[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Z2FDMPZPS2CRKHEPJPZH6":3,"skill-same:01M78Z2FDMPZPS2CRKHEPJPZH6":79},{"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},"01M78Z2FDMPZPS2CRKHEPJPZH6","lazy-llm",null,"Guides LazyLLM low-code LLM application workflows including modules, flows, RAG, agents, tools, writer review, CLI, and deployment.","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\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: lazy-llm\ndescription: \"Guides LazyLLM low-code LLM application workflows including\n  modules, flows, RAG, agents, tools, writer review, CLI, and deployment.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# LazyLLM Repo Skill\n\nUse this skill when a task asks how to build, debug, test, or adapt **LazyLLM** applications: low-code LLM modules, composable flows, RAG\u002Fdocument pipelines, agents\u002Ftools\u002FMCP, writer\u002Freview workflows, model deployment, online providers, or the `lazyllm` CLI.\n\n## First actions for any LazyLLM task\n\n1. Read [Repository provenance](references\u002Frepo-provenance.md) if you need to decide whether this skill matches a current checkout or whether a refresh is required.\n2. Pick the focused sub-skill from the route map below before opening details.\n3. Check dependency class early. Base LazyLLM imports do not include every optional RAG, agent, model-serving, multimodal, tracing, or provider dependency.\n4. Prefer the bundled diagnostic scripts over ad hoc probes:\n   - [scripts\u002Fcheck_lazyllm_env.py](scripts\u002Fcheck_lazyllm_env.py) verifies importability, optional workflow groups, and safe CLI availability.\n   - [scripts\u002Finspect_lazyllm_surface.py](scripts\u002Finspect_lazyllm_surface.py) prints verified signatures for the main public APIs without running models or network calls.\n5. Never assume a model, provider key, vector database, parser service, Kubernetes\u002FSlurm cluster, npm MCP server, or GPU backend is available unless the user explicitly provided it.\n\n## Route map\n\n| User task or signal | Read this |\n| --- | --- |\n| Install LazyLLM, inspect extras, use `lazyllm` CLI, configure `lazyllm.config`, launcher\u002Fservice basics, components\u002Fprompters, package import failures | [core-runtime](sub-skills\u002Fcore-runtime\u002FSKILL.md) |\n| Use `TrainableModule`, `OnlineModule`, `OnlineChatModule`, `ServerModule`, deploy\u002Ffine-tune models, choose local vs online vs multimodal backend, diagnose provider\u002Fmodel type behavior | [model-deployment](sub-skills\u002Fmodel-deployment\u002FSKILL.md) |\n| Compose `pipeline`, `parallel`, `diverter`, `switch`, `ifs`, `loop`, `bind`, or traceable application graphs | [flow-orchestration](sub-skills\u002Fflow-orchestration\u002FSKILL.md) |\n| Build RAG\u002Fdocument workflows with `Document`, `DocNode`, readers, transforms, retrievers, rerankers, BM25, vector stores, parser service, Milvus\u002FOpenSearch | [rag-document-processing](sub-skills\u002Frag-document-processing\u002FSKILL.md) |\n| Register function-call tools, use `ToolManager`, build React\u002FReWOO\u002FPlanAndSolve agents, use sandbox flags, SQL\u002FHTTP\u002Fsearch tools, SkillManager, MCP | [agents-tools](sub-skills\u002Fagents-tools\u002FSKILL.md) |\n| Use writer IR\u002Fartifacts, writer tools, revision\u002Fstream utilities, Feishu adapter boundaries, `lazyllm review` or local review workflows | [writer-review](sub-skills\u002Fwriter-review\u002FSKILL.md) |\n\n## Installation and extras quick guide\n\nRead [Installation and optional extras](references\u002Finstallation-and-extras.md) for the full matrix. Typical choices:\n\n```bash\npython -m pip install lazyllm\nlazyllm install rag              # document\u002FRAG imports\nlazyllm install agent-advanced   # MCP\u002Fadvanced agent dependencies\nlazyllm install standard         # broad app stack; may install heavy model\u002Fvector packages\nlazyllm install full             # all optional stacks; use only when explicitly needed\n```\n\nFor a source checkout, use an editable install with a supported Python (`>=3.10,\u003C3.14`) and then install only the extras required by the selected workflow. Do not install `full` just to answer a base CLI\u002Fconfig\u002Fflow question.\n\nMinimal no-network smoke check:\n\n```bash\npython scripts\u002Fcheck_lazyllm_env.py --require-rag --require-agent --require-writer\n```\n\nRun that command from inside this skill directory after copying or locating the script, or pass the script path explicitly from any working directory. It only imports LazyLLM modules and does not call a provider.\n\n## High-signal API surfaces\n\nRead [API surface map](references\u002Fapi-surface-map.md) when a task names a class\u002Ffunction or when you need exact routing. Verified public entry points include:\n\n- `lazyllm.pipeline`, `parallel`, `diverter`, `switch`, `ifs`, `loop`, `bind`\n- `TrainableModule`, `OnlineModule`, `OnlineChatModule`, `ServerModule`, `ActionModule`\n- `Document`, `Retriever`, `Reranker`, `DocNode`, BM25 and store\u002Findex helpers\n- `fc_register`, `ToolManager`, `SkillManager`, `ReactAgent`, `ReWOOAgent`, `PlanAndSolveAgent`\n- writer artifact models and `WriterToolBase`\n- CLI commands: `install`, `deploy`, `run`, `skills`, `review`, `review-local`\n\n## Backend and safety policy\n\n- **Safe by default**: import checks, config\u002FCLI inspection, flow graphs with Python callables, BM25\u002Flocal RAG smoke, writer artifact round trips, tool schema registration.\n- **Ask or require explicit evidence**: cloud provider calls, model downloads, local GPU serving\u002Ffine-tuning, multimodal generation, external vector databases, parser-service workers, MCP servers launched through `npx`\u002Fnpm, Kubernetes\u002FSlurm\u002FSCO jobs, PR posting.\n- **Do not post or mutate remote systems** from review, MCP, Feishu, database, or provider helpers unless the user asks for that side effect and provides credentials.\n\n## Troubleshooting shortcuts\n\nStart with [cross-cutting troubleshooting](references\u002Ftroubleshooting.md), then the owning sub-skill's troubleshooting file. Common LazyLLM symptoms:\n\n- `ImportError: Missing package(s): ... You can install them by: lazyllm install rag` → read the RAG or install reference; install the exact extra, not `full`, unless the task needs heavy backends.\n- `lazyllm --help` exits with a usage error → this CLI prints usage from its dispatcher; use concrete subcommands such as `lazyllm skills list` or inspect the command table in [core-runtime](sub-skills\u002Fcore-runtime\u002FSKILL.md).\n- Provider\u002FAPI-key errors → route to [model-deployment](sub-skills\u002Fmodel-deployment\u002FSKILL.md) and keep provider tests optional.\n- Flow result mismatch → route to [flow-orchestration](sub-skills\u002Fflow-orchestration\u002FSKILL.md) and verify `bind`, skip\u002Fkept items, and input tuple handling.\n\n## When not to use this skill\n\nDo not use this skill for generic LLM theory, non-LazyLLM frameworks, model architecture research unrelated to LazyLLM modules, or direct production deployment to a user cluster without first checking the model-deployment and core runtime dependency\u002Fback-end constraints.\n","# LazyLLM Repo Skill\n\nUse this skill when a task asks how to build, debug, test, or adapt **LazyLLM** applications: low-code LLM modules, composable flows, RAG\u002Fdocument pipelines, agents\u002Ftools\u002FMCP, writer\u002Freview workflows, model deployment, online providers, or the `lazyllm` CLI.\n\n## First actions for any LazyLLM task\n\n1. Read [Repository provenance](references\u002Frepo-provenance.md) if you need to decide whether this skill matches a current checkout or whether a refresh is required.\n2. Pick the focused sub-skill from the route map below before opening details.\n3. Check dependency class early. Base LazyLLM imports do not include every optional RAG, agent, model-serving, multimodal, tracing, or provider dependency.\n4. Prefer the bundled diagnostic scripts over ad hoc probes:\n   - [scripts\u002Fcheck_lazyllm_env.py](scripts\u002Fcheck_lazyllm_env.py) verifies importability, optional workflow groups, and safe CLI availability.\n   - [scripts\u002Finspect_lazyllm_surface.py](scripts\u002Finspect_lazyllm_surface.py) prints verified signatures for the main public APIs without running models or network calls.\n5. Never assume a model, provider key, vector database, parser service, Kubernetes\u002FSlurm cluster, npm MCP server, or GPU backend is available unless the user explicitly provided it.\n\n## Route map\n\n| User task or signal | Read this |\n| --- | --- |\n| Install LazyLLM, inspect extras, use `lazyllm` CLI, configure `lazyllm.config`, launcher\u002Fservice basics, components\u002Fprompters, package import failures | [core-runtime](sub-skills\u002Fcore-runtime\u002FSKILL.md) |\n| Use `TrainableModule`, `OnlineModule`, `OnlineChatModule`, `ServerModule`, deploy\u002Ffine-tune models, choose local vs online vs multimodal backend, diagnose provider\u002Fmodel type behavior | [model-deployment](sub-skills\u002Fmodel-deployment\u002FSKILL.md) |\n| Compose `pipeline`, `parallel`, `diverter`, `switch`, `ifs`, `loop`, `bind`, or traceable application graphs | [flow-orchestration](sub-skills\u002Fflow-orchestration\u002FSKILL.md) |\n| Build RAG\u002Fdocument workflows with `Document`, `DocNode`, readers, transforms, retrievers, rerankers, BM25, vector stores, parser service, Milvus\u002FOpenSearch | [rag-document-processing](sub-skills\u002Frag-document-processing\u002FSKILL.md) |\n| Register function-call tools, use `ToolManager`, build React\u002FReWOO\u002FPlanAndSolve agents, use sandbox flags, SQL\u002FHTTP\u002Fsearch tools, SkillManager, MCP | [agents-tools](sub-skills\u002Fagents-tools\u002FSKILL.md) |\n| Use writer IR\u002Fartifacts, writer tools, revision\u002Fstream utilities, Feishu adapter boundaries, `lazyllm review` or local review workflows | [writer-review](sub-skills\u002Fwriter-review\u002FSKILL.md) |\n\n## Installation and extras quick guide\n\nRead [Installation and optional extras](references\u002Finstallation-and-extras.md) for the full matrix. Typical choices:\n\n```bash\npython -m pip install lazyllm\nlazyllm install rag              # document\u002FRAG imports\nlazyllm install agent-advanced   # MCP\u002Fadvanced agent dependencies\nlazyllm install standard         # broad app stack; may install heavy model\u002Fvector packages\nlazyllm install full             # all optional stacks; use only when explicitly needed\n```\n\nFor a source checkout, use an editable install with a supported Python (`>=3.10,\u003C3.14`) and then install only the extras required by the selected workflow. Do not install `full` just to answer a base CLI\u002Fconfig\u002Fflow question.\n\nMinimal no-network smoke check:\n\n```bash\npython scripts\u002Fcheck_lazyllm_env.py --require-rag --require-agent --require-writer\n```\n\nRun that command from inside this skill directory after copying or locating the script, or pass the script path explicitly from any working directory. It only imports LazyLLM modules and does not call a provider.\n\n## High-signal API surfaces\n\nRead [API surface map](references\u002Fapi-surface-map.md) when a task names a class\u002Ffunction or when you need exact routing. Verified public entry points include:\n\n- `lazyllm.pipeline`, `parallel`, `diverter`, `switch`, `ifs`, `loop`, `bind`\n- `TrainableModule`, `OnlineModule`, `OnlineChatModule`, `ServerModule`, `ActionModule`\n- `Document`, `Retriever`, `Reranker`, `DocNode`, BM25 and store\u002Findex helpers\n- `fc_register`, `ToolManager`, `SkillManager`, `ReactAgent`, `ReWOOAgent`, `PlanAndSolveAgent`\n- writer artifact models and `WriterToolBase`\n- CLI commands: `install`, `deploy`, `run`, `skills`, `review`, `review-local`\n\n## Backend and safety policy\n\n- **Safe by default**: import checks, config\u002FCLI inspection, flow graphs with Python callables, BM25\u002Flocal RAG smoke, writer artifact round trips, tool schema registration.\n- **Ask or require explicit evidence**: cloud provider calls, model downloads, local GPU serving\u002Ffine-tuning, multimodal generation, external vector databases, parser-service workers, MCP servers launched through `npx`\u002Fnpm, Kubernetes\u002FSlurm\u002FSCO jobs, PR posting.\n- **Do not post or mutate remote systems** from review, MCP, Feishu, database, or provider helpers unless the user asks for that side effect and provides credentials.\n\n## Troubleshooting shortcuts\n\nStart with [cross-cutting troubleshooting](references\u002Ftroubleshooting.md), then the owning sub-skill's troubleshooting file. Common LazyLLM symptoms:\n\n- `ImportError: Missing package(s): ... You can install them by: lazyllm install rag` → read the RAG or install reference; install the exact extra, not `full`, unless the task needs heavy backends.\n- `lazyllm --help` exits with a usage error → this CLI prints usage from its dispatcher; use concrete subcommands such as `lazyllm skills list` or inspect the command table in [core-runtime](sub-skills\u002Fcore-runtime\u002FSKILL.md).\n- Provider\u002FAPI-key errors → route to [model-deployment](sub-skills\u002Fmodel-deployment\u002FSKILL.md) and keep provider tests optional.\n- Flow result mismatch → route to [flow-orchestration](sub-skills\u002Fflow-orchestration\u002FSKILL.md) and verify `bind`, skip\u002Fkept items, and input tuple handling.\n\n## When not to use this skill\n\nDo not use this skill for generic LLM theory, non-LazyLLM frameworks, model architecture research unrelated to LazyLLM modules, or direct production deployment to a user cluster without first checking the model-deployment and core runtime dependency\u002Fback-end constraints.\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",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 lazy-llm",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill lazy-llm",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill lazy-llm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002FSKILL.md",[47,53,57,61,65,69,75],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-surface-map.md","REFERENCE","参考文档",6413,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Freferences\u002Fapi-surface-map.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Finstallation-and-extras.md",4664,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Freferences\u002Finstallation-and-extras.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-provenance.md",3175,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Freferences\u002Frepo-provenance.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frepo-routing-metadata.json",484,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Freferences\u002Frepo-routing-metadata.json",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",4557,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fcheck_lazyllm_env.py","SCRIPT","脚本",6017,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fscripts\u002Fcheck_lazyllm_env.py",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Finspect_lazyllm_surface.py",3912,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fscripts\u002Finspect_lazyllm_surface.py",[80,87,94,101,108,115],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"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":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"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":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"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",[],[]]