[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797HDSCERQZDTHE0PC5EW0K":3,"skill-same:01M797HDSCERQZDTHE0PC5EW0K":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},"01M797HDSCERQZDTHE0PC5EW0K","xlnet",null,"Operate the legacy TensorFlow 1.x XLNet repository for model APIs, classification, SQuAD, RACE, and pretraining 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\u002Fxlnet\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: xlnet\ndescription: \"Operate the legacy TensorFlow 1.x XLNet repository for model APIs,\n  classification, SQuAD, RACE, and pretraining workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# XLNet repo skill\n\nUse this skill when a Researcher task involves the original `zihangdai\u002Fxlnet` TensorFlow 1.x repository: released XLNet checkpoints, `xlnet_config.json`, `spiece.model`, source-script fine-tuning, SQuAD\u002FRACE workflows, pretraining data, or direct XLNet graph APIs.\n\n## Before you act\n\n1. Confirm the caller wants the original TensorFlow 1.x XLNet code, not modern Hugging Face `transformers.XLNet*` APIs.\n2. Collect the model bundle paths: `xlnet_config.json`, `spiece.model`, and, for training, the TensorFlow checkpoint prefix.\n3. Identify the workflow family and route to the focused sub-skill below.\n4. Run `scripts\u002Fcheck_xlnet_environment.py --help` when you need a safe import\u002Fconfig diagnostic. It does not download data, open checkpoints, or launch training.\n5. Read [references\u002Fmodel-overview.md](references\u002Fmodel-overview.md) for released model artifacts, memory anchors, and hardware expectations.\n6. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for cross-cutting TensorFlow 1.x, protobuf, Abseil flag, checkpoint, and backend failures.\n7. Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before deciding whether this skill is stale for a checkout.\n\n## Runtime prerequisites\n\n- Legacy TensorFlow 1.x runtime. TensorFlow 2.x lacks several `tf.contrib` APIs used by the repository.\n- `sentencepiece`, `numpy`, and task-specific metric packages such as `scipy`\u002F`scikit-learn` for RACE metrics.\n- An XLNet source checkout or runtime where source modules such as `xlnet`, `modeling`, `run_classifier`, `run_squad`, and `run_race` are importable.\n- Released or fine-tuned model artifacts supplied by the user; this skill does not bundle checkpoints, tokenizer models, or datasets.\n- GPU\u002FTPU hardware only when the selected workflow requires actual training or large evaluation. Many checks and command builders are CPU-safe.\n\nMinimal diagnostic from a runtime where XLNet source is importable:\n\n```bash\npython scripts\u002Fcheck_xlnet_environment.py --repo-root \u002Fpath\u002Fto\u002Fxlnet --config \u002Fpath\u002Fto\u002Fxlnet_config.json\n```\n\nIf no checkout path is needed because the modules are already importable, omit `--repo-root`.\n\n## Route map\n\n| User task | Read next | Why |\n| --- | --- | --- |\n| Use `XLNetConfig`, `RunConfig`, `XLNetModel`, tokenizer helpers, losses, checkpoint loading, or custom TensorFlow graph code. | [sub-skills\u002Fmodel-api\u002FSKILL.md](sub-skills\u002Fmodel-api\u002FSKILL.md) | Covers verified signatures, tensor shapes, config validation, and runtime helpers. |\n| Fine-tune\u002Fevaluate\u002Fpredict GLUE MNLI, STS-B, IMDB, Yelp-5, or processor-backed classification\u002Fregression through `run_classifier.py`. | [sub-skills\u002Fclassification\u002FSKILL.md](sub-skills\u002Fclassification\u002FSKILL.md) | Covers task names, data layouts, train\u002Feval\u002Fpredict flags, and command generation. |\n| Preprocess or fine-tune SQuAD 1.1\u002F2.0, generate predictions, decode n-best answers, or handle no-answer thresholds. | [sub-skills\u002Fsquad-qa\u002FSKILL.md](sub-skills\u002Fsquad-qa\u002FSKILL.md) | Covers SQuAD JSON, feature caches, GPU\u002FTPU recipes, prediction outputs, and threshold metrics. |\n| Run RACE multiple-choice reading-comprehension training\u002Fevaluation or adapt TPU RACE recipes. | [sub-skills\u002Frace-reading-comprehension\u002FSKILL.md](sub-skills\u002Frace-reading-comprehension\u002FSKILL.md) | Covers RACE directory layout, high\u002Fmiddle filtering, four-candidate batching, and TPU command templates. |\n| Prepare raw text or token-id corpora for pretraining, generate TFRecords, or build `train_gpu.py`\u002F`train.py` pretraining commands. | [sub-skills\u002Fdata-pretraining\u002FSKILL.md](sub-skills\u002Fdata-pretraining\u002FSKILL.md) | Covers corpus format, SentencePiece assumptions, record_info files, and pretraining command builders. |\n\n## Operating guardrails\n\n- Do not import several task scripts in the same long-lived Python process; their Abseil flags collide. Inspect one CLI module per process.\n- Keep `data_dir`, `output_dir`, `model_dir`, `predict_dir`, and `init_checkpoint` conceptually separate.\n- Treat `output_dir` as a cache. Use a new cache or overwrite flag when sequence length, task data, tokenizer, or split changes.\n- For multi-GPU task fine-tuning, `num_core_per_host` means number of GPUs and `train_batch_size` is per GPU.\n- Prefer command-builder scripts in the sub-skills when assembling long commands. They print commands only and avoid accidental training, downloads, or GCS writes.\n- Do not treat README result numbers as proof for a new run. They are context anchors; real results require matching data, checkpoints, hardware, and training time.\n\n## Bundled root files\n\n- [references\u002Fmodel-overview.md](references\u002Fmodel-overview.md): released models, artifact contracts, memory table, and result anchors.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md): shared runtime, artifact, and backend troubleshooting.\n- [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md): source snapshot and refresh baseline.\n- [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json): structured metadata for a future managed repo-skill import.\n- [scripts\u002Fcheck_xlnet_environment.py](scripts\u002Fcheck_xlnet_environment.py): safe runtime\u002Fconfig diagnostic helper.\n","# XLNet repo skill\n\nUse this skill when a Researcher task involves the original `zihangdai\u002Fxlnet` TensorFlow 1.x repository: released XLNet checkpoints, `xlnet_config.json`, `spiece.model`, source-script fine-tuning, SQuAD\u002FRACE workflows, pretraining data, or direct XLNet graph APIs.\n\n## Before you act\n\n1. Confirm the caller wants the original TensorFlow 1.x XLNet code, not modern Hugging Face `transformers.XLNet*` APIs.\n2. Collect the model bundle paths: `xlnet_config.json`, `spiece.model`, and, for training, the TensorFlow checkpoint prefix.\n3. Identify the workflow family and route to the focused sub-skill below.\n4. Run `scripts\u002Fcheck_xlnet_environment.py --help` when you need a safe import\u002Fconfig diagnostic. It does not download data, open checkpoints, or launch training.\n5. Read [references\u002Fmodel-overview.md](references\u002Fmodel-overview.md) for released model artifacts, memory anchors, and hardware expectations.\n6. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for cross-cutting TensorFlow 1.x, protobuf, Abseil flag, checkpoint, and backend failures.\n7. Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before deciding whether this skill is stale for a checkout.\n\n## Runtime prerequisites\n\n- Legacy TensorFlow 1.x runtime. TensorFlow 2.x lacks several `tf.contrib` APIs used by the repository.\n- `sentencepiece`, `numpy`, and task-specific metric packages such as `scipy`\u002F`scikit-learn` for RACE metrics.\n- An XLNet source checkout or runtime where source modules such as `xlnet`, `modeling`, `run_classifier`, `run_squad`, and `run_race` are importable.\n- Released or fine-tuned model artifacts supplied by the user; this skill does not bundle checkpoints, tokenizer models, or datasets.\n- GPU\u002FTPU hardware only when the selected workflow requires actual training or large evaluation. Many checks and command builders are CPU-safe.\n\nMinimal diagnostic from a runtime where XLNet source is importable:\n\n```bash\npython scripts\u002Fcheck_xlnet_environment.py --repo-root \u002Fpath\u002Fto\u002Fxlnet --config \u002Fpath\u002Fto\u002Fxlnet_config.json\n```\n\nIf no checkout path is needed because the modules are already importable, omit `--repo-root`.\n\n## Route map\n\n| User task | Read next | Why |\n| --- | --- | --- |\n| Use `XLNetConfig`, `RunConfig`, `XLNetModel`, tokenizer helpers, losses, checkpoint loading, or custom TensorFlow graph code. | [sub-skills\u002Fmodel-api\u002FSKILL.md](sub-skills\u002Fmodel-api\u002FSKILL.md) | Covers verified signatures, tensor shapes, config validation, and runtime helpers. |\n| Fine-tune\u002Fevaluate\u002Fpredict GLUE MNLI, STS-B, IMDB, Yelp-5, or processor-backed classification\u002Fregression through `run_classifier.py`. | [sub-skills\u002Fclassification\u002FSKILL.md](sub-skills\u002Fclassification\u002FSKILL.md) | Covers task names, data layouts, train\u002Feval\u002Fpredict flags, and command generation. |\n| Preprocess or fine-tune SQuAD 1.1\u002F2.0, generate predictions, decode n-best answers, or handle no-answer thresholds. | [sub-skills\u002Fsquad-qa\u002FSKILL.md](sub-skills\u002Fsquad-qa\u002FSKILL.md) | Covers SQuAD JSON, feature caches, GPU\u002FTPU recipes, prediction outputs, and threshold metrics. |\n| Run RACE multiple-choice reading-comprehension training\u002Fevaluation or adapt TPU RACE recipes. | [sub-skills\u002Frace-reading-comprehension\u002FSKILL.md](sub-skills\u002Frace-reading-comprehension\u002FSKILL.md) | Covers RACE directory layout, high\u002Fmiddle filtering, four-candidate batching, and TPU command templates. |\n| Prepare raw text or token-id corpora for pretraining, generate TFRecords, or build `train_gpu.py`\u002F`train.py` pretraining commands. | [sub-skills\u002Fdata-pretraining\u002FSKILL.md](sub-skills\u002Fdata-pretraining\u002FSKILL.md) | Covers corpus format, SentencePiece assumptions, record_info files, and pretraining command builders. |\n\n## Operating guardrails\n\n- Do not import several task scripts in the same long-lived Python process; their Abseil flags collide. Inspect one CLI module per process.\n- Keep `data_dir`, `output_dir`, `model_dir`, `predict_dir`, and `init_checkpoint` conceptually separate.\n- Treat `output_dir` as a cache. Use a new cache or overwrite flag when sequence length, task data, tokenizer, or split changes.\n- For multi-GPU task fine-tuning, `num_core_per_host` means number of GPUs and `train_batch_size` is per GPU.\n- Prefer command-builder scripts in the sub-skills when assembling long commands. They print commands only and avoid accidental training, downloads, or GCS writes.\n- Do not treat README result numbers as proof for a new run. They are context anchors; real results require matching data, checkpoints, hardware, and training time.\n\n## Bundled root files\n\n- [references\u002Fmodel-overview.md](references\u002Fmodel-overview.md): released models, artifact contracts, memory table, and result anchors.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md): shared runtime, artifact, and backend troubleshooting.\n- [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md): source snapshot and refresh baseline.\n- [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json): structured metadata for a future managed repo-skill import.\n- [scripts\u002Fcheck_xlnet_environment.py](scripts\u002Fcheck_xlnet_environment.py): safe runtime\u002Fconfig diagnostic helper.\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\u002Fxlnet",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 xlnet",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill xlnet",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill xlnet","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fxlnet\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fmodel-overview.md","REFERENCE","参考文档",3789,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fxlnet\u002Freferences\u002Fmodel-overview.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",2577,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fxlnet\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",534,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fxlnet\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",5200,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fxlnet\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcheck_xlnet_environment.py","SCRIPT","脚本",4888,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fxlnet\u002Fscripts\u002Fcheck_xlnet_environment.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",[],[]]