[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Z2MPHSQB1VT1T4J9C5XBW":3,"skill-same:01M78Z2MPHSQB1VT1T4J9C5XBW":63},{"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},"01M78Z2MPHSQB1VT1T4J9C5XBW","core-runtime",null,"Guides LazyLLM installation, optional extras, CLI commands, configuration, launcher, components, prompters, and base runtime diagnostics.","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\u002Fcore-runtime\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: core-runtime\ndescription: \"Guides LazyLLM installation, optional extras, CLI commands,\n  configuration, launcher, components, prompters, and base runtime diagnostics.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# LazyLLM Core Runtime\n\nUse this sub-skill for base LazyLLM setup and runtime questions: package installation, optional extras, CLI command routing, `lazyllm.config`, namespace behavior, launchers, components\u002Fregistries, prompters, dependency diagnostics, and safe source-checkout smoke tests.\n\n## Start here when\n\n- The user asks to install LazyLLM or choose between base, `rag`, `standard`, `full`, `dev`, or backend-specific extras.\n- An import error names missing optional packages or `lazyllm install \u003Cextra>`.\n- The task mentions `lazyllm` CLI commands: `install`, `deploy`, `run`, `skills`, `review`, or `review-local`.\n- The task concerns `lazyllm.config`, environment-backed options, `lazyllm.namespace`, `ComponentBase`, component registration, prompt templates, or launcher\u002Fservice scaffolding.\n- You need a no-network check before moving to RAG, agents, models, writer, or flows.\n\n## Files to read\n\n- [config-cli-components.md](references\u002Fconfig-cli-components.md) for CLI command families, config behavior, prompters, components, and launcher notes.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for core install\u002Fimport\u002FCLI\u002Fconfig failure modes.\n- Root [Installation and optional extras](..\u002F..\u002Freferences\u002Finstallation-and-extras.md) for extra selection across workflows.\n- [scripts\u002Fconfig_cli_smoke.py](scripts\u002Fconfig_cli_smoke.py) for a safe local smoke check of config, prompt, component registration, and CLI command table assumptions.\n\n## Core workflow checklist\n\n1. **Identify the selected workflow.** If the task is only config\u002FCLI\u002Fimport, keep it here. If it needs a domain feature, route onward after checking dependencies:\n   - RAG\u002Fdocument import → [rag-document-processing](..\u002Frag-document-processing\u002FSKILL.md)\n   - Agents\u002Ftools\u002FMCP → [agents-tools](..\u002Fagents-tools\u002FSKILL.md)\n   - Model serving\u002Fprovider\u002Ffine-tuning → [model-deployment](..\u002Fmodel-deployment\u002FSKILL.md)\n   - Flow composition → [flow-orchestration](..\u002Fflow-orchestration\u002FSKILL.md)\n   - Writer\u002Freview → [writer-review](..\u002Fwriter-review\u002FSKILL.md)\n2. **Check Python and install state.** LazyLLM 0.7.5 expects Python `>=3.10,\u003C3.14`.\n3. **Run a safe import\u002FCLI diagnostic** when environment state is unclear:\n   ```bash\n   python ..\u002F..\u002Fscripts\u002Fcheck_lazyllm_env.py --check-cli\n   python scripts\u002Fconfig_cli_smoke.py\n   ```\n4. **Install the smallest extra** named by the failure. For example, RAG import failures usually require `lazyllm install rag`, not `full`.\n5. **Avoid side effects.** Core runtime checks should not download models, call providers, start external services, or post reviews.\n\n## CLI command families\n\nThe dispatcher recognizes these top-level commands:\n\n```text\nlazyllm install \u003Cextra1> \u003Cextra2> \u003Cpkg1> ...\nlazyllm deploy modelname\nlazyllm deploy mcp_server \u003Ccommand> [args ...] [options]\nlazyllm run graph.json\nlazyllm run chatbot\nlazyllm run rag\nlazyllm skills init\u002Flist\u002Finfo\u002Fdelete\u002Fadd\u002Fimport\u002Finstall\nlazyllm review ...\nlazyllm review-local ...\n```\n\nA bare `lazyllm --help` can print usage and exit non-zero. Use concrete subcommands such as `lazyllm skills list` for smoke checks.\n\n## Config and namespace facts\n\n- `lazyllm.config` supports key lookup and mutation with option validation, aliases, default fallback for empty strings, and post-action hooks.\n- Environment-backed values can be refreshed, and namespace contexts can redirect environment prefixes, for example `lazyllm.namespace(\"my\")`.\n- Tests verify `LAZYLLM_GPU_TYPE`, `LAZYLLM_DISPLAY`, alias normalization, strict options, and namespace isolation behavior.\n\n## Component and prompt facts\n\n- `lazyllm.components.register` can create groups and register callables\u002Fclasses under lowercase and capitalization-preserving names.\n- `fc_register` belongs to agents\u002Ftools, but simple tool registration metadata is often debugged from core runtime imports.\n- `Prompter`, `AlpacaPrompter`, and `ChatPrompter` generate string prompts and OpenAI-style `messages` payloads with history support.\n\n## Review before handing off\n\nBefore routing to a heavier sub-skill, leave the user with:\n\n- active Python interpreter and LazyLLM version,\n- selected optional extra or reason none is needed,\n- safe command to reproduce the import\u002FCLI\u002Fconfig state,\n- explicit note if a provider, GPU, model download, external DB, parser service, MCP process, or remote review action is required.\n","# LazyLLM Core Runtime\n\nUse this sub-skill for base LazyLLM setup and runtime questions: package installation, optional extras, CLI command routing, `lazyllm.config`, namespace behavior, launchers, components\u002Fregistries, prompters, dependency diagnostics, and safe source-checkout smoke tests.\n\n## Start here when\n\n- The user asks to install LazyLLM or choose between base, `rag`, `standard`, `full`, `dev`, or backend-specific extras.\n- An import error names missing optional packages or `lazyllm install \u003Cextra>`.\n- The task mentions `lazyllm` CLI commands: `install`, `deploy`, `run`, `skills`, `review`, or `review-local`.\n- The task concerns `lazyllm.config`, environment-backed options, `lazyllm.namespace`, `ComponentBase`, component registration, prompt templates, or launcher\u002Fservice scaffolding.\n- You need a no-network check before moving to RAG, agents, models, writer, or flows.\n\n## Files to read\n\n- [config-cli-components.md](references\u002Fconfig-cli-components.md) for CLI command families, config behavior, prompters, components, and launcher notes.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for core install\u002Fimport\u002FCLI\u002Fconfig failure modes.\n- Root [Installation and optional extras](..\u002F..\u002Freferences\u002Finstallation-and-extras.md) for extra selection across workflows.\n- [scripts\u002Fconfig_cli_smoke.py](scripts\u002Fconfig_cli_smoke.py) for a safe local smoke check of config, prompt, component registration, and CLI command table assumptions.\n\n## Core workflow checklist\n\n1. **Identify the selected workflow.** If the task is only config\u002FCLI\u002Fimport, keep it here. If it needs a domain feature, route onward after checking dependencies:\n   - RAG\u002Fdocument import → [rag-document-processing](..\u002Frag-document-processing\u002FSKILL.md)\n   - Agents\u002Ftools\u002FMCP → [agents-tools](..\u002Fagents-tools\u002FSKILL.md)\n   - Model serving\u002Fprovider\u002Ffine-tuning → [model-deployment](..\u002Fmodel-deployment\u002FSKILL.md)\n   - Flow composition → [flow-orchestration](..\u002Fflow-orchestration\u002FSKILL.md)\n   - Writer\u002Freview → [writer-review](..\u002Fwriter-review\u002FSKILL.md)\n2. **Check Python and install state.** LazyLLM 0.7.5 expects Python `>=3.10,\u003C3.14`.\n3. **Run a safe import\u002FCLI diagnostic** when environment state is unclear:\n   ```bash\n   python ..\u002F..\u002Fscripts\u002Fcheck_lazyllm_env.py --check-cli\n   python scripts\u002Fconfig_cli_smoke.py\n   ```\n4. **Install the smallest extra** named by the failure. For example, RAG import failures usually require `lazyllm install rag`, not `full`.\n5. **Avoid side effects.** Core runtime checks should not download models, call providers, start external services, or post reviews.\n\n## CLI command families\n\nThe dispatcher recognizes these top-level commands:\n\n```text\nlazyllm install \u003Cextra1> \u003Cextra2> \u003Cpkg1> ...\nlazyllm deploy modelname\nlazyllm deploy mcp_server \u003Ccommand> [args ...] [options]\nlazyllm run graph.json\nlazyllm run chatbot\nlazyllm run rag\nlazyllm skills init\u002Flist\u002Finfo\u002Fdelete\u002Fadd\u002Fimport\u002Finstall\nlazyllm review ...\nlazyllm review-local ...\n```\n\nA bare `lazyllm --help` can print usage and exit non-zero. Use concrete subcommands such as `lazyllm skills list` for smoke checks.\n\n## Config and namespace facts\n\n- `lazyllm.config` supports key lookup and mutation with option validation, aliases, default fallback for empty strings, and post-action hooks.\n- Environment-backed values can be refreshed, and namespace contexts can redirect environment prefixes, for example `lazyllm.namespace(\"my\")`.\n- Tests verify `LAZYLLM_GPU_TYPE`, `LAZYLLM_DISPLAY`, alias normalization, strict options, and namespace isolation behavior.\n\n## Component and prompt facts\n\n- `lazyllm.components.register` can create groups and register callables\u002Fclasses under lowercase and capitalization-preserving names.\n- `fc_register` belongs to agents\u002Ftools, but simple tool registration metadata is often debugged from core runtime imports.\n- `Prompter`, `AlpacaPrompter`, and `ChatPrompter` generate string prompts and OpenAI-style `messages` payloads with history support.\n\n## Review before handing off\n\nBefore routing to a heavier sub-skill, leave the user with:\n\n- active Python interpreter and LazyLLM version,\n- selected optional extra or reason none is needed,\n- safe command to reproduce the import\u002FCLI\u002Fconfig state,\n- explicit note if a provider, GPU, model download, external DB, parser service, MCP process, or remote review action is required.\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\u002Fcore-runtime",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 core-runtime",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill core-runtime",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill core-runtime","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\u002Fcore-runtime\u002FSKILL.md",[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fconfig-cli-components.md","REFERENCE","参考文档",4144,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Fcore-runtime\u002Freferences\u002Fconfig-cli-components.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",1909,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Fcore-runtime\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fconfig_cli_smoke.py","SCRIPT","脚本",2404,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Fcore-runtime\u002Fscripts\u002Fconfig_cli_smoke.py",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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",[],[]]