[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794260PF093TM8M978DX67X":3,"skill-same:01M794260PF093TM8M978DX67X":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},"01M794260PF093TM8M978DX67X","rags",null,"Use this repo skill for RAGs, a Streamlit app that builds configurable LlamaIndex RAG agents from natural-language setup, data sources, and model settings.","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\u002Frags\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: rags\ndescription: \"Use this repo skill for RAGs, a Streamlit app that builds\n  configurable LlamaIndex RAG agents from natural-language setup, data sources,\n  and model settings.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# RAGs Repo Skill\n\nRAGs is a Streamlit application for building retrieval-augmented chat agents\nover user-provided data. Use this skill when the task mentions RAGs, creating a\nRAG bot from natural language, configuring generated RAG parameters, querying a\ngenerated agent, or debugging RAGs cache\u002Fsecrets\u002Fmodel behavior.\n\n## Before Acting\n\n1. Read [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) when\n   checking whether this skill is current for a checkout or when refreshing it.\n2. Read [`references\u002Fapp-architecture.md`](references\u002Fapp-architecture.md) when\n   you need the cross-page architecture, state, cache, model, and tool flow.\n3. Run or inspect [`scripts\u002Fcheck_install.py`](scripts\u002Fcheck_install.py) for a\n   safe dependency\u002Fsource-import diagnostic. It does not call external LLMs.\n4. Use [`scripts\u002Frun_rags_app.py`](scripts\u002Frun_rags_app.py) to validate or wrap\n   the Streamlit launch command for a user-provided RAGs checkout. It dry-runs\n   by default; pass `--execute` only when the user wants a long-running server.\n\nThe current source snapshot is an app-style repository, not an installable\nPython package named `rags`. Dependency-oriented setup and running from a RAGs\ncheckout is the supported operating model captured by this skill.\n\n## Route Map\n\n| User intent | Read |\n| --- | --- |\n| Build a new RAG bot from files, a directory, URLs, task text, RAG parameters, optional web search, or beta multimodal setup. | [`sub-skills\u002Fbuilder\u002FSKILL.md`](sub-skills\u002Fbuilder\u002FSKILL.md) |\n| Inspect, edit, update, delete, rename, or repair a generated agent's configuration or cache. | [`sub-skills\u002Fconfiguration\u002FSKILL.md`](sub-skills\u002Fconfiguration\u002FSKILL.md) |\n| Ask questions to an existing generated agent, inspect sources, or debug no\u002Firrelevant\u002Fbroken sources. | [`sub-skills\u002Fchat\u002FSKILL.md`](sub-skills\u002Fchat\u002FSKILL.md) |\n| Diagnose install, secrets, dependency version, root-package install, cache upgrade, or optional dependency problems. | [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) |\n\n## Install and Launch Checks\n\nUse public project instructions or equivalent dependency installation. The\nverified inspection environment used Python 3.10 with `streamlit==1.28.0`,\n`llama-index==0.9.7`, `llama-hub==0.0.44`, `langchain==0.0.305`, and\n`pypdf==3.17.1`. A dependency-only Poetry setup or requirements-based setup may\nbe needed because root package installation fails for this snapshot.\n\nSafe checks:\n\n```bash\npython scripts\u002Fcheck_install.py\npython scripts\u002Fcheck_install.py --repo-root \u002Fpath\u002Fto\u002Frags\npython scripts\u002Frun_rags_app.py --repo-root \u002Fpath\u002Fto\u002Frags --check-secrets\n```\n\nLaunch only with user intent:\n\n```bash\npython scripts\u002Frun_rags_app.py --repo-root \u002Fpath\u002Fto\u002Frags --execute -- --server.headless true\n```\n\nRAGs reads a Streamlit secret named `openai_key` while configuring the builder\nLLM. Provider-specific routes may also need `anthropic_key`, `replicate_key`, or\n`metaphor_key`.\n\n## Verification Scope\n\nThe generated skill is based on source inspection plus live dependency\u002Fsource\nmodule inspection. Safe checks covered imports, signatures, `RAGParams` defaults,\nlocal text `load_data`, Streamlit CLI help, and cache-registry behavior. The\nfollowing were intentionally not executed by default: real OpenAI\u002FAnthropic\u002F\nReplicate\u002FMetaphor calls, URL downloads, a long-running Streamlit server, and\nactual beta multimodal construction with torch\u002FCLIP dependencies.\n\n## Boundaries\n\nDo not use this skill as a generic LlamaIndex manual. It is specifically for the\nRAGs app's builder\u002Fconfiguration\u002Fchat workflow and its cache\u002Fsecrets behavior.\nFor changing the RAGs source code itself, treat this as repository maintenance\nand combine with ordinary code inspection rather than relying only on this\noperating skill.\n","# RAGs Repo Skill\n\nRAGs is a Streamlit application for building retrieval-augmented chat agents\nover user-provided data. Use this skill when the task mentions RAGs, creating a\nRAG bot from natural language, configuring generated RAG parameters, querying a\ngenerated agent, or debugging RAGs cache\u002Fsecrets\u002Fmodel behavior.\n\n## Before Acting\n\n1. Read [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) when\n   checking whether this skill is current for a checkout or when refreshing it.\n2. Read [`references\u002Fapp-architecture.md`](references\u002Fapp-architecture.md) when\n   you need the cross-page architecture, state, cache, model, and tool flow.\n3. Run or inspect [`scripts\u002Fcheck_install.py`](scripts\u002Fcheck_install.py) for a\n   safe dependency\u002Fsource-import diagnostic. It does not call external LLMs.\n4. Use [`scripts\u002Frun_rags_app.py`](scripts\u002Frun_rags_app.py) to validate or wrap\n   the Streamlit launch command for a user-provided RAGs checkout. It dry-runs\n   by default; pass `--execute` only when the user wants a long-running server.\n\nThe current source snapshot is an app-style repository, not an installable\nPython package named `rags`. Dependency-oriented setup and running from a RAGs\ncheckout is the supported operating model captured by this skill.\n\n## Route Map\n\n| User intent | Read |\n| --- | --- |\n| Build a new RAG bot from files, a directory, URLs, task text, RAG parameters, optional web search, or beta multimodal setup. | [`sub-skills\u002Fbuilder\u002FSKILL.md`](sub-skills\u002Fbuilder\u002FSKILL.md) |\n| Inspect, edit, update, delete, rename, or repair a generated agent's configuration or cache. | [`sub-skills\u002Fconfiguration\u002FSKILL.md`](sub-skills\u002Fconfiguration\u002FSKILL.md) |\n| Ask questions to an existing generated agent, inspect sources, or debug no\u002Firrelevant\u002Fbroken sources. | [`sub-skills\u002Fchat\u002FSKILL.md`](sub-skills\u002Fchat\u002FSKILL.md) |\n| Diagnose install, secrets, dependency version, root-package install, cache upgrade, or optional dependency problems. | [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) |\n\n## Install and Launch Checks\n\nUse public project instructions or equivalent dependency installation. The\nverified inspection environment used Python 3.10 with `streamlit==1.28.0`,\n`llama-index==0.9.7`, `llama-hub==0.0.44`, `langchain==0.0.305`, and\n`pypdf==3.17.1`. A dependency-only Poetry setup or requirements-based setup may\nbe needed because root package installation fails for this snapshot.\n\nSafe checks:\n\n```bash\npython scripts\u002Fcheck_install.py\npython scripts\u002Fcheck_install.py --repo-root \u002Fpath\u002Fto\u002Frags\npython scripts\u002Frun_rags_app.py --repo-root \u002Fpath\u002Fto\u002Frags --check-secrets\n```\n\nLaunch only with user intent:\n\n```bash\npython scripts\u002Frun_rags_app.py --repo-root \u002Fpath\u002Fto\u002Frags --execute -- --server.headless true\n```\n\nRAGs reads a Streamlit secret named `openai_key` while configuring the builder\nLLM. Provider-specific routes may also need `anthropic_key`, `replicate_key`, or\n`metaphor_key`.\n\n## Verification Scope\n\nThe generated skill is based on source inspection plus live dependency\u002Fsource\nmodule inspection. Safe checks covered imports, signatures, `RAGParams` defaults,\nlocal text `load_data`, Streamlit CLI help, and cache-registry behavior. The\nfollowing were intentionally not executed by default: real OpenAI\u002FAnthropic\u002F\nReplicate\u002FMetaphor calls, URL downloads, a long-running Streamlit server, and\nactual beta multimodal construction with torch\u002FCLIP dependencies.\n\n## Boundaries\n\nDo not use this skill as a generic LlamaIndex manual. It is specifically for the\nRAGs app's builder\u002Fconfiguration\u002Fchat workflow and its cache\u002Fsecrets behavior.\nFor changing the RAGs source code itself, treat this as repository maintenance\nand combine with ordinary code inspection rather than relying only on this\noperating skill.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Frags",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 rags",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill rags",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill rags","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frags\u002FSKILL.md",[46,52,56,60,64,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapp-architecture.md","REFERENCE","参考文档",3484,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frags\u002Freferences\u002Fapp-architecture.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",2336,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frags\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",487,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frags\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",3465,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frags\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_install.py","SCRIPT","脚本",6002,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frags\u002Fscripts\u002Fcheck_install.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Frun_rags_app.py",3410,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frags\u002Fscripts\u002Frun_rags_app.py",[75,83,90,97,104,111],{"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":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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]