微信扫一扫把 Skill 的源码、资源快照、README、包体和安装信号放进一个可搜索、可筛选的公开目录。
Adversarially challenge research assumptions, mechanisms, and arguments in writing. Use when stress-testing a claim or design before committing to it. Not for an interactive oral drill or a full refer…
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Compute RDKit physicochemical descriptors and rule-based drug-likeness heuristics (Ro5, Veber, QED) from SMILES.
>
Query PubChem via PUG-REST to retrieve CIDs, computed properties, synonyms, and 2D/3D SDF structures.
>
Compute Morgan/ECFP fingerprints, Tanimoto similarity, and optional Butina clusters/heatmaps for small-molecule comparison.
Run a protein-ligand MD simulation in OpenMM with energy minimization, restrained equilibration, and production NPT, producing trajectory and checkpoint files for downstream analysis.
Extract cognitive patterns and thinking fingerprints from any text. Use this skill when the user wants to analyze how someone thinks, understand cognitive style, profile writing or speech patterns, co…
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs…
>
Query ChEMBL web services for targets, molecules, and curated bioactivity measurements (IC50, Ki, EC50, etc.).
Post-docking analysis of virtual screening results including score distributions, enrichment metrics (ROC AUC, enrichment factors), and ligand efficiency calculations.
Prepare small-molecule ligands for docking and analysis via optional state enumeration, 3D conformer generation, MMFF/UFF minimization, and export to SDF + AutoDock PDBQT.
>
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming
DiffDock and DiffDock-L molecular docking. Use for protein-small-molecule pose prediction from PDB or sequence plus SMILES/SDF/MOL2, batch docking, virtual screening, and pose-confidence interpretatio…
Build and operate reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets, native workflows, dxCompiler, and Nextflow. Use for DNAnexus data transfers, dxapp.json development, …
Fetch biological assays and target proteins a chemical has been tested against via PubChem.
Search, filter, and retrieve macromolecular structures from the RCSB Protein Data Bank (PDB), including metadata, bound ligands, and optional coordinate/validation downloads.
Dock small-molecule ligands into a protein receptor using AutoDock Vina (Python API) and save ranked poses + docking metadata for reproducible virtual screening.
>
Validate docked or generated ligand poses for physical plausibility using PoseBusters, filtering out chemically invalid or clashing poses before downstream refinement.
Architecture, component selection, firmware design, and regulatory considerations for a medical wearable device (smartwatch-class) that records patient vital signs (SpO2, ECG, heart rate, temperature,…