Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
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,…
>
Use when drafting or revising the 中文内容提要 (~300 字, official) or English 梗概/Summary for an 《经济研究》 manuscript. Enforces the five-sentence Chinese pattern, the five-element English Summary, and forbids em…
Analyze, manipulate, compare, annotate, and visualize phylogenetic or other hierarchical trees with ETE 4. Use for Newick/Nexus tree I/O, topology edits and pattern matching, Robinson-Foulds compariso…
>
Use when a workflow plan exists and stages need to be executed sequentially in the current session
>
Run a protein-ligand MD simulation in OpenMM with energy minimization, restrained equilibration, and production NPT, producing trajectory and checkpoint files for downstream analysis.
>
>
Use when writing the data and sample section of an Economic-Research manuscript — naming databases, building variable-definition and descriptive-statistics tables, and leaving an auditable sample-filt…
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language suppor…
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and ski…
Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable. Use whenever someone is planning…
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align …
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
>
>
Use when working directly with the `esm` Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.
Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering,…
Web toolkit powered by Exa, tuned for scientific and technical content. Use this skill when the user needs to search the web or fetch/extract URL content. Covers: web search (semantic lookups, researc…
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; mi…
Read, inspect, and write Flow Cytometry Standard (FCS) 2.0, 3.0, and 3.1 files with FlowIO. Use for low-level FCS metadata and channel inspection, NumPy event extraction, multi-dataset files, table ex…