[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F1PC26G9BR7SCD1YSP9V6Y":3,"skill-same:01M7F1PC26G9BR7SCD1YSP9V6Y":67},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7F1PC26G9BR7SCD1YSP9V6Y","core-sdk",null,"Build local mcp-agent apps with MCPApp, Agent, AgentSpec, AugmentedLLM, RequestParams, settings, secrets, decorators, and factory basics.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fmcp-agent\u002Fsub-skills\u002Fcore-sdk\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: core-sdk\ndescription: \"Build local mcp-agent apps with MCPApp, Agent, AgentSpec,\n  AugmentedLLM, RequestParams, settings, secrets, decorators, and factory\n  basics.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# core-sdk\n\nUse this sub-skill when the task is to create, configure, or debug a local `mcp-agent` application using the core Python SDK. It covers `MCPApp`, `Agent`, `AgentSpec`, `AugmentedLLM`, `RequestParams`, programmatic `Settings`, YAML config\u002Fsecrets, local function tools, human-input hooks, and the basic agent factory helpers.\n\n## Start Here\n\n1. Read `references\u002Fapi-reference.md` for verified constructor signatures, lifecycle patterns, LLM attachment, provider\u002Fmodel selection, and request parameters.\n2. Read `references\u002Fconfiguration.md` when the task involves `mcp_agent.config.yaml`, `mcp_agent.secrets.yaml`, `Settings(...)`, provider keys, or schema validation.\n3. Read `references\u002Fdecorators-and-factory.md` for `@app.tool`, `@app.async_tool`, workflow decorator basics, `AgentSpec`, `create_agent`, `create_llm`, and agent-spec loading.\n4. Read `references\u002Ftroubleshooting.md` when imports, provider extras, secrets, YAML merging, server names, async lifecycle, decorators, or `RequestParams` fail.\n5. Run `scripts\u002Fcheck_core_sdk.py --help` to see the credential-free smoke checks; run it before blaming provider credentials or network access.\n\n## Core Workflow\n\n- Create one `MCPApp` per process, preferably with an explicit `Settings` object or explicit config path for deterministic runs.\n- Enter `async with app.run() as running_app:` before using app context, configured server registry, logging, token counters, human-input hooks, or workflow decorators that depend on runtime context.\n- Define `Agent(name=..., instruction=..., server_names=[...], functions=[...], context=running_app.context)` for local agents; attach a provider implementation with `await agent.attach_llm(...)` only after provider package and credentials are available.\n- Use `RequestParams(...)` per generation to set model, model preferences, temperature, token limits, tool filtering, history, iteration count, strict mode, and reasoning effort.\n- Keep provider keys in secrets or environment variables; keep reusable server\u002Fmodel defaults in config or programmatic `Settings`.\n\n## Route Elsewhere\n\n- Route workflow pattern selection, routers\u002Forchestrators\u002Fparallel\u002Fdeep workflow design, and durable workflow strategy to sibling `workflow-patterns`.\n- Route MCP server exposure, server auth internals, FastMCP deployment, and app-as-server details to sibling `mcp-server-integration`.\n- Route CLI commands, cloud deployment, and hosted operations to sibling `cli-cloud-operations`.\n- Route Temporal worker operations and production durability to sibling `durable-execution`.\n- Route tracing\u002Fexporter\u002Fprovider-wrapper internals to sibling `observability-integrations`.\n\n## Bundled Check\n\nUse the smoke checker for local SDK validation without credentials or network:\n\n```bash\npython scripts\u002Fcheck_core_sdk.py\npython scripts\u002Fcheck_core_sdk.py --provider openai\n```\n\nThe default check imports core APIs, constructs programmatic settings, validates local function-tool annotations, registers decorators, creates an `AgentSpec`, and builds `RequestParams`. Provider checks only import the provider wrapper and report whether a key-shaped setting is present; they do not call external services.\n","# core-sdk\n\nUse this sub-skill when the task is to create, configure, or debug a local `mcp-agent` application using the core Python SDK. It covers `MCPApp`, `Agent`, `AgentSpec`, `AugmentedLLM`, `RequestParams`, programmatic `Settings`, YAML config\u002Fsecrets, local function tools, human-input hooks, and the basic agent factory helpers.\n\n## Start Here\n\n1. Read `references\u002Fapi-reference.md` for verified constructor signatures, lifecycle patterns, LLM attachment, provider\u002Fmodel selection, and request parameters.\n2. Read `references\u002Fconfiguration.md` when the task involves `mcp_agent.config.yaml`, `mcp_agent.secrets.yaml`, `Settings(...)`, provider keys, or schema validation.\n3. Read `references\u002Fdecorators-and-factory.md` for `@app.tool`, `@app.async_tool`, workflow decorator basics, `AgentSpec`, `create_agent`, `create_llm`, and agent-spec loading.\n4. Read `references\u002Ftroubleshooting.md` when imports, provider extras, secrets, YAML merging, server names, async lifecycle, decorators, or `RequestParams` fail.\n5. Run `scripts\u002Fcheck_core_sdk.py --help` to see the credential-free smoke checks; run it before blaming provider credentials or network access.\n\n## Core Workflow\n\n- Create one `MCPApp` per process, preferably with an explicit `Settings` object or explicit config path for deterministic runs.\n- Enter `async with app.run() as running_app:` before using app context, configured server registry, logging, token counters, human-input hooks, or workflow decorators that depend on runtime context.\n- Define `Agent(name=..., instruction=..., server_names=[...], functions=[...], context=running_app.context)` for local agents; attach a provider implementation with `await agent.attach_llm(...)` only after provider package and credentials are available.\n- Use `RequestParams(...)` per generation to set model, model preferences, temperature, token limits, tool filtering, history, iteration count, strict mode, and reasoning effort.\n- Keep provider keys in secrets or environment variables; keep reusable server\u002Fmodel defaults in config or programmatic `Settings`.\n\n## Route Elsewhere\n\n- Route workflow pattern selection, routers\u002Forchestrators\u002Fparallel\u002Fdeep workflow design, and durable workflow strategy to sibling `workflow-patterns`.\n- Route MCP server exposure, server auth internals, FastMCP deployment, and app-as-server details to sibling `mcp-server-integration`.\n- Route CLI commands, cloud deployment, and hosted operations to sibling `cli-cloud-operations`.\n- Route Temporal worker operations and production durability to sibling `durable-execution`.\n- Route tracing\u002Fexporter\u002Fprovider-wrapper internals to sibling `observability-integrations`.\n\n## Bundled Check\n\nUse the smoke checker for local SDK validation without credentials or network:\n\n```bash\npython scripts\u002Fcheck_core_sdk.py\npython scripts\u002Fcheck_core_sdk.py --provider openai\n```\n\nThe default check imports core APIs, constructs programmatic settings, validates local function-tool annotations, registers decorators, creates an `AgentSpec`, and builds `RequestParams`. Provider checks only import the provider wrapper and report whether a key-shaped setting is present; they do not call external services.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fmcp-agent\u002Fsub-skills\u002Fcore-sdk",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":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill core-sdk",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill core-sdk",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill core-sdk","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fmcp-agent\u002Fsub-skills\u002Fcore-sdk\u002FSKILL.md",[49,55,59,63],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fapi-reference.md","REFERENCE","参考文档",10799,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fmcp-agent\u002Fsub-skills\u002Fcore-sdk\u002Freferences\u002Fapi-reference.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fconfiguration.md",9021,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fmcp-agent\u002Fsub-skills\u002Fcore-sdk\u002Freferences\u002Fconfiguration.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fdecorators-and-factory.md",9983,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fmcp-agent\u002Fsub-skills\u002Fcore-sdk\u002Freferences\u002Fdecorators-and-factory.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Ftroubleshooting.md",10423,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fmcp-agent\u002Fsub-skills\u002Fcore-sdk\u002Freferences\u002Ftroubleshooting.md",[68,76,81,88,95,102],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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.","MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":77,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"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",[],[]]