[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ECRP478G4SVCZF4G5D3XPP":3,"skill-same:01M7ECRP478G4SVCZF4G5D3XPP":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},"01M7ECRP478G4SVCZF4G5D3XPP","langroid",null,"Use Langroid to build Python LLM agents, tools, tasks, RAG\u002Fdocument chat, provider configs, structured data agents, MCP integrations, Chainlit callbacks, and no-network smoke checks.","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\u002F03-逆向工程\u002Flangroid\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: langroid\ndescription: \"Use Langroid to build Python LLM agents, tools, tasks,\n  RAG\u002Fdocument chat, provider configs, structured data agents, MCP integrations,\n  Chainlit callbacks, and no-network smoke checks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Langroid Repo Skill\n\nUse this repo skill when a task names Langroid or asks for Python LLM agent\nworkflows involving `ChatAgent`, `Task`, `ToolMessage`, providers, RAG,\nstructured data agents, MCP, Chainlit, or Langroid optional extras.\n\nLangroid is a Python framework for building LLM-powered agents that use tools,\nexchange messages, delegate tasks, retrieve from documents, and integrate with\nproviders and external tool systems.\n\n## First checks\n\nRead [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) when you\nneed to decide whether this skill matches a checkout or installed package\nversion. For install and extras selection, read\n[`references\u002Finstall-and-extras.md`](references\u002Finstall-and-extras.md) and\n[`references\u002Foptional-dependencies.md`](references\u002Foptional-dependencies.md).\n\nMinimal package check:\n\n```bash\npython - \u003C\u003C'PY'\nimport langroid as lr\nimport langroid.language_models as lm\nprint(lr.ChatAgent, lr.Task, lr.ToolMessage)\nprint(lm.OpenAIGPTConfig().chat_model)\nPY\n```\n\nNo-network skill helper:\n\n```bash\npython scripts\u002Fcheck_langroid_environment.py --json --optional\n```\n\n## Route by task\n\n| User task shape | Read |\n| --- | --- |\n| Create a `ChatAgent`, define\u002Fenable `ToolMessage`, wire handlers, use `Task`, delegate subtasks, route recipients, configure `done_sequences`, test with `MockLM`, or debug tool\u002Ftask loops | [`sub-skills\u002Fagents-tasks-tools\u002FSKILL.md`](sub-skills\u002Fagents-tasks-tools\u002FSKILL.md) |\n| Configure OpenAI-compatible models, Azure, Gemini, LiteLLM proxy, Ollama\u002Flocal endpoints, Portkey, LangDB, HTTP clients, rotating keys, cached clients, embeddings, or model-name selection | [`sub-skills\u002Fllm-provider-config\u002FSKILL.md`](sub-skills\u002Fllm-provider-config\u002FSKILL.md) |\n| Build document QA\u002FRAG with `DocChatAgent`, parse PDFs\u002FDOCX\u002FURLs\u002FMarkdown\u002FDataFrames, tune chunking\u002Fretrieval\u002Freranking, choose vector stores or embeddings, or debug empty retrieval | [`sub-skills\u002Fretrieval-doc-chat\u002FSKILL.md`](sub-skills\u002Fretrieval-doc-chat\u002FSKILL.md) |\n| Use `TableChatAgent`, `SQLChatAgent`, `Neo4jChatAgent`, `ArangoChatAgent`, CSV-to-KG, schema metadata, database URIs, query validators, or dangerous-operation safety controls | [`sub-skills\u002Fdata-sql-graph-agents\u002FSKILL.md`](sub-skills\u002Fdata-sql-graph-agents\u002FSKILL.md) |\n| Convert MCP servers to Langroid tools, choose async\u002Fdecorator MCP patterns, enable search\u002Ffile tools, wire Chainlit callbacks, HTML logging, quiet\u002Fstatus output, or external integration smoke checks | [`sub-skills\u002Fintegrations-mcp-chainlit\u002FSKILL.md`](sub-skills\u002Fintegrations-mcp-chainlit\u002FSKILL.md) |\n\n## Operating defaults\n\n- Prefer deterministic `MockLM` or config-construction checks before making live\n  LLM\u002Fprovider calls.\n- Use the smallest optional extra needed for the workflow; do not install\n  `all` unless broad demo coverage is explicitly required.\n- Treat API keys, local LLM servers, MCP subprocess transports, Chainlit apps,\n  vector DB services, SQL\u002Fgraph databases, model downloads, OCR, and GPU\n  execution as optional live-backend work that needs explicit prerequisites.\n- Keep security defaults unless the environment is trusted:\n  `VectorStoreConfig.full_eval=False`, `TableChatAgentConfig.full_eval=False`,\n  and SQL\u002Fgraph `allow_dangerous_operations=False`.\n- Do not depend on original repo examples or tests at runtime. Use this skill's\n  bundled references and scripts.\n\n## Bundled smoke scripts\n\nRun these from this skill directory or pass their full path from another current\nworking directory:\n\n```bash\npython scripts\u002Fcheck_langroid_environment.py --json --optional\npython sub-skills\u002Fagents-tasks-tools\u002Fscripts\u002Fcore_agent_smoke.py\npython sub-skills\u002Fllm-provider-config\u002Fscripts\u002Fprovider_config_smoke.py --compact\npython sub-skills\u002Fretrieval-doc-chat\u002Fscripts\u002Frag_config_smoke.py --json\npython sub-skills\u002Fdata-sql-graph-agents\u002Fscripts\u002Fdata_agent_safety_smoke.py\npython sub-skills\u002Fintegrations-mcp-chainlit\u002Fscripts\u002Fmcp_tool_smoke.py\n```\n\nThese helpers avoid provider calls, live database queries, long-running servers,\nnetwork downloads, training, and destructive writes by default.\n\n## Cross-cutting troubleshooting\n\nStart with [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for\ninstall\u002Fimport\u002Fextras, provider credential boundaries, security defaults, and\nwhich sub-skill owns each failure surface. Use sub-skill troubleshooting files\nfor workflow-specific symptoms and recovery.\n","# Langroid Repo Skill\n\nUse this repo skill when a task names Langroid or asks for Python LLM agent\nworkflows involving `ChatAgent`, `Task`, `ToolMessage`, providers, RAG,\nstructured data agents, MCP, Chainlit, or Langroid optional extras.\n\nLangroid is a Python framework for building LLM-powered agents that use tools,\nexchange messages, delegate tasks, retrieve from documents, and integrate with\nproviders and external tool systems.\n\n## First checks\n\nRead [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) when you\nneed to decide whether this skill matches a checkout or installed package\nversion. For install and extras selection, read\n[`references\u002Finstall-and-extras.md`](references\u002Finstall-and-extras.md) and\n[`references\u002Foptional-dependencies.md`](references\u002Foptional-dependencies.md).\n\nMinimal package check:\n\n```bash\npython - \u003C\u003C'PY'\nimport langroid as lr\nimport langroid.language_models as lm\nprint(lr.ChatAgent, lr.Task, lr.ToolMessage)\nprint(lm.OpenAIGPTConfig().chat_model)\nPY\n```\n\nNo-network skill helper:\n\n```bash\npython scripts\u002Fcheck_langroid_environment.py --json --optional\n```\n\n## Route by task\n\n| User task shape | Read |\n| --- | --- |\n| Create a `ChatAgent`, define\u002Fenable `ToolMessage`, wire handlers, use `Task`, delegate subtasks, route recipients, configure `done_sequences`, test with `MockLM`, or debug tool\u002Ftask loops | [`sub-skills\u002Fagents-tasks-tools\u002FSKILL.md`](sub-skills\u002Fagents-tasks-tools\u002FSKILL.md) |\n| Configure OpenAI-compatible models, Azure, Gemini, LiteLLM proxy, Ollama\u002Flocal endpoints, Portkey, LangDB, HTTP clients, rotating keys, cached clients, embeddings, or model-name selection | [`sub-skills\u002Fllm-provider-config\u002FSKILL.md`](sub-skills\u002Fllm-provider-config\u002FSKILL.md) |\n| Build document QA\u002FRAG with `DocChatAgent`, parse PDFs\u002FDOCX\u002FURLs\u002FMarkdown\u002FDataFrames, tune chunking\u002Fretrieval\u002Freranking, choose vector stores or embeddings, or debug empty retrieval | [`sub-skills\u002Fretrieval-doc-chat\u002FSKILL.md`](sub-skills\u002Fretrieval-doc-chat\u002FSKILL.md) |\n| Use `TableChatAgent`, `SQLChatAgent`, `Neo4jChatAgent`, `ArangoChatAgent`, CSV-to-KG, schema metadata, database URIs, query validators, or dangerous-operation safety controls | [`sub-skills\u002Fdata-sql-graph-agents\u002FSKILL.md`](sub-skills\u002Fdata-sql-graph-agents\u002FSKILL.md) |\n| Convert MCP servers to Langroid tools, choose async\u002Fdecorator MCP patterns, enable search\u002Ffile tools, wire Chainlit callbacks, HTML logging, quiet\u002Fstatus output, or external integration smoke checks | [`sub-skills\u002Fintegrations-mcp-chainlit\u002FSKILL.md`](sub-skills\u002Fintegrations-mcp-chainlit\u002FSKILL.md) |\n\n## Operating defaults\n\n- Prefer deterministic `MockLM` or config-construction checks before making live\n  LLM\u002Fprovider calls.\n- Use the smallest optional extra needed for the workflow; do not install\n  `all` unless broad demo coverage is explicitly required.\n- Treat API keys, local LLM servers, MCP subprocess transports, Chainlit apps,\n  vector DB services, SQL\u002Fgraph databases, model downloads, OCR, and GPU\n  execution as optional live-backend work that needs explicit prerequisites.\n- Keep security defaults unless the environment is trusted:\n  `VectorStoreConfig.full_eval=False`, `TableChatAgentConfig.full_eval=False`,\n  and SQL\u002Fgraph `allow_dangerous_operations=False`.\n- Do not depend on original repo examples or tests at runtime. Use this skill's\n  bundled references and scripts.\n\n## Bundled smoke scripts\n\nRun these from this skill directory or pass their full path from another current\nworking directory:\n\n```bash\npython scripts\u002Fcheck_langroid_environment.py --json --optional\npython sub-skills\u002Fagents-tasks-tools\u002Fscripts\u002Fcore_agent_smoke.py\npython sub-skills\u002Fllm-provider-config\u002Fscripts\u002Fprovider_config_smoke.py --compact\npython sub-skills\u002Fretrieval-doc-chat\u002Fscripts\u002Frag_config_smoke.py --json\npython sub-skills\u002Fdata-sql-graph-agents\u002Fscripts\u002Fdata_agent_safety_smoke.py\npython sub-skills\u002Fintegrations-mcp-chainlit\u002Fscripts\u002Fmcp_tool_smoke.py\n```\n\nThese helpers avoid provider calls, live database queries, long-running servers,\nnetwork downloads, training, and destructive writes by default.\n\n## Cross-cutting troubleshooting\n\nStart with [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for\ninstall\u002Fimport\u002Fextras, provider credential boundaries, security defaults, and\nwhich sub-skill owns each failure surface. Use sub-skill troubleshooting files\nfor workflow-specific symptoms and recovery.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","03-逆向工程\u002Flangroid",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 langroid",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill langroid",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill langroid","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Flangroid\u002FSKILL.md",[48,54,58,62,66],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Finstall-and-extras.md","REFERENCE","参考文档",2868,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Flangroid\u002Freferences\u002Finstall-and-extras.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Foptional-dependencies.md",2810,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Flangroid\u002Freferences\u002Foptional-dependencies.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Frepo-provenance.md",1830,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Flangroid\u002Freferences\u002Frepo-provenance.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Frepo-routing-metadata.json",483,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Flangroid\u002Freferences\u002Frepo-routing-metadata.json",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Ftroubleshooting.md",3066,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Flangroid\u002Freferences\u002Ftroubleshooting.md",[71,79,84,91,98,105],{"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":78},"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",[],[],"2026-11-16 10:05:34",{"skillNo":80,"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":81,"categories":82,"keywords":83,"publishedAt":78},"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":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":78},"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":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":78},"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":78},"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":78},"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",[],[]]