[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7965WJR2SDVR49V24JN2RJ7":3,"skill-same:01M7965WJR2SDVR49V24JN2RJ7":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},"01M7965WJR2SDVR49V24JN2RJ7","classification-models",null,"Route classic TensorFlow 1.x text classification model selection, graph inspection, training, prediction, and artifact prerequisites for brightmart\u002Ftext_classification.","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\u002Ftext-classification\u002Fsub-skills\u002Fclassification-models\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: classification-models\ndescription: \"Route classic TensorFlow 1.x text classification model selection,\n  graph inspection, training, prediction, and artifact prerequisites for\n  brightmart\u002Ftext_classification.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Classification Models\n\nUse this sub-skill when the task is to choose, inspect, train, restore, or adapt one of the repository's classic classification model families:\n\n- fastTextB averaged embeddings for multi-label baselines.\n- TextCNN convolution, max-pooling, and sigmoid multi-label classification.\n- TextRNN, TextRCNN, and Hierarchical Attention Network variants.\n- BERT fine-tuning\u002Fclassification heads and online prediction patterns.\n- Legacy TFLearn toy classification examples.\n\nThis repository is a legacy TensorFlow 1.x script collection, not an installable Python package. Assume Python 3.7-era compatibility work and TensorFlow 1.x\u002FTFLearn semantics. Do not assume TensorFlow 2.x eager execution, `tf.keras` rewrites, or Python 3.13 compatibility.\n\n## Route by task\n\n- For architecture choice, placeholders, tensor shapes, and safe graph-construction probes, read [references\u002Fmodel-reference.md](references\u002Fmodel-reference.md).\n- For training, prediction, checkpoint, cache, and embedding prerequisites, read [references\u002Ftraining-and-prediction.md](references\u002Ftraining-and-prediction.md).\n- For TensorFlow 1.x, TFLearn, checkpoint, data-cache, and model-specific failure modes, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n- To inspect small TensorFlow 1.x graphs without running full training, use [scripts\u002Finspect_tf1_model_shapes.py](scripts\u002Finspect_tf1_model_shapes.py).\n\n## Boundaries\n\nUse this sub-skill only for the classification families above. Route seq2seq, Transformer classification\u002Fgeneration, entity networks, and dynamic memory networks to `sequence-and-memory-models`. Route relation models, two-sentence models, boosting, hybrid CNN+RCNN, and ensemble prediction workflows to `relation-and-ensemble-workflows`. Route raw data cleaning, vocabulary construction, HDF5 generation, and label validation to `data-preparation`.\n\n## Safety posture\n\nFull training usually requires external HDF5\u002Fpickle caches, optional word2vec binaries, checkpoint directories, and long runtimes. These artifacts are not bundled with the skill. Prefer tiny graph construction and shape inspection first; run training or prediction scripts only after data, vocabulary, label, checkpoint, and TensorFlow 1.x compatibility are confirmed.\n","# Classification Models\n\nUse this sub-skill when the task is to choose, inspect, train, restore, or adapt one of the repository's classic classification model families:\n\n- fastTextB averaged embeddings for multi-label baselines.\n- TextCNN convolution, max-pooling, and sigmoid multi-label classification.\n- TextRNN, TextRCNN, and Hierarchical Attention Network variants.\n- BERT fine-tuning\u002Fclassification heads and online prediction patterns.\n- Legacy TFLearn toy classification examples.\n\nThis repository is a legacy TensorFlow 1.x script collection, not an installable Python package. Assume Python 3.7-era compatibility work and TensorFlow 1.x\u002FTFLearn semantics. Do not assume TensorFlow 2.x eager execution, `tf.keras` rewrites, or Python 3.13 compatibility.\n\n## Route by task\n\n- For architecture choice, placeholders, tensor shapes, and safe graph-construction probes, read [references\u002Fmodel-reference.md](references\u002Fmodel-reference.md).\n- For training, prediction, checkpoint, cache, and embedding prerequisites, read [references\u002Ftraining-and-prediction.md](references\u002Ftraining-and-prediction.md).\n- For TensorFlow 1.x, TFLearn, checkpoint, data-cache, and model-specific failure modes, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n- To inspect small TensorFlow 1.x graphs without running full training, use [scripts\u002Finspect_tf1_model_shapes.py](scripts\u002Finspect_tf1_model_shapes.py).\n\n## Boundaries\n\nUse this sub-skill only for the classification families above. Route seq2seq, Transformer classification\u002Fgeneration, entity networks, and dynamic memory networks to `sequence-and-memory-models`. Route relation models, two-sentence models, boosting, hybrid CNN+RCNN, and ensemble prediction workflows to `relation-and-ensemble-workflows`. Route raw data cleaning, vocabulary construction, HDF5 generation, and label validation to `data-preparation`.\n\n## Safety posture\n\nFull training usually requires external HDF5\u002Fpickle caches, optional word2vec binaries, checkpoint directories, and long runtimes. These artifacts are not bundled with the skill. Prefer tiny graph construction and shape inspection first; run training or prediction scripts only after data, vocabulary, label, checkpoint, and TensorFlow 1.x compatibility are confirmed.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Ftext-classification\u002Fsub-skills\u002Fclassification-models",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 classification-models",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill classification-models",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill classification-models","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftext-classification\u002Fsub-skills\u002Fclassification-models\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fmodel-reference.md","REFERENCE","参考文档",10122,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftext-classification\u002Fsub-skills\u002Fclassification-models\u002Freferences\u002Fmodel-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftraining-and-prediction.md",9182,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftext-classification\u002Fsub-skills\u002Fclassification-models\u002Freferences\u002Ftraining-and-prediction.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",6509,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftext-classification\u002Fsub-skills\u002Fclassification-models\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Finspect_tf1_model_shapes.py","SCRIPT","脚本",17623,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftext-classification\u002Fsub-skills\u002Fclassification-models\u002Fscripts\u002Finspect_tf1_model_shapes.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",[],[]]