[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78X619VBWP2Q6AFC6KYPDF3":3,"skill-same:01M78X619VBWP2Q6AFC6KYPDF3":70},{"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},"01M78X619VBWP2Q6AFC6KYPDF3","flashrag",null,"Use FlashRAG for retrieval-augmented generation research workflows: config\u002Fdata validation, retrieval and index building, generation\u002Frefinement components, RAG pipelines\u002Fmethod reproduction, evaluation, and WebUI setup.","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\u002Fflashrag\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: flashrag\ndescription: \"Use FlashRAG for retrieval-augmented generation research\n  workflows: config\u002Fdata validation, retrieval and index building,\n  generation\u002Frefinement components, RAG pipelines\u002Fmethod reproduction,\n  evaluation, and WebUI setup.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# FlashRAG\n\nUse this skill when a task asks for help with FlashRAG, the Python toolkit for Retrieval-Augmented Generation research, benchmark reproduction, custom RAG pipelines, retriever\u002Findex setup, generator\u002Frefiner configuration, evaluation, or the FlashRAG UI.\n\n## Start Here\n\n- **Check staleness first**: Read [repo-provenance.md](references\u002Frepo-provenance.md) before using this skill with a local checkout; refresh the skill if the commit, dirty state, package version, or public evidence paths changed.\n- **Install minimally**: Public package name is `flashrag-dev`; install with `pip install flashrag-dev --pre` or install a checkout with `pip install -e .` when editing the repo.\n- **Verify import**: Run `python -c \"import flashrag, importlib.metadata as md; print(md.version('flashrag_dev'))\"` after install. If metadata lookup fails, try `flashrag-dev` because Python tools normalize underscores and hyphens differently.\n- **Check optional dependencies**: Run [check_flashrag_environment.py](scripts\u002Fcheck_flashrag_environment.py) before loading models, building indexes, or launching services.\n- **Read troubleshooting**: Use [troubleshooting.md](references\u002Ftroubleshooting.md) for cross-cutting install\u002Fimport, optional dependency, data, hardware, credential, and stale-skill failures.\n\n## Route by Task\n\n- **Config, dataset, corpus schemas, and safe input checks**: Use [data-and-config](sub-skills\u002Fdata-and-config\u002FSKILL.md) for `Config`, `Dataset`, YAML\u002Fdict override behavior, JSONL schemas, and validation helpers.\n- **Corpus preparation, retrieval, reranking, and index building**: Use [retrieval-and-indexing](sub-skills\u002Fretrieval-and-indexing\u002FSKILL.md) for BM25s\u002FPyserini, dense Faiss, CLIP\u002Fmultimodal retrieval, Serper\u002Fweb retrieval, rerankers, and multi-retriever fusion.\n- **Generators, prompt templates, refiners, compressors, and judgers**: Use [generation-and-refinement](sub-skills\u002Fgeneration-and-refinement\u002FSKILL.md) for HF\u002FFastChat\u002FvLLM\u002FOpenAI generation, multimodal generators, `PromptTemplate`, refiners, and judgers.\n- **End-to-end pipelines and method reproduction**: Use [pipelines-and-methods](sub-skills\u002Fpipelines-and-methods\u002FSKILL.md) for quick-start demos, `SequentialPipeline`, active\u002Fbranching\u002Fadaptive\u002Freasoning RAG, multimodal RAG, and experiment-runner planning.\n- **Evaluation metrics and WebUI**: Use [evaluation-and-webui](sub-skills\u002Fevaluation-and-webui\u002FSKILL.md) for `Evaluator`, metrics, prediction parsing, WebUI chat\u002Fevaluate setup, and service troubleshooting.\n\n## Capability Map\n\nRead [capability-map.md](references\u002Fcapability-map.md) when a request spans multiple FlashRAG areas or when you need to choose the right sub-skill owner for a source artifact, helper, or failure mode.\n\n## Safe Workflow Defaults\n\n1. Validate config\u002Fdata with the data\u002Fconfig helper before running retrieval or pipelines.\n2. For retrieval, validate corpus JSONL and build command arguments before starting index construction.\n3. For generation or methods, inspect config keys and optional dependency requirements before loading models or contacting APIs.\n4. Treat benchmark reproduction, model downloads, vLLM serving, WebUI launch, and large index builds as explicit user-approved runtime actions.\n5. Keep API keys, model paths, dataset locations, and machine-specific paths out of generated notes unless the user explicitly asks for local operational commands.\n\n## Optional Dependency Surface\n\nFlashRAG core workflows commonly need `torch`, `transformers`, `PyYAML`, `numpy`, `tqdm`, and related runtime packages. Optional workflows add more constraints:\n\n- Dense retrieval: `faiss` plus embedding model packages.\n- BM25 retrieval: `bm25s` for lightweight CPU use, or `pyserini` plus Java for Lucene-backed indexes.\n- Generator acceleration: `vllm` requires a compatible PyTorch\u002FCUDA stack.\n- OpenAI generation or LLMJudge-style evaluation: `openai`, `tiktoken`, and credentials.\n- Multimodal RAG: image packages and model-specific utilities such as Qwen-VL helpers.\n- WebUI: service\u002FUI dependencies such as Streamlit or Gradio plus valid model\u002Findex configs.\n\n## When Editing a FlashRAG Checkout\n\n- Prefer focused changes in the owning module and update nearby docs\u002Fexamples when public behavior changes.\n- Use package source and installed-package inspection to confirm APIs; docs\u002Fexamples show intended workflows but source resolves defaults and edge behavior.\n- If modifying public config keys, retriever\u002Fgenerator factories, pipeline names, or metric names, refresh this skill after the code change so routing and references stay aligned.\n","# FlashRAG\n\nUse this skill when a task asks for help with FlashRAG, the Python toolkit for Retrieval-Augmented Generation research, benchmark reproduction, custom RAG pipelines, retriever\u002Findex setup, generator\u002Frefiner configuration, evaluation, or the FlashRAG UI.\n\n## Start Here\n\n- **Check staleness first**: Read [repo-provenance.md](references\u002Frepo-provenance.md) before using this skill with a local checkout; refresh the skill if the commit, dirty state, package version, or public evidence paths changed.\n- **Install minimally**: Public package name is `flashrag-dev`; install with `pip install flashrag-dev --pre` or install a checkout with `pip install -e .` when editing the repo.\n- **Verify import**: Run `python -c \"import flashrag, importlib.metadata as md; print(md.version('flashrag_dev'))\"` after install. If metadata lookup fails, try `flashrag-dev` because Python tools normalize underscores and hyphens differently.\n- **Check optional dependencies**: Run [check_flashrag_environment.py](scripts\u002Fcheck_flashrag_environment.py) before loading models, building indexes, or launching services.\n- **Read troubleshooting**: Use [troubleshooting.md](references\u002Ftroubleshooting.md) for cross-cutting install\u002Fimport, optional dependency, data, hardware, credential, and stale-skill failures.\n\n## Route by Task\n\n- **Config, dataset, corpus schemas, and safe input checks**: Use [data-and-config](sub-skills\u002Fdata-and-config\u002FSKILL.md) for `Config`, `Dataset`, YAML\u002Fdict override behavior, JSONL schemas, and validation helpers.\n- **Corpus preparation, retrieval, reranking, and index building**: Use [retrieval-and-indexing](sub-skills\u002Fretrieval-and-indexing\u002FSKILL.md) for BM25s\u002FPyserini, dense Faiss, CLIP\u002Fmultimodal retrieval, Serper\u002Fweb retrieval, rerankers, and multi-retriever fusion.\n- **Generators, prompt templates, refiners, compressors, and judgers**: Use [generation-and-refinement](sub-skills\u002Fgeneration-and-refinement\u002FSKILL.md) for HF\u002FFastChat\u002FvLLM\u002FOpenAI generation, multimodal generators, `PromptTemplate`, refiners, and judgers.\n- **End-to-end pipelines and method reproduction**: Use [pipelines-and-methods](sub-skills\u002Fpipelines-and-methods\u002FSKILL.md) for quick-start demos, `SequentialPipeline`, active\u002Fbranching\u002Fadaptive\u002Freasoning RAG, multimodal RAG, and experiment-runner planning.\n- **Evaluation metrics and WebUI**: Use [evaluation-and-webui](sub-skills\u002Fevaluation-and-webui\u002FSKILL.md) for `Evaluator`, metrics, prediction parsing, WebUI chat\u002Fevaluate setup, and service troubleshooting.\n\n## Capability Map\n\nRead [capability-map.md](references\u002Fcapability-map.md) when a request spans multiple FlashRAG areas or when you need to choose the right sub-skill owner for a source artifact, helper, or failure mode.\n\n## Safe Workflow Defaults\n\n1. Validate config\u002Fdata with the data\u002Fconfig helper before running retrieval or pipelines.\n2. For retrieval, validate corpus JSONL and build command arguments before starting index construction.\n3. For generation or methods, inspect config keys and optional dependency requirements before loading models or contacting APIs.\n4. Treat benchmark reproduction, model downloads, vLLM serving, WebUI launch, and large index builds as explicit user-approved runtime actions.\n5. Keep API keys, model paths, dataset locations, and machine-specific paths out of generated notes unless the user explicitly asks for local operational commands.\n\n## Optional Dependency Surface\n\nFlashRAG core workflows commonly need `torch`, `transformers`, `PyYAML`, `numpy`, `tqdm`, and related runtime packages. Optional workflows add more constraints:\n\n- Dense retrieval: `faiss` plus embedding model packages.\n- BM25 retrieval: `bm25s` for lightweight CPU use, or `pyserini` plus Java for Lucene-backed indexes.\n- Generator acceleration: `vllm` requires a compatible PyTorch\u002FCUDA stack.\n- OpenAI generation or LLMJudge-style evaluation: `openai`, `tiktoken`, and credentials.\n- Multimodal RAG: image packages and model-specific utilities such as Qwen-VL helpers.\n- WebUI: service\u002FUI dependencies such as Streamlit or Gradio plus valid model\u002Findex configs.\n\n## When Editing a FlashRAG Checkout\n\n- Prefer focused changes in the owning module and update nearby docs\u002Fexamples when public behavior changes.\n- Use package source and installed-package inspection to confirm APIs; docs\u002Fexamples show intended workflows but source resolves defaults and edge behavior.\n- If modifying public config keys, retriever\u002Fgenerator factories, pipeline names, or metric names, refresh this skill after the code change so routing and references stay aligned.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fflashrag",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 flashrag",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill flashrag",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill flashrag","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcapability-map.md","REFERENCE","参考文档",4301,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002Freferences\u002Fcapability-map.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",1953,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",501,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",3899,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_flashrag_environment.py","SCRIPT","脚本",4176,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002Fscripts\u002Fcheck_flashrag_environment.py",[71,79,86,93,100,107],{"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":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]