[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FCPQB0KZ7K7KC6YX4CZSCR":3,"skill-same:01M7FCPQB0KZ7K7KC6YX4CZSCR":78},{"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},"01M7FCPQB0KZ7K7KC6YX4CZSCR","time-series-library",null,"Use Time-Series-Library (TSLib) to configure, run, debug, and adapt deep time-series forecasting, imputation, anomaly detection, classification, zero-shot, and model-customization workflows.","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\u002F06-前端与设计\u002Ftime-series-library\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: time-series-library\ndescription: \"Use Time-Series-Library (TSLib) to configure, run, debug, and\n  adapt deep time-series forecasting, imputation, anomaly detection,\n  classification, zero-shot, and model-customization workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Time-Series-Library (TSLib)\n\nUse this skill when the task names Time-Series-Library, TSLib, `run.py`, TimesNet, TimeXer, iTransformer, PatchTST, DLinear, M4, ETT, UEA, PSM\u002FMSL\u002FSMAP\u002FSMD\u002FSWAT, long-term forecasting, short-term forecasting, time-series imputation, anomaly detection, classification, zero-shot forecasting, or adapting a model\u002Fscript inside a TSLib-style checkout.\n\n## Start Here\n\n1. Confirm the environment and source layout before running training-scale work. From this skill directory, pass the user's TSLib checkout as `--repo-root`:\n   ```bash\n   python scripts\u002Fcheck_tslib_environment.py --repo-root \u002Fpath\u002Fto\u002FTime-Series-Library --check-torch --check-core-imports\n   ```\n2. For command\u002Fdata debugging, create a tiny local `custom` CSV in the user's checkout instead of downloading benchmark data:\n   ```bash\n   python scripts\u002Fcreate_tiny_tslib_dataset.py --output \u002Fpath\u002Fto\u002FTime-Series-Library\u002Fdataset\u002Ftiny-custom\u002Ftiny.csv\n   ```\n3. Use the route map below. TSLib has one unified CLI (`python run.py ...`), but each task has different data layouts, output files, metrics, and failure modes.\n4. Prefer `--no_use_gpu`, tiny custom data, `--train_epochs 1`, and `--num_workers 0` for smoke checks. Treat upstream benchmark scripts as templates, not as safe default commands.\n\n## Route by Task\n\n- **Data layout, CLI flags, outputs, and preflight checks**: use `sub-skills\u002Fdata-and-cli\u002FSKILL.md` for `run.py` arguments, dataset names, local-vs-Hugging Face fallback behavior, GPU flags, result\u002Fcheckpoint folders, and safe data validation.\n- **Forecasting workflows**: use `sub-skills\u002Fforecasting\u002FSKILL.md` for long-term forecasting, short-term\u002FM4 forecasting, exogenous\u002FTimeXer recipes, zero-shot forecast routing, metrics, M4 summary behavior, and forecast command construction.\n- **Imputation, anomaly detection, and classification**: use `sub-skills\u002Fimputation-anomaly-classification\u002FSKILL.md` for masked reconstruction, reconstruction-threshold anomaly detection, UEA classification, task metrics, and dataset-specific troubleshooting.\n- **Model catalog, optional dependencies, and customization**: use `sub-skills\u002Ffoundation-models-and-customization\u002FSKILL.md` for dynamic model discovery, Mamba and large time-series model dependencies, augmentation flags, custom `models\u002F\u003CName>.py` files, and contribution-style script additions.\n\n## Core Mental Model\n\nTSLib is a source-tree benchmark framework rather than a packaged library with console entry points. The normal flow is:\n\n```text\nchoose a task and bash\u002Fscript template -> run python run.py with explicit flags ->\nrun.py dispatches to exp\u002FExp_* -> data_provider builds datasets\u002Floaders ->\nmodels\u002F\u003CName>.py is lazy-imported -> train\u002Ftest writes checkpoints, metrics, and result files\n```\n\nImportant consequences:\n\n- `--task_name` selects the experiment class, not just reporting labels.\n- `--data` selects a loader family; `--root_path` and `--data_path` must match that family.\n- `--model` must match a Python file under `models\u002F`; `Exp_Basic` scans that directory dynamically.\n- Many upstream shell scripts export `CUDA_VISIBLE_DEVICES` and run full benchmark settings. Remove or change those exports for your machine and use smoke settings first.\n- Several optional model families need extra packages or model downloads; do not assume a basic TSLib environment can import every file in `models\u002F`.\n\n## References\n\n- `references\u002Finstallation-and-environment.md` explains public installation choices, optional dependencies, and safe smoke checks.\n- `references\u002Fcli-arguments.md` summarizes the unified `run.py` argument families and task dispatch.\n- `references\u002Fdata-formats.md` documents CSV, M4, anomaly, and UEA layouts plus local-vs-Hub behavior.\n- `references\u002Fmodel-catalog.md` lists model families, dynamic discovery, and optional dependency surfaces.\n- `references\u002Ftroubleshooting.md` covers cross-cutting install\u002Fimport, data, CLI, GPU, output, and source-tree issues.\n- `references\u002Frepo-provenance.md` records the source revision and evidence baseline.\n\n## Helpers\n\n- `scripts\u002Fcheck_tslib_environment.py` checks Python imports, selected models, `run.py --help`, and optional torch CUDA status without training; pass `--repo-root` for the user's TSLib checkout.\n- `scripts\u002Fcreate_tiny_tslib_dataset.py` creates a small local `custom` CSV with a `date` column and target column for smoke commands.\n\n## Operating Rules\n\n- Do not run benchmark-scale scripts or download large datasets\u002Fmodel weights unless the user explicitly wants that cost.\n- Do not recommend a raw upstream `scripts\u002F...\u002F*.sh` command without checking its `CUDA_VISIBLE_DEVICES`, dataset path, epochs, model dependencies, and output folders.\n- Use local tiny fixtures for CLI\u002Fdata validation; use real benchmark data only for final experiment work.\n- Treat Mamba\u002FMambaSL and large time-series model files as optional dependency routes. First decide whether the user's task requires them; otherwise choose a core model such as DLinear, TimesNet, TimeXer, PatchTST, or Transformer for smoke checks.\n- Keep generated commands generic and portable across TSLib checkouts; never rely on a particular local checkout path.\n","# Time-Series-Library (TSLib)\n\nUse this skill when the task names Time-Series-Library, TSLib, `run.py`, TimesNet, TimeXer, iTransformer, PatchTST, DLinear, M4, ETT, UEA, PSM\u002FMSL\u002FSMAP\u002FSMD\u002FSWAT, long-term forecasting, short-term forecasting, time-series imputation, anomaly detection, classification, zero-shot forecasting, or adapting a model\u002Fscript inside a TSLib-style checkout.\n\n## Start Here\n\n1. Confirm the environment and source layout before running training-scale work. From this skill directory, pass the user's TSLib checkout as `--repo-root`:\n   ```bash\n   python scripts\u002Fcheck_tslib_environment.py --repo-root \u002Fpath\u002Fto\u002FTime-Series-Library --check-torch --check-core-imports\n   ```\n2. For command\u002Fdata debugging, create a tiny local `custom` CSV in the user's checkout instead of downloading benchmark data:\n   ```bash\n   python scripts\u002Fcreate_tiny_tslib_dataset.py --output \u002Fpath\u002Fto\u002FTime-Series-Library\u002Fdataset\u002Ftiny-custom\u002Ftiny.csv\n   ```\n3. Use the route map below. TSLib has one unified CLI (`python run.py ...`), but each task has different data layouts, output files, metrics, and failure modes.\n4. Prefer `--no_use_gpu`, tiny custom data, `--train_epochs 1`, and `--num_workers 0` for smoke checks. Treat upstream benchmark scripts as templates, not as safe default commands.\n\n## Route by Task\n\n- **Data layout, CLI flags, outputs, and preflight checks**: use `sub-skills\u002Fdata-and-cli\u002FSKILL.md` for `run.py` arguments, dataset names, local-vs-Hugging Face fallback behavior, GPU flags, result\u002Fcheckpoint folders, and safe data validation.\n- **Forecasting workflows**: use `sub-skills\u002Fforecasting\u002FSKILL.md` for long-term forecasting, short-term\u002FM4 forecasting, exogenous\u002FTimeXer recipes, zero-shot forecast routing, metrics, M4 summary behavior, and forecast command construction.\n- **Imputation, anomaly detection, and classification**: use `sub-skills\u002Fimputation-anomaly-classification\u002FSKILL.md` for masked reconstruction, reconstruction-threshold anomaly detection, UEA classification, task metrics, and dataset-specific troubleshooting.\n- **Model catalog, optional dependencies, and customization**: use `sub-skills\u002Ffoundation-models-and-customization\u002FSKILL.md` for dynamic model discovery, Mamba and large time-series model dependencies, augmentation flags, custom `models\u002F\u003CName>.py` files, and contribution-style script additions.\n\n## Core Mental Model\n\nTSLib is a source-tree benchmark framework rather than a packaged library with console entry points. The normal flow is:\n\n```text\nchoose a task and bash\u002Fscript template -> run python run.py with explicit flags ->\nrun.py dispatches to exp\u002FExp_* -> data_provider builds datasets\u002Floaders ->\nmodels\u002F\u003CName>.py is lazy-imported -> train\u002Ftest writes checkpoints, metrics, and result files\n```\n\nImportant consequences:\n\n- `--task_name` selects the experiment class, not just reporting labels.\n- `--data` selects a loader family; `--root_path` and `--data_path` must match that family.\n- `--model` must match a Python file under `models\u002F`; `Exp_Basic` scans that directory dynamically.\n- Many upstream shell scripts export `CUDA_VISIBLE_DEVICES` and run full benchmark settings. Remove or change those exports for your machine and use smoke settings first.\n- Several optional model families need extra packages or model downloads; do not assume a basic TSLib environment can import every file in `models\u002F`.\n\n## References\n\n- `references\u002Finstallation-and-environment.md` explains public installation choices, optional dependencies, and safe smoke checks.\n- `references\u002Fcli-arguments.md` summarizes the unified `run.py` argument families and task dispatch.\n- `references\u002Fdata-formats.md` documents CSV, M4, anomaly, and UEA layouts plus local-vs-Hub behavior.\n- `references\u002Fmodel-catalog.md` lists model families, dynamic discovery, and optional dependency surfaces.\n- `references\u002Ftroubleshooting.md` covers cross-cutting install\u002Fimport, data, CLI, GPU, output, and source-tree issues.\n- `references\u002Frepo-provenance.md` records the source revision and evidence baseline.\n\n## Helpers\n\n- `scripts\u002Fcheck_tslib_environment.py` checks Python imports, selected models, `run.py --help`, and optional torch CUDA status without training; pass `--repo-root` for the user's TSLib checkout.\n- `scripts\u002Fcreate_tiny_tslib_dataset.py` creates a small local `custom` CSV with a `date` column and target column for smoke commands.\n\n## Operating Rules\n\n- Do not run benchmark-scale scripts or download large datasets\u002Fmodel weights unless the user explicitly wants that cost.\n- Do not recommend a raw upstream `scripts\u002F...\u002F*.sh` command without checking its `CUDA_VISIBLE_DEVICES`, dataset path, epochs, model dependencies, and output folders.\n- Use local tiny fixtures for CLI\u002Fdata validation; use real benchmark data only for final experiment work.\n- Treat Mamba\u002FMambaSL and large time-series model files as optional dependency routes. First decide whether the user's task requires them; otherwise choose a core model such as DLinear, TimesNet, TimeXer, PatchTST, or Transformer for smoke checks.\n- Keep generated commands generic and portable across TSLib checkouts; never rely on a particular local checkout path.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Ftime-series-library",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 time-series-library",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill time-series-library",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill time-series-library","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftime-series-library\u002FSKILL.md",[48,54,58,62,66,70,74],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fcli-arguments.md","REFERENCE","参考文档",4040,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftime-series-library\u002Freferences\u002Fcli-arguments.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fdata-formats.md",3312,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftime-series-library\u002Freferences\u002Fdata-formats.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Finstallation-and-environment.md",4715,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftime-series-library\u002Freferences\u002Finstallation-and-environment.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fmodel-catalog.md",3688,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftime-series-library\u002Freferences\u002Fmodel-catalog.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Frepo-provenance.md",1422,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftime-series-library\u002Freferences\u002Frepo-provenance.md",{"path":71,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Frepo-routing-metadata.json",513,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftime-series-library\u002Freferences\u002Frepo-routing-metadata.json",{"path":75,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Ftroubleshooting.md",4046,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftime-series-library\u002Freferences\u002Ftroubleshooting.md",[79,86,91,98,105,112],{"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},"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":87,"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":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"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":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"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",[],[]]