[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Z2HNE6THFYEFVR76KEPC8":3,"skill-same:01M78Z2HNE6THFYEFVR76KEPC8":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},"01M78Z2HNE6THFYEFVR76KEPC8","agents-tools",null,"Guides LazyLLM function-call tools, ToolManager, agents, sandbox metadata, SkillManager, MCP, search, SQL, HTTP, and built-in tools.","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\u002Flazy-llm\u002Fsub-skills\u002Fagents-tools\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agents-tools\ndescription: \"Guides LazyLLM function-call tools, ToolManager, agents, sandbox\n  metadata, SkillManager, MCP, search, SQL, HTTP, and built-in tools.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# LazyLLM Agents and Tools\n\nUse this sub-skill for LazyLLM function-call tools, `fc_register`, `ToolManager`, tool metadata, sandbox flags, file parameters, built-in tools, SQL\u002FHTTP\u002Fsearch tools, `ReactAgent`, `ReWOOAgent`, `PlanAndSolveAgent`, `SkillManager`, skills CLI, and MCP integration.\n\n## Start here when\n\n- The task mentions `fc_register`, `lazyllm.tool`, `ToolManager`, `execute_in_sandbox`, tool schemas, `input_files_parm`, or `output_files_parm`.\n- The user wants to build a React\u002FReWOO\u002FPlanAndSolve agent or debug tool-calling traces.\n- The task uses `lazyllm skills` commands, `SkillManager`, repo\u002Fuser skill directories, or skills agent examples.\n- The task mentions MCP clients\u002Fservers, `deploy mcp_server`, npm\u002Fnpx, or external tool processes.\n- The task asks about built-in search, SQL manager, HTTP nodes, sandboxed execution, or PowerMemory-style examples.\n\n## Files to read\n\n- [agent-tool-workflows.md](references\u002Fagent-tool-workflows.md) for deterministic tool registration and agent planning recipes.\n- [mcp-and-skills.md](references\u002Fmcp-and-skills.md) for SkillManager, skills CLI, and MCP boundaries.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for schema, sandbox, MCP, provider, and tool-call errors.\n- [scripts\u002Ftool_agent_smoke.py](scripts\u002Ftool_agent_smoke.py) for a no-network check of tool registration metadata.\n\n## Safe workflow\n\n1. **Register\u002Finspect tools without an LLM first.** Use `fc_register` and verify metadata.\n2. **Choose agent class only after tool contracts are stable.**\n   - `ReactAgent`: iterative tool use with retries.\n   - `ReWOOAgent`: plan then solve with tool observations.\n   - `PlanAndSolveAgent`: planning and solving roles with optional separate LLMs.\n3. **Separate schema from execution.** Tool registration and schema checks are safe; executing shell, HTTP, SQL, search, or MCP tools can be side-effecting.\n4. **Treat LLM calls as optional.** Agent reasoning needs an LLM\u002Fprovider or local model configured by [model-deployment](..\u002Fmodel-deployment\u002FSKILL.md).\n5. **Treat MCP as external-process work.** Do not run npm\u002Fnpx\u002FMCP servers unless the user approves the command and environment.\n\n## Verified signatures to remember\n\n- `fc_register(f, *, rewrite_func=None, **kwargs)` registers callable tools and metadata.\n- `ToolManager(tools, return_trace=False, sandbox=None)` manages callable or named tools.\n- `SkillManager(dir=None, skills=None, max_skill_md_bytes=None, fs=None, sandbox=None)` loads LazyLLM skills.\n- `ReactAgent(llm, tools=None, max_retries=5, return_trace=False, prompt=None, stream=False, return_last_tool_calls=False, skills=None, desc='', workspace=None, sandbox=None, force_summarize=False, force_summarize_context='', keep_full_turns=0, fs=None, skills_dir=None, enable_builtin_tools=True, extra_stop_condition=None, on_max_retries=None)`.\n- `ReWOOAgent` and `PlanAndSolveAgent` accept optional `plan_llm`, `solve_llm`, `tools`, tracing, streaming, skills, sandbox, fs, and built-in tool controls.\n\n## Tool metadata facts\n\nLazyLLM tests verify:\n\n- `execute_in_sandbox` defaults to true and can be disabled.\n- `input_files_parm`, `output_files_parm`, and static `output_files` metadata are preserved.\n- unsupported `fc_register` parameters raise assertions.\n- writer\u002Fsearch\u002FSQL\u002FHTTP tools have local contract tests and should be validated before real external calls.\n\n## Handoff checklist\n\nWhen completing an agent\u002Ftool task, provide:\n\n- tool names, docstrings, parameter schema expectations, and sandbox\u002Ffile metadata,\n- whether the tool was registered and inspected without LLM calls,\n- selected agent class and LLM\u002Fbackend status,\n- explicit side-effect classification for shell, HTTP, SQL, search, MCP, or remote services,\n- local smoke command and optional\u002Funrun external verification.\n","# LazyLLM Agents and Tools\n\nUse this sub-skill for LazyLLM function-call tools, `fc_register`, `ToolManager`, tool metadata, sandbox flags, file parameters, built-in tools, SQL\u002FHTTP\u002Fsearch tools, `ReactAgent`, `ReWOOAgent`, `PlanAndSolveAgent`, `SkillManager`, skills CLI, and MCP integration.\n\n## Start here when\n\n- The task mentions `fc_register`, `lazyllm.tool`, `ToolManager`, `execute_in_sandbox`, tool schemas, `input_files_parm`, or `output_files_parm`.\n- The user wants to build a React\u002FReWOO\u002FPlanAndSolve agent or debug tool-calling traces.\n- The task uses `lazyllm skills` commands, `SkillManager`, repo\u002Fuser skill directories, or skills agent examples.\n- The task mentions MCP clients\u002Fservers, `deploy mcp_server`, npm\u002Fnpx, or external tool processes.\n- The task asks about built-in search, SQL manager, HTTP nodes, sandboxed execution, or PowerMemory-style examples.\n\n## Files to read\n\n- [agent-tool-workflows.md](references\u002Fagent-tool-workflows.md) for deterministic tool registration and agent planning recipes.\n- [mcp-and-skills.md](references\u002Fmcp-and-skills.md) for SkillManager, skills CLI, and MCP boundaries.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for schema, sandbox, MCP, provider, and tool-call errors.\n- [scripts\u002Ftool_agent_smoke.py](scripts\u002Ftool_agent_smoke.py) for a no-network check of tool registration metadata.\n\n## Safe workflow\n\n1. **Register\u002Finspect tools without an LLM first.** Use `fc_register` and verify metadata.\n2. **Choose agent class only after tool contracts are stable.**\n   - `ReactAgent`: iterative tool use with retries.\n   - `ReWOOAgent`: plan then solve with tool observations.\n   - `PlanAndSolveAgent`: planning and solving roles with optional separate LLMs.\n3. **Separate schema from execution.** Tool registration and schema checks are safe; executing shell, HTTP, SQL, search, or MCP tools can be side-effecting.\n4. **Treat LLM calls as optional.** Agent reasoning needs an LLM\u002Fprovider or local model configured by [model-deployment](..\u002Fmodel-deployment\u002FSKILL.md).\n5. **Treat MCP as external-process work.** Do not run npm\u002Fnpx\u002FMCP servers unless the user approves the command and environment.\n\n## Verified signatures to remember\n\n- `fc_register(f, *, rewrite_func=None, **kwargs)` registers callable tools and metadata.\n- `ToolManager(tools, return_trace=False, sandbox=None)` manages callable or named tools.\n- `SkillManager(dir=None, skills=None, max_skill_md_bytes=None, fs=None, sandbox=None)` loads LazyLLM skills.\n- `ReactAgent(llm, tools=None, max_retries=5, return_trace=False, prompt=None, stream=False, return_last_tool_calls=False, skills=None, desc='', workspace=None, sandbox=None, force_summarize=False, force_summarize_context='', keep_full_turns=0, fs=None, skills_dir=None, enable_builtin_tools=True, extra_stop_condition=None, on_max_retries=None)`.\n- `ReWOOAgent` and `PlanAndSolveAgent` accept optional `plan_llm`, `solve_llm`, `tools`, tracing, streaming, skills, sandbox, fs, and built-in tool controls.\n\n## Tool metadata facts\n\nLazyLLM tests verify:\n\n- `execute_in_sandbox` defaults to true and can be disabled.\n- `input_files_parm`, `output_files_parm`, and static `output_files` metadata are preserved.\n- unsupported `fc_register` parameters raise assertions.\n- writer\u002Fsearch\u002FSQL\u002FHTTP tools have local contract tests and should be validated before real external calls.\n\n## Handoff checklist\n\nWhen completing an agent\u002Ftool task, provide:\n\n- tool names, docstrings, parameter schema expectations, and sandbox\u002Ffile metadata,\n- whether the tool was registered and inspected without LLM calls,\n- selected agent class and LLM\u002Fbackend status,\n- explicit side-effect classification for shell, HTTP, SQL, search, MCP, or remote services,\n- local smoke command and optional\u002Funrun external verification.\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\u002Flazy-llm\u002Fsub-skills\u002Fagents-tools",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 agents-tools",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill agents-tools",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill agents-tools","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Fagents-tools\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fagent-tool-workflows.md","REFERENCE","参考文档",2990,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Fagents-tools\u002Freferences\u002Fagent-tool-workflows.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fmcp-and-skills.md",2039,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Fagents-tools\u002Freferences\u002Fmcp-and-skills.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",2170,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Fagents-tools\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Ftool_agent_smoke.py","SCRIPT","脚本",1856,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Fagents-tools\u002Fscripts\u002Ftool_agent_smoke.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",[],[]]