[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QFMPM5B9H3V9SW9RZGHBKG":3,"skill-same:01M6QFMPM5B9H3V9SW9RZGHBKG":103},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":14,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6QFMPM5B9H3V9SW9RZGHBKG","pyhealth",null,"Builds clinical deep-learning pipelines with PyHealth using its Dataset → Task → Model → Trainer → Metrics pattern. Covers loading MIMIC-III\u002FIV, eICU, OMOP, SleepEDF, ChestXray14 and EHRShot data, defining prediction tasks (mortality, readmission, length of stay, drug recommendation, sleep staging, ICD coding, EEG events), models such as Transformer, RETAIN, GAMENet, SafeDrug and StageNet, training with Trainer, and ICD\u002FATC\u002FNDC\u002FRxNorm code lookup and cross-mapping. Use when building a clinical prediction model on EHR data. Use when working with MIMIC or eICU datasets. Use when recommending drugs or staging sleep from signals. Use when mapping medical codes between ICD, ATC, NDC or RxNorm. Not for generic PyTorch on tabular data.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-pyhealth\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"pattern","retain","sleep","loading","mapping","dataset","clinical","medical","deep","signals","deep learning","coding","model","healthcare","data","code","tasks","training","pytorch","2026-11-10 10:12:30",false,"---\nname: pyhealth\ndescription: Builds clinical deep-learning pipelines with PyHealth using its Dataset → Task → Model → Trainer → Metrics pattern. Covers loading MIMIC-III\u002FIV, eICU, OMOP, SleepEDF, ChestXray14 and EHRShot data, defining prediction tasks (mortality, readmission, length of stay, drug recommendation, sleep staging, ICD coding, EEG events), models such as Transformer, RETAIN, GAMENet, SafeDrug and StageNet, training with Trainer, and ICD\u002FATC\u002FNDC\u002FRxNorm code lookup and cross-mapping. Use when building a clinical prediction model on EHR data. Use when working with MIMIC or eICU datasets. Use when recommending drugs or staging sleep from signals. Use when mapping medical codes between ICD, ATC, NDC or RxNorm. Not for generic PyTorch on tabular data.\nlicense: MIT\nmetadata:\n  version: '1.1'\n  category: clinical-and-health\n  maintainer: Kalaris Labs\n  tags: clinical machine learning, EHR, MIMIC, healthcare AI, deep learning\n---\n\n# PyHealth\n\nPyHealth (https:\u002F\u002Fpyhealth.dev\u002F) is a Python toolkit for clinical deep learning. It provides a unified, modular pipeline across electronic health records (EHR), physiological signals, and medical imaging.\n\nThe library is built around a **5-stage pipeline** — `Dataset → Task → Model → Trainer → Metrics` — where each stage is replaceable and the interfaces between stages are stable. Code that follows this pipeline shape composes well; code that bypasses it usually fights the library.\n\n## When to use this skill\n\nUse this skill whenever the user is doing clinical\u002Fhealthcare ML and any of the following are true:\n\n- They mention PyHealth, MIMIC-III\u002FIV, eICU, OMOP-CDM, EHRShot, SleepEDF, SHHS, ISRUC, COVID19-CXR, ChestX-ray14, TUEV\u002FTUAB.\n- They want to predict mortality, readmission, length of stay, drug recommendations, sleep stages, ICD codes, EEG events, or de-identification.\n- They need to look up or cross-map medical codes (ICD-9-CM, ICD-10-CM, ATC, NDC, RxNorm, CCS).\n- They have EHR-shaped data and want to train a clinical model without writing the plumbing themselves.\n\nPyHealth is the right tool when the workflow fits its 5 stages. If the user just wants generic PyTorch on tabular data, this skill is not necessary.\n\n## Installation (uv)\n\nPyHealth 2.0 requires Python ≥ 3.12, \u003C 3.14. Use `uv` for environment management — it's faster and reproducible.\n\n```bash\n# Create a project with the right Python\nuv init my-pyhealth-project\ncd my-pyhealth-project\nuv python pin 3.12\n\n# Add PyHealth (this also pulls in PyTorch and friends)\nuv add pyhealth\n\n# Run scripts inside the env\nuv run python train.py\n```\n\nFor a one-off script without a project, use `uv run --with pyhealth python script.py`. For the legacy 1.x line (Python 3.9+), `uv add pyhealth==1.16`. Detailed install notes, MIMIC access, and GPU\u002FCPU device tips are in `references\u002Finstallation.md`.\n\n## The 5-stage pipeline\n\nA complete pipeline is typically \u003C20 lines. This is the canonical shape — start here and modify pieces:\n\n```python\nfrom pyhealth.datasets import MIMIC3Dataset, split_by_patient, get_dataloader\nfrom pyhealth.tasks import MortalityPredictionMIMIC3\nfrom pyhealth.models import Transformer\nfrom pyhealth.trainer import Trainer\nfrom pyhealth.metrics.binary import binary_metrics_fn\n\n# 1. Dataset — raw patient registry\nbase = MIMIC3Dataset(\n    root=\"https:\u002F\u002Fstorage.googleapis.com\u002Fpyhealth\u002FSynthetic_MIMIC-III\u002F\",\n    tables=[\"DIAGNOSES_ICD\", \"PROCEDURES_ICD\", \"PRESCRIPTIONS\"],\n)\n\n# 2. Task — converts patients into supervised samples\nsamples = base.set_task(MortalityPredictionMIMIC3())\n\n# 3. Split + DataLoaders (split by patient to avoid leakage)\ntrain_ds, val_ds, test_ds = split_by_patient(samples, [0.8, 0.1, 0.1])\ntrain_loader = get_dataloader(train_ds, batch_size=32, shuffle=True)\nval_loader   = get_dataloader(val_ds,   batch_size=32, shuffle=False)\ntest_loader  = get_dataloader(test_ds,  batch_size=32, shuffle=False)\n\n# 4. Model — must be passed the SampleDataset, not the BaseDataset\nmodel = Transformer(dataset=samples)\n\n# 5. Train + evaluate\ntrainer = Trainer(model=model)\ntrainer.train(\n    train_dataloader=train_loader,\n    val_dataloader=val_loader,\n    epochs=50,\n    monitor=\"pr_auc\",\n)\n\ny_true, y_prob, _ = trainer.inference(test_loader)\nprint(binary_metrics_fn(y_true, y_prob, metrics=[\"pr_auc\", \"roc_auc\"]))\n```\n\nA copy-pasteable starter is in `assets\u002Fstarter_pipeline.py`.\n\n## Critical things to get right\n\nThese are the mistakes that PyHealth code most commonly trips on. Internalize them before writing pipelines:\n\n1. **Models take a `SampleDataset`, not a `BaseDataset`.** `MIMIC3Dataset(...)` returns a `BaseDataset` (a queryable patient registry). Only after `.set_task(task)` do you get a `SampleDataset`, which is what models, splitters, and DataLoaders expect. If you pass `base` to a model, it will fail or behave wrong.\n\n2. **Always split by patient (or visit), not by sample.** Random sample-level splits leak information across train\u002Ftest because the same patient can appear in both. Use `split_by_patient` for patient-level prediction, `split_by_visit` only when visits are independent.\n\n3. **Match the task to the dataset.** Tasks are dataset-specific: `MortalityPredictionMIMIC3` won't work on MIMIC-IV — use `MortalityPredictionMIMIC4` or `InHospitalMortalityMIMIC4`. The full mapping is in `references\u002Ftasks.md`.\n\n4. **Pick `monitor` to match the task type.** For binary classification use `\"pr_auc\"` or `\"roc_auc\"`. For multilabel (drug rec) use `\"pr_auc_samples\"` or `\"jaccard_samples\"`. For multiclass use `\"accuracy\"` or `\"f1_macro\"`. Wrong monitor → checkpoint selection saves the wrong epoch.\n\n5. **MIMIC-IV uses `ehr_root=`, not `root=`.** This is the one inconsistency in the dataset constructors.\n\n6. **For reproducible work, point `cache_dir=` somewhere persistent.** PyHealth caches the parsed dataset; without `cache_dir`, you re-parse every run.\n\n## How to use this skill\n\nPyHealth has a large API surface — there's no point loading it all at once. Read the reference file that matches the user's task:\n\n| If the user is asking about… | Read |\n|---|---|\n| Installing, env setup, MIMIC access, GPU | `references\u002Finstallation.md` |\n| Which dataset class to use, loading patterns, splitting | `references\u002Fdatasets.md` |\n| What prediction task to choose (mortality, readmission, drug rec, sleep…) | `references\u002Ftasks.md` |\n| Picking a model architecture, model-specific arguments | `references\u002Fmodels.md` |\n| Looking up or cross-mapping ICD\u002FATC\u002FNDC\u002FRxNorm\u002FCCS codes, tokenizers | `references\u002Fmedcode.md` |\n| End-to-end recipes for common scenarios | `references\u002Fexamples.md` |\n\nFor multi-step tasks (e.g., \"build a drug recommendation pipeline on MIMIC-IV\"), read `tasks.md` + `models.md` + `examples.md` together — they cross-reference each other.\n\n## A note on style\n\nWrite minimal, idiomatic PyHealth. The library is opinionated; lean into its abstractions instead of reimplementing them in raw PyTorch. If you find yourself writing a custom training loop, ask whether `Trainer` would do the job — it almost always will, and it handles checkpointing, logging, and best-model selection for free.\n\nWhen the user has private MIMIC access, point them at the local CSV root; for demos and learning, the synthetic MIMIC-III bucket (`https:\u002F\u002Fstorage.googleapis.com\u002Fpyhealth\u002FSynthetic_MIMIC-III\u002F`) is fine and works without credentialing.\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm data access permissions, de-identification status and the governing regulations or protocols.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Work on a de-identified sample or synthetic data first.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Check outputs against clinical guidelines and reporting standards; have a qualified human review clinical content.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| Data appears to contain identifiable patient information | Stop and ask the user before processing further. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Outputs are decision support for qualified professionals, not medical advice; never present them as diagnoses or orders.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `transformers`: Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audi…\n","# PyHealth\n\nPyHealth (https:\u002F\u002Fpyhealth.dev\u002F) is a Python toolkit for clinical deep learning. It provides a unified, modular pipeline across electronic health records (EHR), physiological signals, and medical imaging.\n\nThe library is built around a **5-stage pipeline** — `Dataset → Task → Model → Trainer → Metrics` — where each stage is replaceable and the interfaces between stages are stable. Code that follows this pipeline shape composes well; code that bypasses it usually fights the library.\n\n## When to use this skill\n\nUse this skill whenever the user is doing clinical\u002Fhealthcare ML and any of the following are true:\n\n- They mention PyHealth, MIMIC-III\u002FIV, eICU, OMOP-CDM, EHRShot, SleepEDF, SHHS, ISRUC, COVID19-CXR, ChestX-ray14, TUEV\u002FTUAB.\n- They want to predict mortality, readmission, length of stay, drug recommendations, sleep stages, ICD codes, EEG events, or de-identification.\n- They need to look up or cross-map medical codes (ICD-9-CM, ICD-10-CM, ATC, NDC, RxNorm, CCS).\n- They have EHR-shaped data and want to train a clinical model without writing the plumbing themselves.\n\nPyHealth is the right tool when the workflow fits its 5 stages. If the user just wants generic PyTorch on tabular data, this skill is not necessary.\n\n## Installation (uv)\n\nPyHealth 2.0 requires Python ≥ 3.12, \u003C 3.14. Use `uv` for environment management — it's faster and reproducible.\n\n```bash\n# Create a project with the right Python\nuv init my-pyhealth-project\ncd my-pyhealth-project\nuv python pin 3.12\n\n# Add PyHealth (this also pulls in PyTorch and friends)\nuv add pyhealth\n\n# Run scripts inside the env\nuv run python train.py\n```\n\nFor a one-off script without a project, use `uv run --with pyhealth python script.py`. For the legacy 1.x line (Python 3.9+), `uv add pyhealth==1.16`. Detailed install notes, MIMIC access, and GPU\u002FCPU device tips are in `references\u002Finstallation.md`.\n\n## The 5-stage pipeline\n\nA complete pipeline is typically \u003C20 lines. This is the canonical shape — start here and modify pieces:\n\n```python\nfrom pyhealth.datasets import MIMIC3Dataset, split_by_patient, get_dataloader\nfrom pyhealth.tasks import MortalityPredictionMIMIC3\nfrom pyhealth.models import Transformer\nfrom pyhealth.trainer import Trainer\nfrom pyhealth.metrics.binary import binary_metrics_fn\n\n# 1. Dataset — raw patient registry\nbase = MIMIC3Dataset(\n    root=\"https:\u002F\u002Fstorage.googleapis.com\u002Fpyhealth\u002FSynthetic_MIMIC-III\u002F\",\n    tables=[\"DIAGNOSES_ICD\", \"PROCEDURES_ICD\", \"PRESCRIPTIONS\"],\n)\n\n# 2. Task — converts patients into supervised samples\nsamples = base.set_task(MortalityPredictionMIMIC3())\n\n# 3. Split + DataLoaders (split by patient to avoid leakage)\ntrain_ds, val_ds, test_ds = split_by_patient(samples, [0.8, 0.1, 0.1])\ntrain_loader = get_dataloader(train_ds, batch_size=32, shuffle=True)\nval_loader   = get_dataloader(val_ds,   batch_size=32, shuffle=False)\ntest_loader  = get_dataloader(test_ds,  batch_size=32, shuffle=False)\n\n# 4. Model — must be passed the SampleDataset, not the BaseDataset\nmodel = Transformer(dataset=samples)\n\n# 5. Train + evaluate\ntrainer = Trainer(model=model)\ntrainer.train(\n    train_dataloader=train_loader,\n    val_dataloader=val_loader,\n    epochs=50,\n    monitor=\"pr_auc\",\n)\n\ny_true, y_prob, _ = trainer.inference(test_loader)\nprint(binary_metrics_fn(y_true, y_prob, metrics=[\"pr_auc\", \"roc_auc\"]))\n```\n\nA copy-pasteable starter is in `assets\u002Fstarter_pipeline.py`.\n\n## Critical things to get right\n\nThese are the mistakes that PyHealth code most commonly trips on. Internalize them before writing pipelines:\n\n1. **Models take a `SampleDataset`, not a `BaseDataset`.** `MIMIC3Dataset(...)` returns a `BaseDataset` (a queryable patient registry). Only after `.set_task(task)` do you get a `SampleDataset`, which is what models, splitters, and DataLoaders expect. If you pass `base` to a model, it will fail or behave wrong.\n\n2. **Always split by patient (or visit), not by sample.** Random sample-level splits leak information across train\u002Ftest because the same patient can appear in both. Use `split_by_patient` for patient-level prediction, `split_by_visit` only when visits are independent.\n\n3. **Match the task to the dataset.** Tasks are dataset-specific: `MortalityPredictionMIMIC3` won't work on MIMIC-IV — use `MortalityPredictionMIMIC4` or `InHospitalMortalityMIMIC4`. The full mapping is in `references\u002Ftasks.md`.\n\n4. **Pick `monitor` to match the task type.** For binary classification use `\"pr_auc\"` or `\"roc_auc\"`. For multilabel (drug rec) use `\"pr_auc_samples\"` or `\"jaccard_samples\"`. For multiclass use `\"accuracy\"` or `\"f1_macro\"`. Wrong monitor → checkpoint selection saves the wrong epoch.\n\n5. **MIMIC-IV uses `ehr_root=`, not `root=`.** This is the one inconsistency in the dataset constructors.\n\n6. **For reproducible work, point `cache_dir=` somewhere persistent.** PyHealth caches the parsed dataset; without `cache_dir`, you re-parse every run.\n\n## How to use this skill\n\nPyHealth has a large API surface — there's no point loading it all at once. Read the reference file that matches the user's task:\n\n| If the user is asking about… | Read |\n|---|---|\n| Installing, env setup, MIMIC access, GPU | `references\u002Finstallation.md` |\n| Which dataset class to use, loading patterns, splitting | `references\u002Fdatasets.md` |\n| What prediction task to choose (mortality, readmission, drug rec, sleep…) | `references\u002Ftasks.md` |\n| Picking a model architecture, model-specific arguments | `references\u002Fmodels.md` |\n| Looking up or cross-mapping ICD\u002FATC\u002FNDC\u002FRxNorm\u002FCCS codes, tokenizers | `references\u002Fmedcode.md` |\n| End-to-end recipes for common scenarios | `references\u002Fexamples.md` |\n\nFor multi-step tasks (e.g., \"build a drug recommendation pipeline on MIMIC-IV\"), read `tasks.md` + `models.md` + `examples.md` together — they cross-reference each other.\n\n## A note on style\n\nWrite minimal, idiomatic PyHealth. The library is opinionated; lean into its abstractions instead of reimplementing them in raw PyTorch. If you find yourself writing a custom training loop, ask whether `Trainer` would do the job — it almost always will, and it handles checkpointing, logging, and best-model selection for free.\n\nWhen the user has private MIMIC access, point them at the local CSV root; for demos and learning, the synthetic MIMIC-III bucket (`https:\u002F\u002Fstorage.googleapis.com\u002Fpyhealth\u002FSynthetic_MIMIC-III\u002F`) is fine and works without credentialing.\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm data access permissions, de-identification status and the governing regulations or protocols.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Work on a de-identified sample or synthetic data first.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Check outputs against clinical guidelines and reporting standards; have a qualified human review clinical content.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| Data appears to contain identifiable patient information | Stop and ask the user before processing further. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Outputs are decision support for qualified professionals, not medical advice; never present them as diagnoses or orders.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `transformers`: Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audi…\n",{"name":5,"license":15,"metadata":43,"description":7},{"tags":44,"version":45,"category":46,"maintainer":47},"clinical machine learning, EHR, MIMIC, healthcare AI, deep learning","1.1","clinical-and-health","Kalaris Labs","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fkal-pyhealth","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill pyhealth",{"tool":63,"command":64},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill pyhealth",{"tool":66,"command":67},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill pyhealth","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-pyhealth\u002FSKILL.md",true,[71,77,83,87,91,95,99],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"assets\u002Fstarter_pipeline.py","SCRIPT","脚本",2338,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-pyhealth\u002Fassets\u002Fstarter_pipeline.py",{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fdatasets.md","REFERENCE","参考文档",4892,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-pyhealth\u002Freferences\u002Fdatasets.md",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fexamples.md",8137,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-pyhealth\u002Freferences\u002Fexamples.md",{"path":88,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Finstallation.md",3972,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-pyhealth\u002Freferences\u002Finstallation.md",{"path":92,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fmedcode.md",3394,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-pyhealth\u002Freferences\u002Fmedcode.md",{"path":96,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Fmodels.md",4551,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-pyhealth\u002Freferences\u002Fmodels.md",{"path":100,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Ftasks.md",5267,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-pyhealth\u002Freferences\u002Ftasks.md",[104,135,160,187,212,235],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":115,"publishedAt":38},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[110],{"categoryNo":111,"categoryName":112,"taxonomyType":113,"taxonomyTypeDesc":114},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[116,117,118,119,120,121,33,122,123,124,125,126,127,128,129,130,131,132,133,134],"youtube full","youtube","full","transcript","search","monitoring","Video","Audio","list","files","do","get","age","trigger","URL","for","browsing","request","youtube transcripts",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":38},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[142,143,144,145,120,146,147,148,149,150,151,152,153,154,155,156,157,158,159,131],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","write","strategy","use","platform","grow","posting","competitive",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":169,"publishedAt":38},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[166],{"categoryNo":167,"categoryName":168,"taxonomyType":113,"taxonomyTypeDesc":114},"01JBSEEDCAT000000000000023","Skill与智能体开发",[170,153,171,172,173,174,175,176,155,177,178,48,179,180,181,182,183,184,185,186],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":193,"publishedAt":38},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[194,195,196,197,198,199,200,201,202,155,203,126,204,205,206,207,208,209,210,211],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":216,"categories":217,"keywords":219,"publishedAt":38},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[218],{"categoryNo":167,"categoryName":168,"taxonomyType":113,"taxonomyTypeDesc":114},[220,221,222,223,224,172,199,34,225,226,227,228,153,229,125,230,231,232,233,234],"workflow","workflow builder","builder","design","workflows","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":236,"name":237,"nameZh":6,"description":238,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":239,"categories":240,"keywords":241,"publishedAt":38},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[242,243,244,245,246,247,248,249,250,227,251,252,253,254,255,256,127,257,258,211],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","conversation","back","project","sprint","cadence"]