[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796A14G2G7WRD4AV2PJFNDF":3,"skill-same:01M796A14G2G7WRD4AV2PJFNDF":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},"01M796A14G2G7WRD4AV2PJFNDF","forecasting",null,"Configure, run, and debug Time-Series-Library long-term, short-term\u002FM4, exogenous\u002FTimeXer, and zero-shot forecasting workflows.","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\u002Ftime-series-library\u002Fsub-skills\u002Fforecasting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: forecasting\ndescription: \"Configure, run, and debug Time-Series-Library long-term,\n  short-term\u002FM4, exogenous\u002FTimeXer, and zero-shot forecasting workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# TSLib Forecasting\n\nUse this sub-skill for TSLib forecasting tasks: long-term forecasting on ETT\u002Fcustom\u002FECL\u002FTraffic\u002FWeather\u002FExchange\u002FILI-style CSVs, short-term M4 forecasting, TimeXer\u002Fexogenous variable recipes, zero-shot forecasting with large time-series models, and forecasting metric\u002Foutput interpretation.\n\n## Route Here\n\n- Build or revise `python run.py --task_name long_term_forecast ...` commands.\n- Configure `--seq_len`, `--label_len`, `--pred_len`, `--features`, `--target`, channel counts, and forecast model dimensions.\n- Use TimeXer or `features MS` for exogenous\u002Ftarget-only forecast settings.\n- Run or debug `short_term_forecast` with M4 seasonal patterns and SMAPE\u002FOWA outputs.\n- Understand zero-shot `--task_name zero_shot_forecast` and optional LTSM model dependencies.\n- Interpret `metrics.npy`, `pred.npy`, `true.npy`, result text files, plot PDFs, and M4 forecast CSVs.\n\n## Reroute\n\n- Data file validation, UEA\u002Fanomaly layouts, generic CLI outputs, or CPU\u002FGPU preflight: use `..\u002Fdata-and-cli\u002FSKILL.md`.\n- Imputation, anomaly detection, and classification: use `..\u002Fimputation-anomaly-classification\u002FSKILL.md`.\n- Adding models, Mamba\u002FLTSM dependency installation, and augmentation flags: use `..\u002Ffoundation-models-and-customization\u002FSKILL.md`.\n\n## Start Fast\n\nRender a small command rather than copying a benchmark script verbatim:\n\n```bash\npython scripts\u002Fbuild_tslib_command.py long-term \\\n  --model DLinear --root-path .\u002Fdataset\u002Ftiny-custom\u002F --data-path tiny.csv \\\n  --model-id tiny_custom --features M --channels 3 \\\n  --seq-len 8 --label-len 4 --pred-len 4 --cpu-smoke\n```\n\nThen run the printed command from the TSLib checkout. Use real benchmark scripts only after paths, GPU, dependencies, and expected cost are clear.\n\n## Forecasting Modes\n\n- **Long-term forecast**: `--task_name long_term_forecast`; uses sliding windows and writes MAE\u002FMSE\u002FRMSE\u002FMAPE\u002FMSPE plus optional DTW.\n- **Short-term\u002FM4 forecast**: `--task_name short_term_forecast --data m4`; uses M4 seasonal patterns and losses such as SMAPE. Final averaged M4 metrics print after all six seasonal forecast CSVs exist.\n- **Exogenous\u002FTimeXer forecast**: still uses `long_term_forecast`; TimeXer recipes often set `--model TimeXer` and may use `features MS` when forecasting a target with exogenous inputs.\n- **Zero-shot forecast**: `--task_name zero_shot_forecast --is_training 0`; model files such as Chronos, Moirai, TimesFM, TiRex, Sundial, and TimeMoE can require optional packages, model downloads, and CUDA assumptions.\n\n## References and Helpers\n\n- `references\u002Fforecasting-workflows.md` gives long-term, M4, TimeXer, and zero-shot recipes.\n- `references\u002Fmetrics-and-results.md` explains forecast metrics and result files.\n- `references\u002Ftroubleshooting.md` covers forecasting-specific data\u002Fwindow\u002Fchannel\u002Fmodel errors.\n- `scripts\u002Fbuild_tslib_command.py` renders safe starter commands for long-term, M4, TimeXer, and zero-shot workflows.\n- `..\u002F..\u002Freferences\u002Fmodel-catalog.md` maps model names to optional dependency surfaces.\n\n## Avoid\n\n- Do not treat zero-shot LTSM source files as verified just because core TSLib imports work.\n- Do not run M4 or long-horizon benchmark scripts as a smoke check; use tiny data and short windows first.\n- Do not use `features MS` without confirming `--target` and output channel expectations.\n","# TSLib Forecasting\n\nUse this sub-skill for TSLib forecasting tasks: long-term forecasting on ETT\u002Fcustom\u002FECL\u002FTraffic\u002FWeather\u002FExchange\u002FILI-style CSVs, short-term M4 forecasting, TimeXer\u002Fexogenous variable recipes, zero-shot forecasting with large time-series models, and forecasting metric\u002Foutput interpretation.\n\n## Route Here\n\n- Build or revise `python run.py --task_name long_term_forecast ...` commands.\n- Configure `--seq_len`, `--label_len`, `--pred_len`, `--features`, `--target`, channel counts, and forecast model dimensions.\n- Use TimeXer or `features MS` for exogenous\u002Ftarget-only forecast settings.\n- Run or debug `short_term_forecast` with M4 seasonal patterns and SMAPE\u002FOWA outputs.\n- Understand zero-shot `--task_name zero_shot_forecast` and optional LTSM model dependencies.\n- Interpret `metrics.npy`, `pred.npy`, `true.npy`, result text files, plot PDFs, and M4 forecast CSVs.\n\n## Reroute\n\n- Data file validation, UEA\u002Fanomaly layouts, generic CLI outputs, or CPU\u002FGPU preflight: use `..\u002Fdata-and-cli\u002FSKILL.md`.\n- Imputation, anomaly detection, and classification: use `..\u002Fimputation-anomaly-classification\u002FSKILL.md`.\n- Adding models, Mamba\u002FLTSM dependency installation, and augmentation flags: use `..\u002Ffoundation-models-and-customization\u002FSKILL.md`.\n\n## Start Fast\n\nRender a small command rather than copying a benchmark script verbatim:\n\n```bash\npython scripts\u002Fbuild_tslib_command.py long-term \\\n  --model DLinear --root-path .\u002Fdataset\u002Ftiny-custom\u002F --data-path tiny.csv \\\n  --model-id tiny_custom --features M --channels 3 \\\n  --seq-len 8 --label-len 4 --pred-len 4 --cpu-smoke\n```\n\nThen run the printed command from the TSLib checkout. Use real benchmark scripts only after paths, GPU, dependencies, and expected cost are clear.\n\n## Forecasting Modes\n\n- **Long-term forecast**: `--task_name long_term_forecast`; uses sliding windows and writes MAE\u002FMSE\u002FRMSE\u002FMAPE\u002FMSPE plus optional DTW.\n- **Short-term\u002FM4 forecast**: `--task_name short_term_forecast --data m4`; uses M4 seasonal patterns and losses such as SMAPE. Final averaged M4 metrics print after all six seasonal forecast CSVs exist.\n- **Exogenous\u002FTimeXer forecast**: still uses `long_term_forecast`; TimeXer recipes often set `--model TimeXer` and may use `features MS` when forecasting a target with exogenous inputs.\n- **Zero-shot forecast**: `--task_name zero_shot_forecast --is_training 0`; model files such as Chronos, Moirai, TimesFM, TiRex, Sundial, and TimeMoE can require optional packages, model downloads, and CUDA assumptions.\n\n## References and Helpers\n\n- `references\u002Fforecasting-workflows.md` gives long-term, M4, TimeXer, and zero-shot recipes.\n- `references\u002Fmetrics-and-results.md` explains forecast metrics and result files.\n- `references\u002Ftroubleshooting.md` covers forecasting-specific data\u002Fwindow\u002Fchannel\u002Fmodel errors.\n- `scripts\u002Fbuild_tslib_command.py` renders safe starter commands for long-term, M4, TimeXer, and zero-shot workflows.\n- `..\u002F..\u002Freferences\u002Fmodel-catalog.md` maps model names to optional dependency surfaces.\n\n## Avoid\n\n- Do not treat zero-shot LTSM source files as verified just because core TSLib imports work.\n- Do not run M4 or long-horizon benchmark scripts as a smoke check; use tiny data and short windows first.\n- Do not use `features MS` without confirming `--target` and output channel expectations.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Ftime-series-library\u002Fsub-skills\u002Fforecasting",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 forecasting",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill forecasting",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill forecasting","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftime-series-library\u002Fsub-skills\u002Fforecasting\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fforecasting-workflows.md","REFERENCE","参考文档",2759,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftime-series-library\u002Fsub-skills\u002Fforecasting\u002Freferences\u002Fforecasting-workflows.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fmetrics-and-results.md",1605,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftime-series-library\u002Fsub-skills\u002Fforecasting\u002Freferences\u002Fmetrics-and-results.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",2277,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftime-series-library\u002Fsub-skills\u002Fforecasting\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fbuild_tslib_command.py","SCRIPT","脚本",6568,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftime-series-library\u002Fsub-skills\u002Fforecasting\u002Fscripts\u002Fbuild_tslib_command.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",[],[]]