[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QGMPGHZP7B1NEWEMQ8ZPR5":3,"skill-same:01M6QGMPGHZP7B1NEWEMQ8ZPR5":114},{"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":51,"commitSha":52,"skillDirectory":53,"forksCount":14,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M6QGMPGHZP7B1NEWEMQ8ZPR5","deepchem",null,"Builds molecular property prediction and MoleculeNet workflows with DeepChem, including SMILES featurization, scaffold or grouped holdouts, masked labels, graph models and explicit pretrained encoder transfer. Used for ADMET, toxicity, solubility and chemistry ML when DeepChem data\u002Fmodel contracts and scientific validation are needed.","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\u002Fkd-deepchem\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"model","labels","scientific","solubility","molecular","contracts","only","edit","write","read","workflows","stack","Bash","rdkit","Transformers","data","network","graph","benchmark","2026-11-10 10:12:30",false,"---\nname: deepchem\ndescription: Builds molecular property prediction and MoleculeNet workflows with DeepChem, including SMILES featurization, scaffold or grouped holdouts, masked labels, graph models and explicit pretrained encoder transfer. Used for ADMET, toxicity, solubility and chemistry ML when DeepChem data\u002Fmodel contracts and scientific validation are needed.\nlicense: MIT license\nallowed-tools: Read Write Edit Bash\ncompatibility: Requires Python 3.11 for the tested DeepChem 2.8.0 stack. Molecular workflows need RDKit. Torch, Transformers, torch-geometric or DGL\u002FDGL-LifeSci depend on the chosen model. Network is needed only for package, benchmark or model downloads.\nmetadata:\n  version: \"2.0\"\n  skill-author: K-Dense Inc.\n  last-reviewed: \"2026-09-30\"\ncategory: \"scientific-computing\"\n---\n\n# DeepChem\n\n## When to use\n\nUse for molecular property prediction, SMILES\u002Fgraph featurization, MoleculeNet\nbenchmarks and explicitly configured encoder transfer. The workflow also covers\nDeepChem materials and sequence adapters when their data\u002Fmodel contracts are met.\n\nTargets **DeepChem 2.8.0**, still the stable PyPI release at review. Nightly 2.8.1\nbuilds have additional APIs and different constraints; do not mix `latest` docs\nwith a stable installation. The tested CPU stack and optional-backend limitations\nare in [references\u002Freview.md](references\u002Freview.md).\n\n## Workflow\n\n1. Define compound identity, assay conditions, target units and missing labels.\n   Parse SMILES and retain a record of rejected rows. Audit duplicate structures\n   and repeated measurements before splitting.\n2. Match the representation to the model using the table below. Fit a numeric\n   baseline first; dataset size alone does not select the best architecture.\n3. Choose a scaffold, temporal or grouped holdout for the deployment question.\n   Preserve exact split IDs, inspect scaffold overlap and per-task class support,\n   and reject empty splits. Scaffold splitting does not eliminate all leakage.\n4. Fit preprocessing on training data only. Preserve `dataset.w` masks. Normalize\n   continuous targets only, and invert those transforms for metrics\u002Fpredictions.\n5. Select model settings\u002Fepochs on validation data and evaluate the final holdout\n   once. Report per-task support, uncertainty across planned repeats and baseline\n   comparisons. AUC requires both observed classes.\n6. Predict using the training representation and transforms. Preserve identifiers,\n   original target units and applicability limits. Successful fitting is not\n   evidence of prospective scientific performance.\n\n## Essential model contracts\n\n| Model path | Input |\n|---|---|\n| Fingerprint baseline or `MultitaskRegressor` | Explicit `CircularFingerprint(size=2048)` |\n| Torch GCN\u002FGAT | `MolGraphConvFeaturizer()` |\n| Torch AttentiveFP\u002FMPNN | `MolGraphConvFeaturizer(use_edges=True)` |\n| DMPNN | `DMPNNFeaturizer()`; binary tasks need `n_classes=2` |\n| GROVER | `GroverFeaturizer` plus matching encoder checkpoint\u002Fconfiguration |\n| HF wrapper | SMILES strings, actual network object and tokenizer object |\n\nMoleculeNet's `'ECFP'` alias is **1024** bits, while the fingerprint class defaults\nto **2048**. `'GraphConv'` is legacy `ConvMolFeaturizer`, incompatible with Torch\nGCN. `'Raw'` defaults to RDKit Mol objects; use `DummyFeaturizer()` for raw strings.\nImport Torch MPNN\u002FGROVER from `deepchem.models.torch_models`.\n\nStable `HuggingFaceModel` returns logits and its training loss ignores sample\nweights. The bundled HF transfer script accepts one fully observed, unweighted\nbinary\u002Fregression task and rejects sparse multitask datasets. A model ID or\n`model_dir` is not itself a loaded pretrained model.\n\n## Installation\n\nUse an isolated Python 3.11 environment, outside any repository environment whose\nPython requirement conflicts. This tested core stack supports the fingerprint,\nDMPNN, local HF and GROVER smoke paths:\n\n```bash\nuv venv --python 3.11 .venv-deepchem\nuv pip install --python .venv-deepchem\u002Fbin\u002Fpython \\\n  'deepchem==2.8.0' 'torch==2.14.1' 'transformers==5.18.0' \\\n  'torch-geometric==2.8.0.post1'\n```\n\nThe CPU smoke checks used these versions, not GPU builds. For GPU training install\nthe correct framework build according to its official platform instructions.\nGCN\u002FGAT\u002FAttentiveFP\u002FTorch MPNN additionally require mutually compatible **DGL and\nDGL-LifeSci**; those backends were not available in this audit. Installing Torch\nalone, or importing DeepChem successfully, does not establish those model paths.\n\nThe stable distribution exposes `torch`, `tensorflow`, `jax`, and `dqc` extras,\nwith historical optional dependency requirements; they are not an assurance that\nevery modern platform\u002Fbackend combination resolves or executes. No `[all]` extra\nexists. The TensorFlow, JAX and quantum-chemistry routes were source-reviewed only.\nCheck [release installation docs](https:\u002F\u002Fdeepchem.readthedocs.io\u002Fen\u002F2.8.0\u002Fget_started\u002Finstallation.html)\nand [requirements](https:\u002F\u002Fdeepchem.readthedocs.io\u002Fen\u002F2.8.0\u002Fget_started\u002Frequirements.html).\nDeepChem attempts optional imports at package import time and can log skipped\nmodules; it does not promise all classes are available after that import.\n\n## Bundled scripts\n\nThe primary executable end-to-end example is `predict_solubility.py` with a custom\nCSV and query SMILES: validate complete continuous targets, create 2048-bit\nfingerprints, scaffold-split, fit training-target normalization, train a Torch\n`MultitaskRegressor`, then print original-unit metrics and predictions. Its Python\ntraining function returns `(model, test, transformers)`. It does not invoke the\nseparate random-forest reference baseline or `GridHyperparamOpt` template.\n\nThe command prints results; it does not export split IDs, rejected-row tables or a\nprediction file. Bad custom rows stop loading rather than becoming a saved rejection\naudit. Persist data provenance, split IDs and outputs explicitly when adapting it\nfor research. Qualitative assay\u002Fapplicability assessment remains the agent's work.\n\nRun from this skill directory with the selected environment's Python. These\nexternal-data commands are illustrative; offline synthetic fits are documented\nin the review. All scripts use CPU, a scaffold split, fixed epochs, and report metrics;\nthey do not perform automatic early stopping or a hyperparameter search.\n\n```bash\n# ESOL log10(mol\u002FL), or custom continuous targets in their declared input units.\npython scripts\u002Fpredict_solubility.py --epochs 50\npython scripts\u002Fpredict_solubility.py --data measured.csv \\\n  --smiles-col smiles --target-col logS --predict CCO c1ccccc1\n\n# Model-specific graph features, including bonds where required.\npython scripts\u002Fgraph_neural_network.py --model dmpnn --dataset bbbp --epochs 20\n\n# Explicit HF network + tokenizer; single complete task only.\npython scripts\u002Ftransfer_learning.py --model chemberta --dataset bbbp --epochs 10\n```\n\nThe CSV guard rejects duplicate headers, non-finite labels, invalid SMILES and\nfeaturization row loss. Empty labels remain masked for compatible graph losses;\ncustom solubility and HF training require complete targets. The shared scorer\nreports original-unit regression metrics and excludes undefined AUC tasks from\nmacro means while reporting the contributing task count.\n\nMoLFormer uses the current `ibm-research\u002FMoLFormer-XL-both-10pct` repository and\nneeds reviewed repository code plus an explicit revision. GROVER needs a local\nDeepChem component checkpoint and matching JSON architecture; simply creating a\nfresh model is not transfer learning. See\n[references\u002Ftypical_workflows.md](references\u002Ftypical_workflows.md) for both recipes.\n\n## References and validation\n\n- [Core scientific workflow and executable numeric baseline](references\u002Fcore_capabilities.md)\n- [Versioned API\u002Frepresentation\u002Fsplit\u002Fmetric contracts](references\u002Fapi_reference.md)\n- [Script recipes](references\u002Ftypical_workflows.md)\n- [Search, generation, materials, sequence and custom-model workflows](references\u002Fworkflows.md)\n- [Executed review evidence and limitations](references\u002Freview.md)\n\n## Citing Scientific Agent Skills\n\nThis skill is part of Scientific Agent Skills by K-Dense. If it materially contributed to a\nmanuscript, report, presentation, or code release, add the paper to the references or\nsoftware section and tell the user you did so:\n\n> Kassis, T., Agarwal, V., He, Y., Patel, D., & Brueckner, A. M. (2026). Scientific Agent\n> Skills: A Library of Procedural Knowledge for Research Agents. arXiv:2609.00065.\n> https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2609.00065\n\nAlways cite the current version. The DOI and https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.00065 resolve to the\nlatest arXiv version, so never append a version suffix such as `v1`. When network access is\navailable, fetch https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.00065 (or\nhttp:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?id_list=2609.00065) before writing the reference and take\nthe author list, year, and version from that record. If the record lists a journal reference\nor publisher DOI, cite the published version instead.\n","# DeepChem\n\n## When to use\n\nUse for molecular property prediction, SMILES\u002Fgraph featurization, MoleculeNet\nbenchmarks and explicitly configured encoder transfer. The workflow also covers\nDeepChem materials and sequence adapters when their data\u002Fmodel contracts are met.\n\nTargets **DeepChem 2.8.0**, still the stable PyPI release at review. Nightly 2.8.1\nbuilds have additional APIs and different constraints; do not mix `latest` docs\nwith a stable installation. The tested CPU stack and optional-backend limitations\nare in [references\u002Freview.md](references\u002Freview.md).\n\n## Workflow\n\n1. Define compound identity, assay conditions, target units and missing labels.\n   Parse SMILES and retain a record of rejected rows. Audit duplicate structures\n   and repeated measurements before splitting.\n2. Match the representation to the model using the table below. Fit a numeric\n   baseline first; dataset size alone does not select the best architecture.\n3. Choose a scaffold, temporal or grouped holdout for the deployment question.\n   Preserve exact split IDs, inspect scaffold overlap and per-task class support,\n   and reject empty splits. Scaffold splitting does not eliminate all leakage.\n4. Fit preprocessing on training data only. Preserve `dataset.w` masks. Normalize\n   continuous targets only, and invert those transforms for metrics\u002Fpredictions.\n5. Select model settings\u002Fepochs on validation data and evaluate the final holdout\n   once. Report per-task support, uncertainty across planned repeats and baseline\n   comparisons. AUC requires both observed classes.\n6. Predict using the training representation and transforms. Preserve identifiers,\n   original target units and applicability limits. Successful fitting is not\n   evidence of prospective scientific performance.\n\n## Essential model contracts\n\n| Model path | Input |\n|---|---|\n| Fingerprint baseline or `MultitaskRegressor` | Explicit `CircularFingerprint(size=2048)` |\n| Torch GCN\u002FGAT | `MolGraphConvFeaturizer()` |\n| Torch AttentiveFP\u002FMPNN | `MolGraphConvFeaturizer(use_edges=True)` |\n| DMPNN | `DMPNNFeaturizer()`; binary tasks need `n_classes=2` |\n| GROVER | `GroverFeaturizer` plus matching encoder checkpoint\u002Fconfiguration |\n| HF wrapper | SMILES strings, actual network object and tokenizer object |\n\nMoleculeNet's `'ECFP'` alias is **1024** bits, while the fingerprint class defaults\nto **2048**. `'GraphConv'` is legacy `ConvMolFeaturizer`, incompatible with Torch\nGCN. `'Raw'` defaults to RDKit Mol objects; use `DummyFeaturizer()` for raw strings.\nImport Torch MPNN\u002FGROVER from `deepchem.models.torch_models`.\n\nStable `HuggingFaceModel` returns logits and its training loss ignores sample\nweights. The bundled HF transfer script accepts one fully observed, unweighted\nbinary\u002Fregression task and rejects sparse multitask datasets. A model ID or\n`model_dir` is not itself a loaded pretrained model.\n\n## Installation\n\nUse an isolated Python 3.11 environment, outside any repository environment whose\nPython requirement conflicts. This tested core stack supports the fingerprint,\nDMPNN, local HF and GROVER smoke paths:\n\n```bash\nuv venv --python 3.11 .venv-deepchem\nuv pip install --python .venv-deepchem\u002Fbin\u002Fpython \\\n  'deepchem==2.8.0' 'torch==2.14.1' 'transformers==5.18.0' \\\n  'torch-geometric==2.8.0.post1'\n```\n\nThe CPU smoke checks used these versions, not GPU builds. For GPU training install\nthe correct framework build according to its official platform instructions.\nGCN\u002FGAT\u002FAttentiveFP\u002FTorch MPNN additionally require mutually compatible **DGL and\nDGL-LifeSci**; those backends were not available in this audit. Installing Torch\nalone, or importing DeepChem successfully, does not establish those model paths.\n\nThe stable distribution exposes `torch`, `tensorflow`, `jax`, and `dqc` extras,\nwith historical optional dependency requirements; they are not an assurance that\nevery modern platform\u002Fbackend combination resolves or executes. No `[all]` extra\nexists. The TensorFlow, JAX and quantum-chemistry routes were source-reviewed only.\nCheck [release installation docs](https:\u002F\u002Fdeepchem.readthedocs.io\u002Fen\u002F2.8.0\u002Fget_started\u002Finstallation.html)\nand [requirements](https:\u002F\u002Fdeepchem.readthedocs.io\u002Fen\u002F2.8.0\u002Fget_started\u002Frequirements.html).\nDeepChem attempts optional imports at package import time and can log skipped\nmodules; it does not promise all classes are available after that import.\n\n## Bundled scripts\n\nThe primary executable end-to-end example is `predict_solubility.py` with a custom\nCSV and query SMILES: validate complete continuous targets, create 2048-bit\nfingerprints, scaffold-split, fit training-target normalization, train a Torch\n`MultitaskRegressor`, then print original-unit metrics and predictions. Its Python\ntraining function returns `(model, test, transformers)`. It does not invoke the\nseparate random-forest reference baseline or `GridHyperparamOpt` template.\n\nThe command prints results; it does not export split IDs, rejected-row tables or a\nprediction file. Bad custom rows stop loading rather than becoming a saved rejection\naudit. Persist data provenance, split IDs and outputs explicitly when adapting it\nfor research. Qualitative assay\u002Fapplicability assessment remains the agent's work.\n\nRun from this skill directory with the selected environment's Python. These\nexternal-data commands are illustrative; offline synthetic fits are documented\nin the review. All scripts use CPU, a scaffold split, fixed epochs, and report metrics;\nthey do not perform automatic early stopping or a hyperparameter search.\n\n```bash\n# ESOL log10(mol\u002FL), or custom continuous targets in their declared input units.\npython scripts\u002Fpredict_solubility.py --epochs 50\npython scripts\u002Fpredict_solubility.py --data measured.csv \\\n  --smiles-col smiles --target-col logS --predict CCO c1ccccc1\n\n# Model-specific graph features, including bonds where required.\npython scripts\u002Fgraph_neural_network.py --model dmpnn --dataset bbbp --epochs 20\n\n# Explicit HF network + tokenizer; single complete task only.\npython scripts\u002Ftransfer_learning.py --model chemberta --dataset bbbp --epochs 10\n```\n\nThe CSV guard rejects duplicate headers, non-finite labels, invalid SMILES and\nfeaturization row loss. Empty labels remain masked for compatible graph losses;\ncustom solubility and HF training require complete targets. The shared scorer\nreports original-unit regression metrics and excludes undefined AUC tasks from\nmacro means while reporting the contributing task count.\n\nMoLFormer uses the current `ibm-research\u002FMoLFormer-XL-both-10pct` repository and\nneeds reviewed repository code plus an explicit revision. GROVER needs a local\nDeepChem component checkpoint and matching JSON architecture; simply creating a\nfresh model is not transfer learning. See\n[references\u002Ftypical_workflows.md](references\u002Ftypical_workflows.md) for both recipes.\n\n## References and validation\n\n- [Core scientific workflow and executable numeric baseline](references\u002Fcore_capabilities.md)\n- [Versioned API\u002Frepresentation\u002Fsplit\u002Fmetric contracts](references\u002Fapi_reference.md)\n- [Script recipes](references\u002Ftypical_workflows.md)\n- [Search, generation, materials, sequence and custom-model workflows](references\u002Fworkflows.md)\n- [Executed review evidence and limitations](references\u002Freview.md)\n\n## Citing Scientific Agent Skills\n\nThis skill is part of Scientific Agent Skills by K-Dense. If it materially contributed to a\nmanuscript, report, presentation, or code release, add the paper to the references or\nsoftware section and tell the user you did so:\n\n> Kassis, T., Agarwal, V., He, Y., Patel, D., & Brueckner, A. M. (2026). Scientific Agent\n> Skills: A Library of Procedural Knowledge for Research Agents. arXiv:2609.00065.\n> https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2609.00065\n\nAlways cite the current version. The DOI and https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.00065 resolve to the\nlatest arXiv version, so never append a version suffix such as `v1`. When network access is\navailable, fetch https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.00065 (or\nhttp:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?id_list=2609.00065) before writing the reference and take\nthe author list, year, and version from that record. If the record lists a journal reference\nor publisher DOI, cite the published version instead.\n",{"name":5,"license":43,"category":44,"metadata":45,"description":7,"allowed-tools":49,"compatibility":50},"MIT license","scientific-computing",{"version":46,"skill-author":47,"last-reviewed":48},"2.0","K-Dense Inc.","2026-09-30","Read Write Edit Bash","Requires Python 3.11 for the tested DeepChem 2.8.0 stack. Molecular workflows need RDKit. Torch, Transformers, torch-geometric or DGL\u002FDGL-LifeSci depend on the chosen model. Network is needed only for package, benchmark or model downloads.","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fkd-deepchem","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":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill deepchem",{"tool":66,"command":67},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill deepchem",{"tool":69,"command":70},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill deepchem","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-deepchem\u002FSKILL.md",true,[74,80,84,88,92,96,102,106,110],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fapi_reference.md","REFERENCE","参考文档",8458,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-deepchem\u002Freferences\u002Fapi_reference.md",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fcore_capabilities.md",3692,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-deepchem\u002Freferences\u002Fcore_capabilities.md",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Freview.md",5325,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-deepchem\u002Freferences\u002Freview.md",{"path":89,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Ftypical_workflows.md",3171,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-deepchem\u002Freferences\u002Ftypical_workflows.md",{"path":93,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fworkflows.md",7206,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-deepchem\u002Freferences\u002Fworkflows.md",{"path":97,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":100,"sourceHtmlUrl":101},"scripts\u002F_common.py","SCRIPT","脚本",6474,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-deepchem\u002Fscripts\u002F_common.py",{"path":103,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Fgraph_neural_network.py",9569,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-deepchem\u002Fscripts\u002Fgraph_neural_network.py",{"path":107,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Fpredict_solubility.py",6945,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-deepchem\u002Fscripts\u002Fpredict_solubility.py",{"path":111,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Ftransfer_learning.py",11161,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-deepchem\u002Fscripts\u002Ftransfer_learning.py",[115,146,170,197,222,245],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":126,"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",[121],{"categoryNo":122,"categoryName":123,"taxonomyType":124,"taxonomyTypeDesc":125},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[127,128,129,130,131,132,34,133,134,135,136,137,138,139,140,141,142,143,144,145],"youtube full","youtube","full","transcript","search","monitoring","Video","Audio","list","files","do","get","age","trigger","URL","for","browsing","request","youtube transcripts",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"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",[],[153,154,155,156,131,157,158,159,160,161,162,163,27,164,165,166,167,168,169,142],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","strategy","use","platform","grow","posting","competitive",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":179,"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",[176],{"categoryNo":177,"categoryName":178,"taxonomyType":124,"taxonomyTypeDesc":125},"01JBSEEDCAT000000000000023","Skill与智能体开发",[180,27,181,182,183,184,185,186,165,187,188,51,189,190,191,192,193,194,195,196],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":203,"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",[],[204,205,206,207,208,209,210,211,212,165,213,137,214,215,216,217,218,219,220,221],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":223,"name":224,"nameZh":6,"description":225,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":226,"categories":227,"keywords":229,"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",[228],{"categoryNo":177,"categoryName":178,"taxonomyType":124,"taxonomyTypeDesc":125},[230,231,232,233,29,182,209,234,235,236,237,238,27,239,136,240,241,242,243,244],"workflow","workflow builder","builder","design","code","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":246,"name":247,"nameZh":6,"description":248,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":249,"categories":250,"keywords":251,"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",[],[252,253,254,255,256,257,258,259,260,237,261,262,263,264,265,266,138,267,268,221],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","conversation","back","project","sprint","cadence"]