[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDFBVRTWC8EAT8TGSPX21W":3,"skill-same:01M7FDFBVRTWC8EAT8TGSPX21W":70},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7FDFBVRTWC8EAT8TGSPX21W","yuxi",null,"Operate and maintain Yuxi, a Docker Compose managed FastAPI, LangGraph, Vue, RAG, OCR, knowledge graph, and CLI platform.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fyuxi\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: yuxi\ndescription: \"Operate and maintain Yuxi, a Docker Compose managed FastAPI,\n  LangGraph, Vue, RAG, OCR, knowledge graph, and CLI platform.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# Yuxi repo skill\n\nLoad this repo skill when the task is about Yuxi \u002F 语析: deploying the stack, debugging agent runtime behavior, working with knowledge bases or OCR, using or extending `yuxi-cli`, or choosing repository development checks.\n\nYuxi combines a FastAPI backend package, LangGraph agent runtime, Vue\u002FVite frontend, Docker Compose services, RAG\u002Fknowledge-graph\u002FOCR workflows, and a Typer-based CLI. Treat Docker Compose as the canonical live runtime, but use CPU-safe package\u002FCLI\u002Fstatic checks before escalating to service-required or external-credential tests.\n\n## First safety gates\n\n1. **Do not expose secrets.** `.env`, `.env.prod`, provider keys, admin credentials, Langfuse keys, API keys, MinIO data, and local database contents are sensitive.\n2. **Classify the backend requirement.** Core package\u002FCLI guidance is CPU\u002Fany. Compose integration\u002Fe2e checks require live services. Model providers, Langfuse, cloud OCR, and external API calls require explicit credentials\u002Fnetwork approval.\n3. **Prefer bundled references and scripts.** Generated files are self-contained. If a source repo helper is mutating or credentialed, use the bundled policy reference instead of auto-running it.\n4. **Keep import disabled for this production run.** This skill was generated with final managed import intentionally disabled; do not import it into the live repo-skills library unless a later user explicitly asks.\n\n## Route tasks to sub-skills\n\n| Task signal | Use sub-skill | Why |\n| --- | --- | --- |\n| Start\u002Fdiagnose the Docker stack, Compose profiles, `.env`, images, ports, logs, production deployment, sandbox-provisioner, OCR services, model-provider config | `sub-skills\u002Fdeployment-and-configuration\u002F` | Owns service topology, configuration, health probes, and deployment troubleshooting. |\n| Agent configs, run submission, request queue, steer, streaming, middleware, attachments, built-in tools, Skills, MCP, subagents, sandbox file semantics, API-key\u002FSSE agent calls, Langfuse runtime hooks | `sub-skills\u002Fagent-runtime\u002F` | Owns Yuxi's LangGraph\u002FFastAPI agent execution path and tool surfaces. |\n| Knowledge bases, document upload\u002Fparse\u002Fchunk\u002Findex\u002Fretrieve, Milvus\u002Fvector config, graph\u002Fmindmap, evaluation, OCR engines, `read_file` image\u002FOCR fallback | `sub-skills\u002Fknowledge-and-ocr\u002F` | Owns RAG, KB, document processing, OCR, and knowledge evaluation behavior. |\n| `yuxi` CLI, remote discovery\u002Flogin\u002Fstatus\u002Flogout, temporary browser chat, `agent eval`, `kb upload\u002Flist\u002Ffiles\u002Fquery\u002Fopen\u002Ffind`, API-key external calls, SSE client behavior | `sub-skills\u002Fcli-and-external-integration\u002F` | Owns CLI and external integration commands, including safe offline smoke checks. |\n| Code edits, monorepo boundaries, Docker hot reload, backend\u002Ffrontend\u002FCLI tests, lint\u002Fformat, changelog\u002Fdocs navigation, versioning\u002Frelease policy | `sub-skills\u002Frepo-development\u002F` | Owns maintainer workflow and bounded check selection. |\n\n## Quick operating sequence\n\n1. Read `references\u002Frepo-provenance.md` before relying on this skill for a new checkout; compare the checkout branch\u002Fcommit and package versions to the recorded evidence.\n2. Pick the sub-skill from the routing table. If the task spans areas, start with deployment\u002Fconfig for live stack prerequisites, then load the runtime\u002Fknowledge\u002FCLI\u002Fdevelopment sub-skill that owns the behavior.\n3. Use the sub-skill's `references\u002Ftroubleshooting.md` before changing code or configuration.\n4. For validation, use the owner sub-skill's native candidate notes and any bundled script. Treat service-required and external-credential candidates as blocked until prerequisites are visibly available.\n\n## Minimal local verification\n\nUse the owning sub-skill before running broad checks, but these smoke paths are safe starting points in a Yuxi checkout:\n\n- Backend package import: `cd backend && uv run --group test pytest test\u002Funit\u002Ftest_package_import.py`\n- CLI help\u002Fconfig: `sub-skills\u002Fcli-and-external-integration\u002Fscripts\u002Fcheck-cli.sh`\n- Running stack health: `sub-skills\u002Fdeployment-and-configuration\u002Fscripts\u002Fcheck-runtime-health.sh --project-dir . --dev`\n- Check selection for code changes: `sub-skills\u002Frepo-development\u002Fscripts\u002Frun-selected-checks.sh all-safe`\n\nDo not treat service-required or external-credential workflows as verified unless their prerequisites are visible and the user approved the run.\n\n## Bundled references\n\n- `references\u002Frepo-provenance.md` — commit, versions, dirty-state note, and evidence paths used to build the skill.\n- `references\u002Frepo-routing-metadata.json` — structured router metadata for repo-skills import tooling.\n- `references\u002Fcapability-map.md` — public capability ownership and native verification candidate summary.\n- `references\u002Fsource-script-policy.md` — why repo-owned helpers were copied, adapted, wrapped, or left reference-only.\n- `references\u002Ftroubleshooting.md` — cross-cutting failure-mode index.\n\n## Bundled scripts\n\nRoot does not own mutable scripts. Use scripts from the owning sub-skill:\n\n- `sub-skills\u002Fdeployment-and-configuration\u002Fscripts\u002Fcheck-runtime-health.sh` — read-only health\u002Flog probe for an already running stack.\n- `sub-skills\u002Fcli-and-external-integration\u002Fscripts\u002Fcheck-cli.sh` — offline CLI help\u002Fconfig smoke check with explicit opt-in remote ping.\n- `sub-skills\u002Frepo-development\u002Fscripts\u002Frun-selected-checks.sh` — opt-in command printer\u002Frunner for bounded maintainer checks.\n\n## Verification status\n\nThis generated skill is an operating-knowledge candidate for Yuxi at the provenance recorded in `references\u002Frepo-provenance.md`. A private CPU\u002Fany Python inspection environment successfully imported the backend package, CLI package, selected agent\u002Fknowledge modules, and `yuxi_cli --help`. Final `verify-repo-skill` usability\u002Fnative verification and managed import have not been performed by this creation phase.\n","# Yuxi repo skill\n\nLoad this repo skill when the task is about Yuxi \u002F 语析: deploying the stack, debugging agent runtime behavior, working with knowledge bases or OCR, using or extending `yuxi-cli`, or choosing repository development checks.\n\nYuxi combines a FastAPI backend package, LangGraph agent runtime, Vue\u002FVite frontend, Docker Compose services, RAG\u002Fknowledge-graph\u002FOCR workflows, and a Typer-based CLI. Treat Docker Compose as the canonical live runtime, but use CPU-safe package\u002FCLI\u002Fstatic checks before escalating to service-required or external-credential tests.\n\n## First safety gates\n\n1. **Do not expose secrets.** `.env`, `.env.prod`, provider keys, admin credentials, Langfuse keys, API keys, MinIO data, and local database contents are sensitive.\n2. **Classify the backend requirement.** Core package\u002FCLI guidance is CPU\u002Fany. Compose integration\u002Fe2e checks require live services. Model providers, Langfuse, cloud OCR, and external API calls require explicit credentials\u002Fnetwork approval.\n3. **Prefer bundled references and scripts.** Generated files are self-contained. If a source repo helper is mutating or credentialed, use the bundled policy reference instead of auto-running it.\n4. **Keep import disabled for this production run.** This skill was generated with final managed import intentionally disabled; do not import it into the live repo-skills library unless a later user explicitly asks.\n\n## Route tasks to sub-skills\n\n| Task signal | Use sub-skill | Why |\n| --- | --- | --- |\n| Start\u002Fdiagnose the Docker stack, Compose profiles, `.env`, images, ports, logs, production deployment, sandbox-provisioner, OCR services, model-provider config | `sub-skills\u002Fdeployment-and-configuration\u002F` | Owns service topology, configuration, health probes, and deployment troubleshooting. |\n| Agent configs, run submission, request queue, steer, streaming, middleware, attachments, built-in tools, Skills, MCP, subagents, sandbox file semantics, API-key\u002FSSE agent calls, Langfuse runtime hooks | `sub-skills\u002Fagent-runtime\u002F` | Owns Yuxi's LangGraph\u002FFastAPI agent execution path and tool surfaces. |\n| Knowledge bases, document upload\u002Fparse\u002Fchunk\u002Findex\u002Fretrieve, Milvus\u002Fvector config, graph\u002Fmindmap, evaluation, OCR engines, `read_file` image\u002FOCR fallback | `sub-skills\u002Fknowledge-and-ocr\u002F` | Owns RAG, KB, document processing, OCR, and knowledge evaluation behavior. |\n| `yuxi` CLI, remote discovery\u002Flogin\u002Fstatus\u002Flogout, temporary browser chat, `agent eval`, `kb upload\u002Flist\u002Ffiles\u002Fquery\u002Fopen\u002Ffind`, API-key external calls, SSE client behavior | `sub-skills\u002Fcli-and-external-integration\u002F` | Owns CLI and external integration commands, including safe offline smoke checks. |\n| Code edits, monorepo boundaries, Docker hot reload, backend\u002Ffrontend\u002FCLI tests, lint\u002Fformat, changelog\u002Fdocs navigation, versioning\u002Frelease policy | `sub-skills\u002Frepo-development\u002F` | Owns maintainer workflow and bounded check selection. |\n\n## Quick operating sequence\n\n1. Read `references\u002Frepo-provenance.md` before relying on this skill for a new checkout; compare the checkout branch\u002Fcommit and package versions to the recorded evidence.\n2. Pick the sub-skill from the routing table. If the task spans areas, start with deployment\u002Fconfig for live stack prerequisites, then load the runtime\u002Fknowledge\u002FCLI\u002Fdevelopment sub-skill that owns the behavior.\n3. Use the sub-skill's `references\u002Ftroubleshooting.md` before changing code or configuration.\n4. For validation, use the owner sub-skill's native candidate notes and any bundled script. Treat service-required and external-credential candidates as blocked until prerequisites are visibly available.\n\n## Minimal local verification\n\nUse the owning sub-skill before running broad checks, but these smoke paths are safe starting points in a Yuxi checkout:\n\n- Backend package import: `cd backend && uv run --group test pytest test\u002Funit\u002Ftest_package_import.py`\n- CLI help\u002Fconfig: `sub-skills\u002Fcli-and-external-integration\u002Fscripts\u002Fcheck-cli.sh`\n- Running stack health: `sub-skills\u002Fdeployment-and-configuration\u002Fscripts\u002Fcheck-runtime-health.sh --project-dir . --dev`\n- Check selection for code changes: `sub-skills\u002Frepo-development\u002Fscripts\u002Frun-selected-checks.sh all-safe`\n\nDo not treat service-required or external-credential workflows as verified unless their prerequisites are visible and the user approved the run.\n\n## Bundled references\n\n- `references\u002Frepo-provenance.md` — commit, versions, dirty-state note, and evidence paths used to build the skill.\n- `references\u002Frepo-routing-metadata.json` — structured router metadata for repo-skills import tooling.\n- `references\u002Fcapability-map.md` — public capability ownership and native verification candidate summary.\n- `references\u002Fsource-script-policy.md` — why repo-owned helpers were copied, adapted, wrapped, or left reference-only.\n- `references\u002Ftroubleshooting.md` — cross-cutting failure-mode index.\n\n## Bundled scripts\n\nRoot does not own mutable scripts. Use scripts from the owning sub-skill:\n\n- `sub-skills\u002Fdeployment-and-configuration\u002Fscripts\u002Fcheck-runtime-health.sh` — read-only health\u002Flog probe for an already running stack.\n- `sub-skills\u002Fcli-and-external-integration\u002Fscripts\u002Fcheck-cli.sh` — offline CLI help\u002Fconfig smoke check with explicit opt-in remote ping.\n- `sub-skills\u002Frepo-development\u002Fscripts\u002Frun-selected-checks.sh` — opt-in command printer\u002Frunner for bounded maintainer checks.\n\n## Verification status\n\nThis generated skill is an operating-knowledge candidate for Yuxi at the provenance recorded in `references\u002Frepo-provenance.md`. A private CPU\u002Fany Python inspection environment successfully imported the backend package, CLI package, selected agent\u002Fknowledge modules, and `yuxi_cli --help`. Final `verify-repo-skill` usability\u002Fnative verification and managed import have not been performed by this creation phase.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fyuxi",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill yuxi",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill yuxi",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill yuxi","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fyuxi\u002FSKILL.md",[48,54,58,62,66],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fcapability-map.md","REFERENCE","参考文档",5221,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fyuxi\u002Freferences\u002Fcapability-map.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Frepo-provenance.md",3787,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fyuxi\u002Freferences\u002Frepo-provenance.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Frepo-routing-metadata.json",496,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fyuxi\u002Freferences\u002Frepo-routing-metadata.json",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fsource-script-policy.md",3553,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fyuxi\u002Freferences\u002Fsource-script-policy.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Ftroubleshooting.md",3627,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fyuxi\u002Freferences\u002Ftroubleshooting.md",[71,78,83,90,97,104],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":79,"name":73,"nameZh":6,"description":74,"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},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\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},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\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},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\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},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]