[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7952Q8VAP2ZMNSS0YZXZV2T":3,"skill-same:01M7952Q8VAP2ZMNSS0YZXZV2T":71},{"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},"01M7952Q8VAP2ZMNSS0YZXZV2T","retrieval-representation",null,"Use Simple Transformers representation, dense retrieval, DPR, BEIR\u002FMSMARCO, hard-negative, and retrieval-evaluation workflows.","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\u002Fsimpletransformers\u002Fsub-skills\u002Fretrieval-representation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: retrieval-representation\ndescription: \"Use Simple Transformers representation, dense retrieval, DPR,\n  BEIR\u002FMSMARCO, hard-negative, and retrieval-evaluation workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Simple Transformers Retrieval and Representation Sub-skill\n\nUse this sub-skill when a task asks for sentence\u002Fword embeddings,\n`RepresentationModel.encode_sentences`, dense retrieval with query\u002Fcontext\nencoders, DPR-style training, hard negatives, BEIR\u002FMSMARCO\u002FTREC data, FAISS\nindexes, or retrieval metrics.\n\n## Owns\n\n- `RepresentationModel` for hidden-state\u002Ftoken\u002Fword\u002Fsentence representations.\n- `RetrievalModel` \u002F `RetrievalArgs` for dense retrieval train\u002Feval\u002Fpredict.\n- `PretrainRetrievalModel` as an advanced pretraining route.\n- Retrieval data schemas: `query_text`, `gold_passage`, optional `title`, prediction queries, BEIR\u002FMSMARCO\u002FTREC conversion.\n- Optional `faiss`, `pytrec_eval`, and `beir` branches.\n\n## Route elsewhere\n\n- Cross-encoder sentence-pair classification reranking: [classification](..\u002Fclassification\u002FSKILL.md).\n- T5\u002FmonoT5 text-to-text reranking: [generative-workflows](..\u002Fgenerative-workflows\u002FSKILL.md).\n- Extractive QA after passage retrieval: [token-and-qa](..\u002Ftoken-and-qa\u002FSKILL.md).\n\n## Read first\n\n1. [API reference](references\u002Fapi-reference.md) for constructors and method map.\n2. [Data formats](references\u002Fdata-formats.md) before preparing retrieval or representation inputs.\n3. [Workflows](references\u002Fworkflows.md) for encode, train\u002Feval\u002Fpredict, and optional evaluation routes.\n4. [Troubleshooting](references\u002Ftroubleshooting.md) for optional dependencies, cache\u002Findex files, hard-negative shapes, and dependency compatibility.\n\n## Validation helper\n\n```bash\npython scripts\u002Fvalidate_retrieval_data.py --task retrieval-csv --input train.csv\npython scripts\u002Fvalidate_retrieval_data.py --task query-lines --input queries.txt\npython scripts\u002Fvalidate_retrieval_data.py --task beir-corpus-jsonl --input corpus.jsonl\npython scripts\u002Fvalidate_retrieval_data.py --task beir-queries-jsonl --input queries.jsonl\npython scripts\u002Fvalidate_retrieval_data.py --task tsv --input train.tsv\n```\n\nThe helper checks file shape only. It does not import FAISS, build indexes,\ndownload datasets, train encoders, or run BEIR evaluation.\n\n## Key decisions\n\n- Use `RepresentationModel` when the output is embeddings or token vectors.\n- Use `RetrievalModel` when the task includes query\u002Fpassage training, hard negatives, or retrieval prediction.\n- Decide whether evaluation needs built-in metrics only, `pytrec_eval`, or full BEIR evaluation.\n- Install FAISS only for workflows that actually build or load FAISS indexes.\n- Keep CPU for small smoke checks; CUDA is performance acceleration, not required for schema validation.\n\n## Verification status\n\nConstructor signatures were inspected with compatibility warnings. Native representation\u002Fretrieval examples require checkpoint\u002Fdataset downloads and optional dependencies, so default verification uses validators and static\u002FAPI evidence unless the user approves larger checks.\n","# Simple Transformers Retrieval and Representation Sub-skill\n\nUse this sub-skill when a task asks for sentence\u002Fword embeddings,\n`RepresentationModel.encode_sentences`, dense retrieval with query\u002Fcontext\nencoders, DPR-style training, hard negatives, BEIR\u002FMSMARCO\u002FTREC data, FAISS\nindexes, or retrieval metrics.\n\n## Owns\n\n- `RepresentationModel` for hidden-state\u002Ftoken\u002Fword\u002Fsentence representations.\n- `RetrievalModel` \u002F `RetrievalArgs` for dense retrieval train\u002Feval\u002Fpredict.\n- `PretrainRetrievalModel` as an advanced pretraining route.\n- Retrieval data schemas: `query_text`, `gold_passage`, optional `title`, prediction queries, BEIR\u002FMSMARCO\u002FTREC conversion.\n- Optional `faiss`, `pytrec_eval`, and `beir` branches.\n\n## Route elsewhere\n\n- Cross-encoder sentence-pair classification reranking: [classification](..\u002Fclassification\u002FSKILL.md).\n- T5\u002FmonoT5 text-to-text reranking: [generative-workflows](..\u002Fgenerative-workflows\u002FSKILL.md).\n- Extractive QA after passage retrieval: [token-and-qa](..\u002Ftoken-and-qa\u002FSKILL.md).\n\n## Read first\n\n1. [API reference](references\u002Fapi-reference.md) for constructors and method map.\n2. [Data formats](references\u002Fdata-formats.md) before preparing retrieval or representation inputs.\n3. [Workflows](references\u002Fworkflows.md) for encode, train\u002Feval\u002Fpredict, and optional evaluation routes.\n4. [Troubleshooting](references\u002Ftroubleshooting.md) for optional dependencies, cache\u002Findex files, hard-negative shapes, and dependency compatibility.\n\n## Validation helper\n\n```bash\npython scripts\u002Fvalidate_retrieval_data.py --task retrieval-csv --input train.csv\npython scripts\u002Fvalidate_retrieval_data.py --task query-lines --input queries.txt\npython scripts\u002Fvalidate_retrieval_data.py --task beir-corpus-jsonl --input corpus.jsonl\npython scripts\u002Fvalidate_retrieval_data.py --task beir-queries-jsonl --input queries.jsonl\npython scripts\u002Fvalidate_retrieval_data.py --task tsv --input train.tsv\n```\n\nThe helper checks file shape only. It does not import FAISS, build indexes,\ndownload datasets, train encoders, or run BEIR evaluation.\n\n## Key decisions\n\n- Use `RepresentationModel` when the output is embeddings or token vectors.\n- Use `RetrievalModel` when the task includes query\u002Fpassage training, hard negatives, or retrieval prediction.\n- Decide whether evaluation needs built-in metrics only, `pytrec_eval`, or full BEIR evaluation.\n- Install FAISS only for workflows that actually build or load FAISS indexes.\n- Keep CPU for small smoke checks; CUDA is performance acceleration, not required for schema validation.\n\n## Verification status\n\nConstructor signatures were inspected with compatibility warnings. Native representation\u002Fretrieval examples require checkpoint\u002Fdataset downloads and optional dependencies, so default verification uses validators and static\u002FAPI evidence unless the user approves larger checks.\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\u002Fsimpletransformers\u002Fsub-skills\u002Fretrieval-representation",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 retrieval-representation",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill retrieval-representation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill retrieval-representation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsimpletransformers\u002Fsub-skills\u002Fretrieval-representation\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",2611,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsimpletransformers\u002Fsub-skills\u002Fretrieval-representation\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdata-formats.md",1809,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsimpletransformers\u002Fsub-skills\u002Fretrieval-representation\u002Freferences\u002Fdata-formats.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",1451,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsimpletransformers\u002Fsub-skills\u002Fretrieval-representation\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fworkflows.md",2045,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsimpletransformers\u002Fsub-skills\u002Fretrieval-representation\u002Freferences\u002Fworkflows.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fvalidate_retrieval_data.py","SCRIPT","脚本",2634,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsimpletransformers\u002Fsub-skills\u002Fretrieval-representation\u002Fscripts\u002Fvalidate_retrieval_data.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]