_evidence(Assurance::Designed, Evidence::doc(\"docs\u002FCLAIMS.md\"))\n```\n\nUpgrade later when evidence is confirmed.\n\n## Parallel Audit Pattern\n\nFor bulk verification, spawn sonnet agents:\n\n```\nTask: Audit PERF_* claims\n- Check benchmark files exist\n- Verify they actually measure what claim says\n- Report which claims have valid evidence\n\nTask: Audit product claims (CLM_STASH, etc.)\n- Find actual test locations\n- Verify symbol names\n- Report path corrections needed\n```\n\n## Anti-Patterns\n\n- **Don't add Tested claims without verifying paths** - CI will fail\n- **Don't embed large values in claim IDs** - Keep IDs short like `CLM_STASH`\n- **Don't skip Designed level** - Even Tested claims should have design evidence\n- **Don't guess component names** - Check `Component` enum in identity.rs\n\n## Quick Reference\n\n```bash\n# Find existing claims\ngrep -n \"Claim::new\" crates\u002Fbasin-norvid\u002Fsrc\u002Fclaims.rs | head -20\n\n# Check CI status\ngraft test -p basin-norvid test_all_claims_verified 2>&1 | grep -E \"FAILED|passed\"\n\n# Find test files for a crate\nfind crates\u002Fbasin-meta -name \"*.rs\" -exec grep -l \"#\\[test\\]\" {} \\;\n\n# Count claims by category\ngrep -E \"Category::\" crates\u002Fbasin-norvid\u002Fsrc\u002Fclaims.rs | sort | uniq -c\n```\n>>>>>>> origin\u002Fmain\n",{"name":5,"description":7},"main","b22eca2e974f918ce591c5b2bd829fb7510e0191","Skills\u002Fnorvidize",18,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills","https:\u002F\u002Fgithub.com\u002FFDU-INS","Fudan University Department of Risk Management and Insurance","2026-07-12 12:54:34",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add FDU-INS\u002FInsurance-Skills --skill norvidize",{"tool":44,"command":45},"bunx","bunx skills add FDU-INS\u002FInsurance-Skills --skill norvidize",{"tool":47,"command":48},"pnpm","pnpm dlx skills add FDU-INS\u002FInsurance-Skills --skill norvidize","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fnorvidize\u002FSKILL.md",true,[],[53,84,108,139,160,193],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":64,"publishedAt":25},"01M713QW6EGEG0YAD75440GSD0","로인장 (Roinjiang)","Activates when the user needs legal advice, contract review, insurance law consultation, startup legal support, or any legal\u002Fregulatory matter. She is a top-tier in-house lawyer with absolute loyalty to the CEO, specializing in insurance law, financial consumer protection, privacy, contracts, labor law, family law, civil and criminal matters.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002F로인장 (Roinjiang)\u002FSKILL.md",[59],{"categoryNo":60,"categoryName":61,"taxonomyType":62,"taxonomyTypeDesc":63},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[55,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83],"insurance law","insurance","civil","contract","family","when","review","loyalty","with","top","contract review","ceo","support","advice","consultation","regulatory","privacy","protection","startup",{"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":25},"01M713QRN8VFMA9VKS6R4DJ2WS","zocdoc-doctor-finder","Use when a user needs to find a doctor, dentist, specialist, therapist, or healthcare provider — especially when they mention insurance, in-network, availability, location, appointments, or booking. Also use for browsing provider reviews, comparing doctors by specialty, or checking if a provider takes their insurance.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fzocdoc-doctor-finder\u002FSKILL.md",[],[91,92,93,94,66,95,96,70,97,98,99,100,101,102,103,24,104,105,106,107],"zocdoc doctor finder","doctor","healthcare","reviews","browser automation","access","browsing","browser","booking","network","therapist","computer","availability","provider","tool","use","automation",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":119,"publishedAt":25},"01M713QKGV3FTX7EEYWKDM8ENZ","zenmux-context","Answers any question about ZenMux by reading the latest official documentation. Use this skill whenever the user asks about ZenMux product features, API usage, configuration, integration, pricing, models, providers, routing, fallback, streaming, multimodal, structured output, tool calling, reasoning, prompt caching, image generation, video generation, web search, long context, observability, logs, cost tracking, usage analytics, insurance, subscription, pay-as-you-go, invoices, best practices for tools like Claude Code, Cursor, Cline, CodeX, Gemini CLI, opencode, Cherry Studio, Obsidian, Sider, Open-WebUI, Dify, Neovate, GitHub Copilot, OpenClaw, CC-Switch, Immersive Translate, Studio Chat, architecture, benchmarks, FAQ, contact, privacy, terms of service, compliance, or any other ZenMux-related topic. Also trigger when the user writes in Chinese about ZenMux: 文档, 使用指南, 快速开始, API 参考, 最佳实践, 模型路由, 供应商路由, 订阅, 按量计费, 可观测性, 帮助, 常见问题, 接入指南, 配置. Trigger on phrases like \"how to use ZenMux\", \"ZenMux docs\", \"ZenMux API\", \"ZenMux integration\", \"ZenMux 怎么用\", \"ZenMux 接入\", \"ZenMux 配置\". Even if the user doesn't say \"ZenMux\" explicitly but asks about LLM API aggregation, model routing, provider fallback in a context where ZenMux is the project being worked on, this skill should activate.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fzenmux-context\u002FSKILL.md",[114],{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[120,121,122,123,66,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138],"context","zenmux context","Video","chinese","project","web search","translate","search","open","question","pay","image","you","activate","architecture","logs","streaming","cherry studio","how",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":25},"01M713QHWTBG634BCBV7NBJME1","workers-comp-guide","Guide workers compensation compliance and claims management.\nTRIGGERS - Use when user needs help with workers-comp-guide related tasks.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fworkers-comp-guide\u002FSKILL.md",[],[146,147,148,149,150,66,151,152,106,70,153,73,154,23,155,156,157,158,159],"workers","comp","workers comp","workers comp guide","guide","triggers","workers-comp","tasks","claims management","compliance","help","compensation","management","user",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":175,"publishedAt":25},"01M713QF45VMV1685AFNF1GPMA","weekly-kpi-report","Generate McKinsey-style board presentation PPTs from weekly auto insurance data. Automatically calculates 16+ KPIs, creates executive-level slides with actionable insights, and supports week-over-week comparisons. Use when user uploads insurance cost data (Excel\u002FCSV) and requests board report, weekly presentation, executive briefing, or mentions keywords like 董事会汇报, 周报PPT, 经营分析演示, McKinsey-style reports.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fweekly-kpi-report\u002FSKILL.md",[166,169,172],{"categoryNo":167,"categoryName":168,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":170,"categoryName":171,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000004","电子表格",{"categoryNo":173,"categoryName":174,"taxonomyType":62,"taxonomyTypeDesc":63},"01JBSEEDCAT000000000000034","行政与办公人员",[176,177,178,179,180,66,181,182,183,184,70,185,186,187,188,189,190,191,106,192],"weekly","weekly kpi report","kpi","report","xlsx","actionable","insights","briefing","auto","board report","reports","generate","演示","data","presentation","slides","uploads",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":202,"publishedAt":25},"01M713QA9WJDHMNVTTY1ENRKVB","wealth-advisory","Wealth management and financial planning for HNW and UHNW clients. Activate when the user\nmentions wealth management, financial planning, retirement, estate planning, tax planning,\nGRAT, IDGT, trust, asset allocation, withdrawal rate, Monte Carlo simulation, goals-based\ninvesting, tax-loss harvesting, Roth conversion, insurance, annuity, mortgage strategy,\nconcentrated stock, family office, direct indexing, 529 plan, charitable giving, donor-advised\nfund, private foundation, or asks about personal finance strategy, inheritance, long-term\nfinancial planning, or UHNW advisory.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fwealth-advisory\u002FSKILL.md",[199],{"categoryNo":200,"categoryName":201,"taxonomyType":62,"taxonomyTypeDesc":63},"01JBSEEDCAT000000000000040","财务",[203,204,66,205,206,70,133,207,208,209,210,211,212,213,214,215,216,217,218,219],"wealth advisory","advisory","stock","inheritance","conversion","indexing","plan","simulation","personal finance","rate","allocation","asset","direct","personal","investing","trust","planning"]