[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796XK1HCWHF18B60HJR8SN5":3,"skill-same:01M796XK1HCWHF18B60HJR8SN5":66},{"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},"01M796XK1HCWHF18B60HJR8SN5","embeddings-retrieval",null,"Use UniLM E5 and SimLM for embedding evaluation, dense retrieval, reranking, hard-negative mining, teacher scoring, and retrieval training workflows.","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\u002Funilm\u002Fsub-skills\u002Fembeddings-retrieval\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: embeddings-retrieval\ndescription: \"Use UniLM E5 and SimLM for embedding evaluation, dense retrieval,\n  reranking, hard-negative mining, teacher scoring, and retrieval training\n  workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Embeddings Retrieval\n\nUse this sub-skill when a task names E5, SimLM, BEIR, MTEB, MS MARCO, DPR\u002FNQ retrieval, dense corpus\u002Fquery encoding, reranking, hard-negative mining, or teacher-score generation.\n\nFor general sequence-to-sequence generation, route to `language-seq2seq`. For image-text or document AI retrieval that does not explicitly name E5 or SimLM, route to `vision-document-ai`. For PFPO\u002FReSA math evaluation or generic training architecture questions, route to `architectures-training`.\n\n## Fast Routing\n\n- Choose **E5** for off-the-shelf text embeddings, BEIR retrieval evaluation, non-retrieval MTEB tasks, multilingual embeddings, and prefix\u002Fpooling questions.\n- Choose **SimLM biencoder** for dense passage retrieval pipelines that separately encode a corpus, encode\u002Fsearch queries, and optionally mine hard negatives from search output.\n- Choose **SimLM reranker** for cross-encoder scoring of `(query, candidate passage)` pairs from an existing top-k run; do not use it to encode a corpus.\n- Choose **SimLM RLM\u002FKD training** for replacing-language-model pretraining, distillation data generation, or retraining MS MARCO\u002FDPR retrieval models.\n\n## Bundled References and Script\n\n- Read `references\u002Fmodel-and-data-reference.md` to choose E5\u002FSimLM model families, prefixes, pooling, dependencies, file roles, and data layouts.\n- Read `references\u002Fworkflows.md` to construct safe E5 evaluation commands and plan SimLM encode\u002Fsearch\u002Frerank\u002Ftrain\u002Fteacher-score phases.\n- Read `references\u002Ftroubleshooting.md` when prefixes, multilingual flags, GPU memory, downloads, DeepSpeed, or missing SimLM data files break a workflow.\n- Run `scripts\u002Fbuild_e5_eval_command.py --help` to print a validated E5 BEIR or MTEB command without downloading data, loading a model, or launching evaluation.\n\n## Safety Defaults\n\n- Treat E5 BEIR\u002FMTEB evaluation as network- and GPU-heavy: the upstream scripts download benchmark data\u002Fmodel weights and can run for hours.\n- Treat SimLM download, train, encode, search, rerank, and teacher-score scripts as reference-only unless the user has explicitly provided data, GPUs, storage, and permission for long jobs.\n- Prefer command construction, file validation, and dry-run planning before any native run. SimLM code asserts CUDA availability for core training\u002Finference paths.\n- Keep generated commands rooted in a caller-provided working copy or environment; this skill does not require or expose the original source checkout.\n","# Embeddings Retrieval\n\nUse this sub-skill when a task names E5, SimLM, BEIR, MTEB, MS MARCO, DPR\u002FNQ retrieval, dense corpus\u002Fquery encoding, reranking, hard-negative mining, or teacher-score generation.\n\nFor general sequence-to-sequence generation, route to `language-seq2seq`. For image-text or document AI retrieval that does not explicitly name E5 or SimLM, route to `vision-document-ai`. For PFPO\u002FReSA math evaluation or generic training architecture questions, route to `architectures-training`.\n\n## Fast Routing\n\n- Choose **E5** for off-the-shelf text embeddings, BEIR retrieval evaluation, non-retrieval MTEB tasks, multilingual embeddings, and prefix\u002Fpooling questions.\n- Choose **SimLM biencoder** for dense passage retrieval pipelines that separately encode a corpus, encode\u002Fsearch queries, and optionally mine hard negatives from search output.\n- Choose **SimLM reranker** for cross-encoder scoring of `(query, candidate passage)` pairs from an existing top-k run; do not use it to encode a corpus.\n- Choose **SimLM RLM\u002FKD training** for replacing-language-model pretraining, distillation data generation, or retraining MS MARCO\u002FDPR retrieval models.\n\n## Bundled References and Script\n\n- Read `references\u002Fmodel-and-data-reference.md` to choose E5\u002FSimLM model families, prefixes, pooling, dependencies, file roles, and data layouts.\n- Read `references\u002Fworkflows.md` to construct safe E5 evaluation commands and plan SimLM encode\u002Fsearch\u002Frerank\u002Ftrain\u002Fteacher-score phases.\n- Read `references\u002Ftroubleshooting.md` when prefixes, multilingual flags, GPU memory, downloads, DeepSpeed, or missing SimLM data files break a workflow.\n- Run `scripts\u002Fbuild_e5_eval_command.py --help` to print a validated E5 BEIR or MTEB command without downloading data, loading a model, or launching evaluation.\n\n## Safety Defaults\n\n- Treat E5 BEIR\u002FMTEB evaluation as network- and GPU-heavy: the upstream scripts download benchmark data\u002Fmodel weights and can run for hours.\n- Treat SimLM download, train, encode, search, rerank, and teacher-score scripts as reference-only unless the user has explicitly provided data, GPUs, storage, and permission for long jobs.\n- Prefer command construction, file validation, and dry-run planning before any native run. SimLM code asserts CUDA availability for core training\u002Finference paths.\n- Keep generated commands rooted in a caller-provided working copy or environment; this skill does not require or expose the original source checkout.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Funilm\u002Fsub-skills\u002Fembeddings-retrieval",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 embeddings-retrieval",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill embeddings-retrieval",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill embeddings-retrieval","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funilm\u002Fsub-skills\u002Fembeddings-retrieval\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fmodel-and-data-reference.md","REFERENCE","参考文档",8370,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funilm\u002Fsub-skills\u002Fembeddings-retrieval\u002Freferences\u002Fmodel-and-data-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",7258,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funilm\u002Fsub-skills\u002Fembeddings-retrieval\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",9599,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funilm\u002Fsub-skills\u002Fembeddings-retrieval\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fbuild_e5_eval_command.py","SCRIPT","脚本",8474,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funilm\u002Fsub-skills\u002Fembeddings-retrieval\u002Fscripts\u002Fbuild_e5_eval_command.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"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.","Apache-2.0","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":71,"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":71,"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":71,"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":71,"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":71,"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",[],[]]