[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M753KW7FE80XSDBVFFY06NFM":3,"skill-same:01M753KW7FE80XSDBVFFY06NFM":74},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M753KW7FE80XSDBVFFY06NFM","agents-tools-and-streaming",null,"Use AdalFlow Agent, Runner, ReActAgent, FunctionTool, ToolManager, streaming events, permissions, and MCP tools safely.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fadalflow\u002Fsub-skills\u002Fagents-tools-and-streaming\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: agents-tools-and-streaming\ndescription: \"Use AdalFlow Agent, Runner, ReActAgent, FunctionTool, ToolManager,\n  streaming events, permissions, and MCP tools safely.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Agents, Tools, and Streaming\n\nUse this sub-skill when the task involves AdalFlow agent execution, tool wrapping, tool calling, streaming run events, human approval for tools, or MCP-served tools.\n\n## Route here for\n\n- Wrapping Python callables as `FunctionTool`, including sync, async, sync-generator, async-generator, and bound-method tools.\n- Inspecting or constructing `FunctionDefinition`, `Function`, `FunctionExpression`, `FunctionOutput`, or `ToolOutput` values.\n- Building a `ToolManager`, parsing function expressions, or executing tool calls directly.\n- Constructing `Agent`, `Runner`, or legacy `ReActAgent` workflows after the model client \u002F generator setup is known.\n- Calling `Runner.call`, `Runner.acall`, or `Runner.astream` and consuming `RunnerResult`, step history, and stream events.\n- Adding human-in-the-loop approvals through `PermissionManager`, CLI\u002FFastAPI handlers, `require_approval`, or pre-execution confirmation details.\n- Integrating MCP tools through MCP server parameter dataclasses, `MCPFunctionTool`, and `MCPToolManager`.\n\n## Route elsewhere\n\n- Model client, provider credentials, `Generator`, prompt\u002Fmodel kwargs, and provider streaming setup belong to `model-client-and-generator-workflows`.\n- DataClass schemas, parser design, and general structured output repair belong to `core-components-and-structured-io` unless the schema is specifically an agent final `answer_data_type`.\n- Retrieval\u002FRAG tools belong to `retrieval-rag-and-data-pipelines` before wrapping them for agent use here.\n- Tracing spans, logs, MLflow, and persistent observability belong to `tracing-observability-and-configuration`.\n- Training and optimizer behavior for agents\u002Ftools belongs to `evaluation-and-optimization`.\n\n## Read these references\n\n1. [references\u002Fagents-and-tools.md](references\u002Fagents-and-tools.md) for `FunctionTool`, `ToolManager`, `Agent`, `Runner`, `ReActAgent`, tool outputs, and fake-planner testing.\n2. [references\u002Fstreaming-and-run-results.md](references\u002Fstreaming-and-run-results.md) for `RunnerResult`, `StepOutput`, streaming event types, and robust event consumption loops.\n3. [references\u002Fmcp-and-permissions.md](references\u002Fmcp-and-permissions.md) for tool approval flows, permission handlers, and MCP manager\u002Fserver parameter patterns.\n4. [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for unsafe tools, missing annotations, async-loop issues, result formatting, max-step exhaustion, finalization, permission denials, stream consumption, and missing MCP dependencies.\n\n## Safe bundled checks\n\n- `python scripts\u002Ffunction_tool_smoke.py` verifies service-free `FunctionTool` and `ToolManager` behavior.\n- `python scripts\u002Fagent_runner_fake_planner_smoke.py` verifies `Agent` + `Runner` sync, async, streaming, and permission behavior with a fake planner and no provider calls.\n\nRun these only in an environment where `adalflow` is importable. They do not require API keys, network services, provider calls, or MCP servers.\n","# Agents, Tools, and Streaming\n\nUse this sub-skill when the task involves AdalFlow agent execution, tool wrapping, tool calling, streaming run events, human approval for tools, or MCP-served tools.\n\n## Route here for\n\n- Wrapping Python callables as `FunctionTool`, including sync, async, sync-generator, async-generator, and bound-method tools.\n- Inspecting or constructing `FunctionDefinition`, `Function`, `FunctionExpression`, `FunctionOutput`, or `ToolOutput` values.\n- Building a `ToolManager`, parsing function expressions, or executing tool calls directly.\n- Constructing `Agent`, `Runner`, or legacy `ReActAgent` workflows after the model client \u002F generator setup is known.\n- Calling `Runner.call`, `Runner.acall`, or `Runner.astream` and consuming `RunnerResult`, step history, and stream events.\n- Adding human-in-the-loop approvals through `PermissionManager`, CLI\u002FFastAPI handlers, `require_approval`, or pre-execution confirmation details.\n- Integrating MCP tools through MCP server parameter dataclasses, `MCPFunctionTool`, and `MCPToolManager`.\n\n## Route elsewhere\n\n- Model client, provider credentials, `Generator`, prompt\u002Fmodel kwargs, and provider streaming setup belong to `model-client-and-generator-workflows`.\n- DataClass schemas, parser design, and general structured output repair belong to `core-components-and-structured-io` unless the schema is specifically an agent final `answer_data_type`.\n- Retrieval\u002FRAG tools belong to `retrieval-rag-and-data-pipelines` before wrapping them for agent use here.\n- Tracing spans, logs, MLflow, and persistent observability belong to `tracing-observability-and-configuration`.\n- Training and optimizer behavior for agents\u002Ftools belongs to `evaluation-and-optimization`.\n\n## Read these references\n\n1. [references\u002Fagents-and-tools.md](references\u002Fagents-and-tools.md) for `FunctionTool`, `ToolManager`, `Agent`, `Runner`, `ReActAgent`, tool outputs, and fake-planner testing.\n2. [references\u002Fstreaming-and-run-results.md](references\u002Fstreaming-and-run-results.md) for `RunnerResult`, `StepOutput`, streaming event types, and robust event consumption loops.\n3. [references\u002Fmcp-and-permissions.md](references\u002Fmcp-and-permissions.md) for tool approval flows, permission handlers, and MCP manager\u002Fserver parameter patterns.\n4. [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for unsafe tools, missing annotations, async-loop issues, result formatting, max-step exhaustion, finalization, permission denials, stream consumption, and missing MCP dependencies.\n\n## Safe bundled checks\n\n- `python scripts\u002Ffunction_tool_smoke.py` verifies service-free `FunctionTool` and `ToolManager` behavior.\n- `python scripts\u002Fagent_runner_fake_planner_smoke.py` verifies `Agent` + `Runner` sync, async, streaming, and permission behavior with a fake planner and no provider calls.\n\nRun these only in an environment where `adalflow` is importable. They do not require API keys, network services, provider calls, or MCP servers.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fadalflow\u002Fsub-skills\u002Fagents-tools-and-streaming",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill agents-tools-and-streaming",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill agents-tools-and-streaming",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill agents-tools-and-streaming","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fadalflow\u002Fsub-skills\u002Fagents-tools-and-streaming\u002FSKILL.md",[46,52,56,60,64,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fagents-and-tools.md","REFERENCE","参考文档",9705,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fadalflow\u002Fsub-skills\u002Fagents-tools-and-streaming\u002Freferences\u002Fagents-and-tools.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fmcp-and-permissions.md",9978,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fadalflow\u002Fsub-skills\u002Fagents-tools-and-streaming\u002Freferences\u002Fmcp-and-permissions.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fstreaming-and-run-results.md",9121,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fadalflow\u002Fsub-skills\u002Fagents-tools-and-streaming\u002Freferences\u002Fstreaming-and-run-results.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",11903,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fadalflow\u002Fsub-skills\u002Fagents-tools-and-streaming\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fagent_runner_fake_planner_smoke.py","SCRIPT","脚本",6857,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fadalflow\u002Fsub-skills\u002Fagents-tools-and-streaming\u002Fscripts\u002Fagent_runner_fake_planner_smoke.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Ffunction_tool_smoke.py",4520,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fadalflow\u002Fsub-skills\u002Fagents-tools-and-streaming\u002Fscripts\u002Ffunction_tool_smoke.py",[75,84,91,98,105,112],{"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":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":83},"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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":83},"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":83},"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":83},"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":83},"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":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":83},"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",[],[]]