[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FEESMSM95N3V4T47PAG6YK":3,"skill-same:01M7FEESMSM95N3V4T47PAG6YK":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7FEESMSM95N3V4T47PAG6YK","training-data",null,"Plan DiffDock score\u002Fconfidence training and prepare datasets, splits, ESM embeddings, caches, and checkpoints safely.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fdiffdock\u002Fsub-skills\u002Ftraining-data\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: training-data\ndescription: \"Plan DiffDock score\u002Fconfidence training and prepare datasets,\n  splits, ESM embeddings, caches, and checkpoints safely.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# DiffDock Training Data\n\nUse this sub-skill when a user wants to plan DiffDock score-model training, confidence-model training, dataset layout checks, split\u002Fcaching decisions, ESM embedding preparation, or checkpoint compatibility before running expensive jobs.\n\n## Start Here\n\n- For score and confidence training command patterns, checkpoint outputs, restart\u002Fpretrain flows, and safe scaling decisions, read [references\u002Ftraining-workflows.md](references\u002Ftraining-workflows.md).\n- For PDBBind, BindingMOAD, DockGen, PoseBusters, van der Mers\u002Fsidechain layouts, split files, CSV schemas, cache behavior, and ESM embedding preparation, read [references\u002Fdata-preparation.md](references\u002Fdata-preparation.md).\n- For parser flag categories, model\u002Fcheckpoint compatibility, all-atom\u002Fcoarse-grained choices, confidence heads, and config portability, read [references\u002Fmodel-and-checkpoint-reference.md](references\u002Fmodel-and-checkpoint-reference.md).\n- For dependency, backend, data path, cache, ESM, W&B, OOM, and checkpoint failures, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Safe Helpers\n\n- Build a command without starting training: [scripts\u002Fbuild_training_command.py](scripts\u002Fbuild_training_command.py).\n- Check dataset and split layout without importing DiffDock, Torch, RDKit, or ProDy: [scripts\u002Fvalidate_dataset_layout.py](scripts\u002Fvalidate_dataset_layout.py).\n- Check an ESM embedding directory or aggregate `.pt` index safely by default: [scripts\u002Fvalidate_esm_embedding_index.py](scripts\u002Fvalidate_esm_embedding_index.py).\n\n## Scope And Routing\n\nThis sub-skill covers training planning and data preparation only: score-model and confidence-model training flags, dataset families, split files, ESM embedding preparation\u002Fconversion, cache naming, model-parameter outputs, and checkpoint compatibility.\n\nRoute these tasks elsewhere:\n\n- Use trained checkpoints for docking prediction, inference YAML tuning, CSV\u002Fbatch inference, and confidence-guided sampling: `..\u002Fdocking-inference\u002FSKILL.md`.\n- Aggregate benchmark metrics, run post-training evaluation, or compare PoseBusters\u002FDockGen\u002FPDBBind results: `..\u002Fevaluation-benchmarks\u002FSKILL.md`.\n- Launch or debug the Gradio UI: `..\u002Fweb-ui\u002FSKILL.md`.\n\n## Quick Commands\n\n```bash\npython sub-skills\u002Ftraining-data\u002Fscripts\u002Fbuild_training_command.py --mode score --dataset pdbbind --data-dir data\u002FPDBBind_processed --split-train data\u002Fsplits\u002Ftimesplit_no_lig_overlap_train --split-val data\u002Fsplits\u002Ftimesplit_no_lig_overlap_val --run-name pdbbind_trial --limit-complexes 16 --n-epochs 1 --batch-size 2\n\npython sub-skills\u002Ftraining-data\u002Fscripts\u002Fvalidate_dataset_layout.py --dataset-type pdbbind --dataset-root data\u002FPDBBind_processed --split-path data\u002Fsplits\u002Ftimesplit_no_lig_overlap_train --max-complexes 5\n\npython sub-skills\u002Ftraining-data\u002Fscripts\u002Fvalidate_esm_embedding_index.py data\u002Fesm2_embeddings.pt --expect-ids data\u002Fsplits\u002Ftimesplit_no_lig_overlap_train\n```\n\n## Key Safety Rules\n\n- Treat training, confidence-dataset generation, ESM extraction, graph preprocessing, and evaluation as expensive GPU\u002Fstorage jobs; do not start them without explicit user approval.\n- Use the bundled helpers first: they print commands or JSON checks and never run DiffDock training.\n- Keep dataset paths, cache paths, and run directories relative to the active DiffDock checkout or user-provided project workspace.\n- Do not assume full imports are available: full training paths require the optional-heavy Torch, PyG, e3nn, W&B, RDKit, ProDy, ESM\u002FOpenFold stack and preferably CUDA.\n- Preserve `model_parameters.yml` with checkpoints; downstream confidence training and inference compatibility depend on it.\n","# DiffDock Training Data\n\nUse this sub-skill when a user wants to plan DiffDock score-model training, confidence-model training, dataset layout checks, split\u002Fcaching decisions, ESM embedding preparation, or checkpoint compatibility before running expensive jobs.\n\n## Start Here\n\n- For score and confidence training command patterns, checkpoint outputs, restart\u002Fpretrain flows, and safe scaling decisions, read [references\u002Ftraining-workflows.md](references\u002Ftraining-workflows.md).\n- For PDBBind, BindingMOAD, DockGen, PoseBusters, van der Mers\u002Fsidechain layouts, split files, CSV schemas, cache behavior, and ESM embedding preparation, read [references\u002Fdata-preparation.md](references\u002Fdata-preparation.md).\n- For parser flag categories, model\u002Fcheckpoint compatibility, all-atom\u002Fcoarse-grained choices, confidence heads, and config portability, read [references\u002Fmodel-and-checkpoint-reference.md](references\u002Fmodel-and-checkpoint-reference.md).\n- For dependency, backend, data path, cache, ESM, W&B, OOM, and checkpoint failures, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Safe Helpers\n\n- Build a command without starting training: [scripts\u002Fbuild_training_command.py](scripts\u002Fbuild_training_command.py).\n- Check dataset and split layout without importing DiffDock, Torch, RDKit, or ProDy: [scripts\u002Fvalidate_dataset_layout.py](scripts\u002Fvalidate_dataset_layout.py).\n- Check an ESM embedding directory or aggregate `.pt` index safely by default: [scripts\u002Fvalidate_esm_embedding_index.py](scripts\u002Fvalidate_esm_embedding_index.py).\n\n## Scope And Routing\n\nThis sub-skill covers training planning and data preparation only: score-model and confidence-model training flags, dataset families, split files, ESM embedding preparation\u002Fconversion, cache naming, model-parameter outputs, and checkpoint compatibility.\n\nRoute these tasks elsewhere:\n\n- Use trained checkpoints for docking prediction, inference YAML tuning, CSV\u002Fbatch inference, and confidence-guided sampling: `..\u002Fdocking-inference\u002FSKILL.md`.\n- Aggregate benchmark metrics, run post-training evaluation, or compare PoseBusters\u002FDockGen\u002FPDBBind results: `..\u002Fevaluation-benchmarks\u002FSKILL.md`.\n- Launch or debug the Gradio UI: `..\u002Fweb-ui\u002FSKILL.md`.\n\n## Quick Commands\n\n```bash\npython sub-skills\u002Ftraining-data\u002Fscripts\u002Fbuild_training_command.py --mode score --dataset pdbbind --data-dir data\u002FPDBBind_processed --split-train data\u002Fsplits\u002Ftimesplit_no_lig_overlap_train --split-val data\u002Fsplits\u002Ftimesplit_no_lig_overlap_val --run-name pdbbind_trial --limit-complexes 16 --n-epochs 1 --batch-size 2\n\npython sub-skills\u002Ftraining-data\u002Fscripts\u002Fvalidate_dataset_layout.py --dataset-type pdbbind --dataset-root data\u002FPDBBind_processed --split-path data\u002Fsplits\u002Ftimesplit_no_lig_overlap_train --max-complexes 5\n\npython sub-skills\u002Ftraining-data\u002Fscripts\u002Fvalidate_esm_embedding_index.py data\u002Fesm2_embeddings.pt --expect-ids data\u002Fsplits\u002Ftimesplit_no_lig_overlap_train\n```\n\n## Key Safety Rules\n\n- Treat training, confidence-dataset generation, ESM extraction, graph preprocessing, and evaluation as expensive GPU\u002Fstorage jobs; do not start them without explicit user approval.\n- Use the bundled helpers first: they print commands or JSON checks and never run DiffDock training.\n- Keep dataset paths, cache paths, and run directories relative to the active DiffDock checkout or user-provided project workspace.\n- Do not assume full imports are available: full training paths require the optional-heavy Torch, PyG, e3nn, W&B, RDKit, ProDy, ESM\u002FOpenFold stack and preferably CUDA.\n- Preserve `model_parameters.yml` with checkpoints; downstream confidence training and inference compatibility depend on it.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","07-后端与架构\u002Fdiffdock\u002Fsub-skills\u002Ftraining-data",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill training-data",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill training-data",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill training-data","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fdiffdock\u002Fsub-skills\u002Ftraining-data\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fdata-preparation.md","REFERENCE","参考文档",7971,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fdiffdock\u002Fsub-skills\u002Ftraining-data\u002Freferences\u002Fdata-preparation.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fmodel-and-checkpoint-reference.md",7836,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fdiffdock\u002Fsub-skills\u002Ftraining-data\u002Freferences\u002Fmodel-and-checkpoint-reference.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Ftraining-workflows.md",7917,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fdiffdock\u002Fsub-skills\u002Ftraining-data\u002Freferences\u002Ftraining-workflows.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Ftroubleshooting.md",6970,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fdiffdock\u002Fsub-skills\u002Ftraining-data\u002Freferences\u002Ftroubleshooting.md",[67,74,79,86,93,100],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":75,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]