[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FCQPSMABFEF1759N4RXWYC":3,"skill-same:01M7FCQPSMABFEF1759N4RXWYC":59},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7FCQPSMABFEF1759N4RXWYC","universal-tasks",null,"Use and debug TimeMixer imputation, anomaly detection, and classification workflows.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftimemixer\u002Fsub-skills\u002Funiversal-tasks\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: universal-tasks\ndescription: \"Use and debug TimeMixer imputation, anomaly detection, and\n  classification workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# TimeMixer Universal Tasks\n\nUse this sub-skill for TimeMixer's non-forecast branches: imputation, anomaly detection, and classification.\n\n## Route here for\n\n- Building or checking `run.py` commands for imputation, anomaly detection, or classification, using the explicit helper path `\u002Fpath\u002Fto\u002Ftimemixer-skill\u002Fsub-skills\u002Funiversal-tasks\u002Fscripts\u002Fbuild_universal_task_command.py`.\n- Understanding task-specific args such as `mask_rate`, `anomaly_ratio`, UEA padding, and `channel_independence`.\n- Locating result files, saved metrics, and checkpoint paths for the non-forecast branches.\n- Debugging dataset-name, mask, threshold, or classification shape issues that are specific to these tasks.\n  The helper prints commands only; run generated `run.py` commands from `\u002Fpath\u002Fto\u002FTimeMixer-checkout`, not from the skill directory.\n## Safe defaults\n\n1. Use the command builder to assemble a command before any training run. Its source-compatible downsampling defaults are `--down-sampling-layers 1 --down-sampling-window 2`; overrides must keep layers >= 1, window >= 2, and the smallest scale non-empty.\n2. M4 imputation is rejected by the builder because this source M4 loader cannot safely use the universal branch's `pred_len=0`; use the forecasting M4 presets instead.\n3. Keep `c_out` aligned with the input channel count for imputation and anomaly detection.\n4. For multi-feature UEA classification, prefer `channel_independence=0`.\n5. Treat `anomaly_ratio` as a percent value in the source threshold calculation.\n6. Do not launch benchmark-scale training or dataset downloads from this sub-skill.\n\n## Route elsewhere\n\n- Forecasting benchmark scripts, custom forecast presets, or M4\u002FPEMS\u002FECL\u002FETT\u002FSolar recipes: `forecasting-experiments`.\n- Dataset file layout, CSV\u002FNPY\u002FTS placement, or validation of raw inputs: `data-preparation`.\n- TimeMixer tensor internals, PDM\u002FFMM shapes, or decomposition\u002Fdownsampling behavior: `model-architecture`.\n\n## Task map\n\n| Task | Source branch | Typical data key | Main metric | Main outputs |\n| --- | --- | --- | --- | --- |\n| Imputation | `Exp_Imputation` | `ETTh1`, `ETTh2`, `ETTm1`, `ETTm2`, `custom`, `m4`, `PEMS`, `Solar` | Masked-value `MSELoss` during training; MAE\u002FMSE\u002FRMSE\u002FMAPE\u002FMSPE on test | `result_imputation.txt`, `results\u002F\u003Csetting>\u002Fmetrics.npy`, `pred.npy`, `true.npy` |\n| Anomaly detection | `Exp_Anomaly_Detection` | `PSM`, `MSL`, `SMAP`, `SMD`, `SWAT` | Accuracy, precision, recall, F-score after thresholding and adjustment | `result_anomaly_detection.txt` |\n| Classification | `Exp_Classification` | `UEA` | Cross-entropy loss; accuracy for validation\u002Ftest | `results\u002F\u003Csetting>\u002Fresult_classification.txt` |\n\n## Bundled assets\n\n- `references\u002Ftask-workflows.md`\n- `references\u002Ftroubleshooting.md`\n- `scripts\u002Fbuild_universal_task_command.py`\n\n## Safe defaults\n\n1. Use the command builder to assemble a command before any training run.\n2. Keep `c_out` aligned with the input channel count for imputation and anomaly detection.\n3. For multi-feature UEA classification, prefer `channel_independence=0`.\n4. Treat `anomaly_ratio` as a percent value in the source threshold calculation.\n5. Do not launch benchmark-scale training or dataset downloads from this sub-skill.\n","# TimeMixer Universal Tasks\n\nUse this sub-skill for TimeMixer's non-forecast branches: imputation, anomaly detection, and classification.\n\n## Route here for\n\n- Building or checking `run.py` commands for imputation, anomaly detection, or classification, using the explicit helper path `\u002Fpath\u002Fto\u002Ftimemixer-skill\u002Fsub-skills\u002Funiversal-tasks\u002Fscripts\u002Fbuild_universal_task_command.py`.\n- Understanding task-specific args such as `mask_rate`, `anomaly_ratio`, UEA padding, and `channel_independence`.\n- Locating result files, saved metrics, and checkpoint paths for the non-forecast branches.\n- Debugging dataset-name, mask, threshold, or classification shape issues that are specific to these tasks.\n  The helper prints commands only; run generated `run.py` commands from `\u002Fpath\u002Fto\u002FTimeMixer-checkout`, not from the skill directory.\n## Safe defaults\n\n1. Use the command builder to assemble a command before any training run. Its source-compatible downsampling defaults are `--down-sampling-layers 1 --down-sampling-window 2`; overrides must keep layers >= 1, window >= 2, and the smallest scale non-empty.\n2. M4 imputation is rejected by the builder because this source M4 loader cannot safely use the universal branch's `pred_len=0`; use the forecasting M4 presets instead.\n3. Keep `c_out` aligned with the input channel count for imputation and anomaly detection.\n4. For multi-feature UEA classification, prefer `channel_independence=0`.\n5. Treat `anomaly_ratio` as a percent value in the source threshold calculation.\n6. Do not launch benchmark-scale training or dataset downloads from this sub-skill.\n\n## Route elsewhere\n\n- Forecasting benchmark scripts, custom forecast presets, or M4\u002FPEMS\u002FECL\u002FETT\u002FSolar recipes: `forecasting-experiments`.\n- Dataset file layout, CSV\u002FNPY\u002FTS placement, or validation of raw inputs: `data-preparation`.\n- TimeMixer tensor internals, PDM\u002FFMM shapes, or decomposition\u002Fdownsampling behavior: `model-architecture`.\n\n## Task map\n\n| Task | Source branch | Typical data key | Main metric | Main outputs |\n| --- | --- | --- | --- | --- |\n| Imputation | `Exp_Imputation` | `ETTh1`, `ETTh2`, `ETTm1`, `ETTm2`, `custom`, `m4`, `PEMS`, `Solar` | Masked-value `MSELoss` during training; MAE\u002FMSE\u002FRMSE\u002FMAPE\u002FMSPE on test | `result_imputation.txt`, `results\u002F\u003Csetting>\u002Fmetrics.npy`, `pred.npy`, `true.npy` |\n| Anomaly detection | `Exp_Anomaly_Detection` | `PSM`, `MSL`, `SMAP`, `SMD`, `SWAT` | Accuracy, precision, recall, F-score after thresholding and adjustment | `result_anomaly_detection.txt` |\n| Classification | `Exp_Classification` | `UEA` | Cross-entropy loss; accuracy for validation\u002Ftest | `results\u002F\u003Csetting>\u002Fresult_classification.txt` |\n\n## Bundled assets\n\n- `references\u002Ftask-workflows.md`\n- `references\u002Ftroubleshooting.md`\n- `scripts\u002Fbuild_universal_task_command.py`\n\n## Safe defaults\n\n1. Use the command builder to assemble a command before any training run.\n2. Keep `c_out` aligned with the input channel count for imputation and anomaly detection.\n3. For multi-feature UEA classification, prefer `channel_independence=0`.\n4. Treat `anomaly_ratio` as a percent value in the source threshold calculation.\n5. Do not launch benchmark-scale training or dataset downloads from this sub-skill.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Ftimemixer\u002Fsub-skills\u002Funiversal-tasks",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":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill universal-tasks",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill universal-tasks",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill universal-tasks","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\u002Ftimemixer\u002Fsub-skills\u002Funiversal-tasks\u002FSKILL.md",[49,55],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Ftask-workflows.md","REFERENCE","参考文档",6978,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftimemixer\u002Fsub-skills\u002Funiversal-tasks\u002Freferences\u002Ftask-workflows.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Ftroubleshooting.md",4346,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Ftimemixer\u002Fsub-skills\u002Funiversal-tasks\u002Freferences\u002Ftroubleshooting.md",[60,68,73,80,87,94],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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.","MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":69,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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",[],[]]