[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794XHF87M4608432CSAVVM4":3,"skill-same:01M794XHF87M4608432CSAVVM4":67},{"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},"01M794XHF87M4608432CSAVVM4","embeddings-and-similarity",null,"Dense SentenceTransformer embedding and similarity workflows for text or multimodal inputs, including construction, encode\u002Fencode_query\u002Fencode_document options, prompt and truncation decisions, precision, normalization, batching\u002Fdevices, local cache cautions, and output validation.","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\u002Fsentence-transformers\u002Fsub-skills\u002Fembeddings-and-similarity\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: embeddings-and-similarity\ndescription: \"Dense SentenceTransformer embedding and similarity workflows for\n  text or multimodal inputs, including construction,\n  encode\u002Fencode_query\u002Fencode_document options, prompt and truncation decisions,\n  precision, normalization, batching\u002Fdevices, local cache cautions, and output\n  validation.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Embeddings and Similarity\n\nUse this sub-skill when the user needs dense `SentenceTransformer` embeddings or direct embedding similarity scores.\n\n## Route Here\n\n- Construct or load a `SentenceTransformer` for embedding inference.\n- Encode text, images, audio, video, multimodal dicts, or chat-style message inputs with dense embedding models.\n- Choose between `encode`, `encode_query`, and `encode_document`, including prompt-aware retrieval embedding.\n- Tune `batch_size`, `device`, `precision`, `truncate_dim`, `normalize_embeddings`, output conversion, and similarity metric choices.\n- Validate embedding shapes, dtypes, normalization, and similarity matrix or pairwise similarity results.\n\n## Route Elsewhere\n\n- Use `..\u002Fretrieval-and-utilities\u002F` for `util.semantic_search`, hard-negative mining, paraphrase mining, quantized retrieval indexes, or vector database workflows.\n- Use `..\u002Fevaluation-and-training\u002F` for fine-tuning, losses, trainers, evaluators, and dataset formatting.\n- Use `..\u002Fbackend-export-optimization\u002F` for ONNX\u002FOpenVINO backend selection, export, optimization, or deployment packaging.\n- Use `..\u002Freranking-cross-encoder\u002F` for `CrossEncoder.predict`, `CrossEncoder.rank`, or reranker scoring.\n- Use `..\u002Fsparse-encoder-search\u002F` for `SparseEncoder`, SPLADE-style sparse vectors, sparse search, or sparsity diagnostics.\n\n## Fast Workflow\n\n1. Confirm the task is dense embedding inference, not retrieval orchestration or model training.\n2. Load a model with explicit network\u002Fcache policy, e.g. `SentenceTransformer(model_id_or_path, local_files_only=True)` for offline use.\n3. Prefer `encode_query` and `encode_document` for retrieval models with query\u002Fdocument prompts; use `encode` for symmetric STS, clustering, or classification features.\n4. Set output options deliberately: `convert_to_numpy=True` for NumPy workflows, `convert_to_tensor=True` for Torch workflows, and avoid both being ambiguous in reusable code.\n5. Validate the returned row count, embedding dimension, dtype, finite values, and similarity output shape before using scores downstream.\n\n## References\n\n- API details: `references\u002Fapi-reference.md`\n- Workflow recipes: `references\u002Fworkflows.md`\n- Failure diagnosis: `references\u002Ftroubleshooting.md`\n- Safe smoke helper: `scripts\u002Fdense_embedding_smoke.py`\n","# Embeddings and Similarity\n\nUse this sub-skill when the user needs dense `SentenceTransformer` embeddings or direct embedding similarity scores.\n\n## Route Here\n\n- Construct or load a `SentenceTransformer` for embedding inference.\n- Encode text, images, audio, video, multimodal dicts, or chat-style message inputs with dense embedding models.\n- Choose between `encode`, `encode_query`, and `encode_document`, including prompt-aware retrieval embedding.\n- Tune `batch_size`, `device`, `precision`, `truncate_dim`, `normalize_embeddings`, output conversion, and similarity metric choices.\n- Validate embedding shapes, dtypes, normalization, and similarity matrix or pairwise similarity results.\n\n## Route Elsewhere\n\n- Use `..\u002Fretrieval-and-utilities\u002F` for `util.semantic_search`, hard-negative mining, paraphrase mining, quantized retrieval indexes, or vector database workflows.\n- Use `..\u002Fevaluation-and-training\u002F` for fine-tuning, losses, trainers, evaluators, and dataset formatting.\n- Use `..\u002Fbackend-export-optimization\u002F` for ONNX\u002FOpenVINO backend selection, export, optimization, or deployment packaging.\n- Use `..\u002Freranking-cross-encoder\u002F` for `CrossEncoder.predict`, `CrossEncoder.rank`, or reranker scoring.\n- Use `..\u002Fsparse-encoder-search\u002F` for `SparseEncoder`, SPLADE-style sparse vectors, sparse search, or sparsity diagnostics.\n\n## Fast Workflow\n\n1. Confirm the task is dense embedding inference, not retrieval orchestration or model training.\n2. Load a model with explicit network\u002Fcache policy, e.g. `SentenceTransformer(model_id_or_path, local_files_only=True)` for offline use.\n3. Prefer `encode_query` and `encode_document` for retrieval models with query\u002Fdocument prompts; use `encode` for symmetric STS, clustering, or classification features.\n4. Set output options deliberately: `convert_to_numpy=True` for NumPy workflows, `convert_to_tensor=True` for Torch workflows, and avoid both being ambiguous in reusable code.\n5. Validate the returned row count, embedding dimension, dtype, finite values, and similarity output shape before using scores downstream.\n\n## References\n\n- API details: `references\u002Fapi-reference.md`\n- Workflow recipes: `references\u002Fworkflows.md`\n- Failure diagnosis: `references\u002Ftroubleshooting.md`\n- Safe smoke helper: `scripts\u002Fdense_embedding_smoke.py`\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\u002Fsentence-transformers\u002Fsub-skills\u002Fembeddings-and-similarity",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 embeddings-and-similarity",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill embeddings-and-similarity",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill embeddings-and-similarity","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsentence-transformers\u002Fsub-skills\u002Fembeddings-and-similarity\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",5661,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsentence-transformers\u002Fsub-skills\u002Fembeddings-and-similarity\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",4276,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsentence-transformers\u002Fsub-skills\u002Fembeddings-and-similarity\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",3970,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsentence-transformers\u002Fsub-skills\u002Fembeddings-and-similarity\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fdense_embedding_smoke.py","SCRIPT","脚本",5042,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsentence-transformers\u002Fsub-skills\u002Fembeddings-and-similarity\u002Fscripts\u002Fdense_embedding_smoke.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]