[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZY4ATW2FPRZ61MWSRCMA3":3,"skill-same:01M78ZY4ATW2FPRZ61MWSRCMA3":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78ZY4ATW2FPRZ61MWSRCMA3","mcp-agent",null,"Build, compose, serve, operate, and troubleshoot mcp-agent applications, workflows, MCP servers, Temporal workers, CLI\u002Fcloud deployments, and observability integrations.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmcp-agent\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mcp-agent\ndescription: \"Build, compose, serve, operate, and troubleshoot mcp-agent\n  applications, workflows, MCP servers, Temporal workers, CLI\u002Fcloud deployments,\n  and observability integrations.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# mcp-agent\n\nUse this repo skill when a task involves the `mcp-agent` Python package or its CLIs: building MCP-enabled agents, composing effective workflow patterns, exposing applications as MCP servers, operating MCP Agent Cloud, using Temporal durability, or configuring logging\u002Ftracing\u002Fintegrations.\n\n## First Checks\n\n1. Confirm the package is available with `python -c \"import mcp_agent; print(mcp_agent.__name__)\"` or install it with `pip install \"mcp-agent\"` \u002F `uv add \"mcp-agent\"`.\n2. Add optional extras only for the selected workflow: `mcp-agent[openai]`, `[anthropic]`, `[google]`, `[azure]`, `[bedrock]`, `[cohere]`, `[temporal]`, `[langchain]`, `[crewai]`, or `[redis]`.\n3. Keep secrets in `mcp_agent.secrets.yaml`, environment variables, or deployment secret handles; keep reusable defaults in `mcp_agent.config.yaml` or a `Settings` object.\n4. Read `references\u002Frepo-provenance.md` before deciding whether this skill matches a checkout or whether `refresh-repo-skill` is needed.\n5. Read `references\u002Ftroubleshooting.md` for cross-cutting install, import, config, optional dependency, CLI, and service failures.\n\n## Route by Task\n\n- **Core SDK and app code:** use `sub-skills\u002Fcore-sdk\u002FSKILL.md` for `MCPApp`, `Agent`, `AgentSpec`, `AugmentedLLM`, `RequestParams`, settings, secrets, local function tools, decorators, and factory basics.\n- **Workflow composition:** use `sub-skills\u002Fworkflow-patterns\u002FSKILL.md` for routers, intent classifiers, parallel fan-out\u002Ffan-in, orchestrators, deep orchestrators, evaluator-optimizer loops, swarms, and structured outputs.\n- **MCP server integration:** use `sub-skills\u002Fmcp-server-integration\u002FSKILL.md` for upstream MCP server config, transports, roots, sampling, elicitation, OAuth\u002Fauth, `create_mcp_server_for_app`, and app-as-server validation.\n- **CLI and Cloud operations:** use `sub-skills\u002Fcli-cloud-operations\u002FSKILL.md` for `mcp-agent`, `mcp-cloud`, `mcpc`, project scaffolding, diagnostics, local dev commands, deploy, logs, env\u002Fsecrets, workflows, and client install.\n- **Durable execution:** use `sub-skills\u002Fdurable-execution\u002FSKILL.md` when workflows need Temporal workers, long-running tools, pause\u002Fresume, signals, retry policies, activity registration, or service-backed durability.\n- **Observability and integrations:** use `sub-skills\u002Fobservability-integrations\u002FSKILL.md` for logger transports, OpenTelemetry, token accounting, progress\u002Fstreaming, provider extras, LM Studio\u002Flocal endpoints, LangChain, and CrewAI adapters.\n\n## Common Decision Points\n\n- Start with `core-sdk` when the user asks to create or debug Python application code; route to `workflow-patterns` only after the app\u002Fagent basics are clear.\n- Route to `mcp-server-integration` when the words are about MCP transports, server config, app-as-server behavior, OAuth, resources, prompts, sampling, roots, elicitation, or client\u002Fserver tool surfaces.\n- Route to `cli-cloud-operations` when the task is command syntax, scaffolding, config checks, deployments, logs, hosted app state, environment secrets, or installing a server into Claude Code\u002FCursor\u002FVS Code\u002FChatGPT clients.\n- Route to `durable-execution` when the user already has or wants a workflow that must survive restarts, pause for human input, receive signals, or run in a Temporal worker.\n- Route to `observability-integrations` when failures involve provider wrapper imports, OpenTelemetry exporters, token counters, JSONL event logs, streaming events, local model endpoints, or LangChain\u002FCrewAI adapters.\n\n## Safe Validation Helpers\n\n- `sub-skills\u002Fcore-sdk\u002Fscripts\u002Fcheck_core_sdk.py` checks imports, signatures, local tools, decorators, `AgentSpec`, and `RequestParams` without credentials or network.\n- `sub-skills\u002Fworkflow-patterns\u002Fscripts\u002Fcheck_workflow_imports.py` verifies canonical workflow imports and class names such as `LLMRouter`.\n- `sub-skills\u002Fmcp-server-integration\u002Fscripts\u002Fvalidate_server_config.py` checks MCP server config shape and optional executable availability.\n- `sub-skills\u002Fcli-cloud-operations\u002Fscripts\u002Fcollect_cli_help.py` collects safe `--help` snapshots without deploy\u002Flogin\u002Finstall side effects.\n- `sub-skills\u002Fdurable-execution\u002Fscripts\u002Fcheck_temporal_config.py` validates Temporal config statically without starting a worker.\n- `sub-skills\u002Fobservability-integrations\u002Fscripts\u002Fcheck_observability_config.py` and `sub-skills\u002Fobservability-integrations\u002Fscripts\u002Fsummarize_event_log.py` inspect logger\u002FOTEL config and JSONL event logs safely.\n\n## Safety Notes\n\n- Do not run Cloud deployment, client install writes, env secret mutation, workflow resume\u002Fcancel, or public server transports unless the user explicitly intends mutation.\n- Do not assume optional provider SDKs, Temporal, Redis, LangChain, CrewAI, or cloud credentials are present in a base install; install and validate the smallest extra needed.\n- Do not paste API keys or secret handles into generated code, logs, support transcripts, or client snippets.\n- Prefer read-only `--help`, config validation, bundled checker scripts, import checks, and dry-run\u002Fstatic modes before starting services or calling external providers.\n","# mcp-agent\n\nUse this repo skill when a task involves the `mcp-agent` Python package or its CLIs: building MCP-enabled agents, composing effective workflow patterns, exposing applications as MCP servers, operating MCP Agent Cloud, using Temporal durability, or configuring logging\u002Ftracing\u002Fintegrations.\n\n## First Checks\n\n1. Confirm the package is available with `python -c \"import mcp_agent; print(mcp_agent.__name__)\"` or install it with `pip install \"mcp-agent\"` \u002F `uv add \"mcp-agent\"`.\n2. Add optional extras only for the selected workflow: `mcp-agent[openai]`, `[anthropic]`, `[google]`, `[azure]`, `[bedrock]`, `[cohere]`, `[temporal]`, `[langchain]`, `[crewai]`, or `[redis]`.\n3. Keep secrets in `mcp_agent.secrets.yaml`, environment variables, or deployment secret handles; keep reusable defaults in `mcp_agent.config.yaml` or a `Settings` object.\n4. Read `references\u002Frepo-provenance.md` before deciding whether this skill matches a checkout or whether `refresh-repo-skill` is needed.\n5. Read `references\u002Ftroubleshooting.md` for cross-cutting install, import, config, optional dependency, CLI, and service failures.\n\n## Route by Task\n\n- **Core SDK and app code:** use `sub-skills\u002Fcore-sdk\u002FSKILL.md` for `MCPApp`, `Agent`, `AgentSpec`, `AugmentedLLM`, `RequestParams`, settings, secrets, local function tools, decorators, and factory basics.\n- **Workflow composition:** use `sub-skills\u002Fworkflow-patterns\u002FSKILL.md` for routers, intent classifiers, parallel fan-out\u002Ffan-in, orchestrators, deep orchestrators, evaluator-optimizer loops, swarms, and structured outputs.\n- **MCP server integration:** use `sub-skills\u002Fmcp-server-integration\u002FSKILL.md` for upstream MCP server config, transports, roots, sampling, elicitation, OAuth\u002Fauth, `create_mcp_server_for_app`, and app-as-server validation.\n- **CLI and Cloud operations:** use `sub-skills\u002Fcli-cloud-operations\u002FSKILL.md` for `mcp-agent`, `mcp-cloud`, `mcpc`, project scaffolding, diagnostics, local dev commands, deploy, logs, env\u002Fsecrets, workflows, and client install.\n- **Durable execution:** use `sub-skills\u002Fdurable-execution\u002FSKILL.md` when workflows need Temporal workers, long-running tools, pause\u002Fresume, signals, retry policies, activity registration, or service-backed durability.\n- **Observability and integrations:** use `sub-skills\u002Fobservability-integrations\u002FSKILL.md` for logger transports, OpenTelemetry, token accounting, progress\u002Fstreaming, provider extras, LM Studio\u002Flocal endpoints, LangChain, and CrewAI adapters.\n\n## Common Decision Points\n\n- Start with `core-sdk` when the user asks to create or debug Python application code; route to `workflow-patterns` only after the app\u002Fagent basics are clear.\n- Route to `mcp-server-integration` when the words are about MCP transports, server config, app-as-server behavior, OAuth, resources, prompts, sampling, roots, elicitation, or client\u002Fserver tool surfaces.\n- Route to `cli-cloud-operations` when the task is command syntax, scaffolding, config checks, deployments, logs, hosted app state, environment secrets, or installing a server into Claude Code\u002FCursor\u002FVS Code\u002FChatGPT clients.\n- Route to `durable-execution` when the user already has or wants a workflow that must survive restarts, pause for human input, receive signals, or run in a Temporal worker.\n- Route to `observability-integrations` when failures involve provider wrapper imports, OpenTelemetry exporters, token counters, JSONL event logs, streaming events, local model endpoints, or LangChain\u002FCrewAI adapters.\n\n## Safe Validation Helpers\n\n- `sub-skills\u002Fcore-sdk\u002Fscripts\u002Fcheck_core_sdk.py` checks imports, signatures, local tools, decorators, `AgentSpec`, and `RequestParams` without credentials or network.\n- `sub-skills\u002Fworkflow-patterns\u002Fscripts\u002Fcheck_workflow_imports.py` verifies canonical workflow imports and class names such as `LLMRouter`.\n- `sub-skills\u002Fmcp-server-integration\u002Fscripts\u002Fvalidate_server_config.py` checks MCP server config shape and optional executable availability.\n- `sub-skills\u002Fcli-cloud-operations\u002Fscripts\u002Fcollect_cli_help.py` collects safe `--help` snapshots without deploy\u002Flogin\u002Finstall side effects.\n- `sub-skills\u002Fdurable-execution\u002Fscripts\u002Fcheck_temporal_config.py` validates Temporal config statically without starting a worker.\n- `sub-skills\u002Fobservability-integrations\u002Fscripts\u002Fcheck_observability_config.py` and `sub-skills\u002Fobservability-integrations\u002Fscripts\u002Fsummarize_event_log.py` inspect logger\u002FOTEL config and JSONL event logs safely.\n\n## Safety Notes\n\n- Do not run Cloud deployment, client install writes, env secret mutation, workflow resume\u002Fcancel, or public server transports unless the user explicitly intends mutation.\n- Do not assume optional provider SDKs, Temporal, Redis, LangChain, CrewAI, or cloud credentials are present in a base install; install and validate the smallest extra needed.\n- Do not paste API keys or secret handles into generated code, logs, support transcripts, or client snippets.\n- Prefer read-only `--help`, config validation, bundled checker scripts, import checks, and dry-run\u002Fstatic modes before starting services or calling external providers.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fmcp-agent",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill mcp-agent",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill mcp-agent",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill mcp-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmcp-agent\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Frepo-provenance.md","REFERENCE","参考文档",2660,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmcp-agent\u002Freferences\u002Frepo-provenance.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-routing-metadata.json",496,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmcp-agent\u002Freferences\u002Frepo-routing-metadata.json",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",4519,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmcp-agent\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_mcp_agent_environment.py","SCRIPT","脚本",5105,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmcp-agent\u002Fscripts\u002Fcheck_mcp_agent_environment.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]