InternScience/Agents-A1 - Page 2

molclaw-prolif-md

ProLIF MD trajectory analysis skill for protein-ligand interaction fingerprints with frame slicing and residue controls.

molclaw-prolif-pdb

ProLIF static complex analysis skill for a single protein-ligand structure.

molclaw-prolif-protein-protein

ProLIF protein-protein trajectory analysis skill for interface interaction fingerprints and stability profiling.

molclaw-prolif-tool

Unified ProLIF analysis skill covering MD trajectories, docking poses, single complex structures, and protein-protein interfaces.

molclaw-protein-ligand-mmpbsa

Execution-ready protein-ligand MM/GB(PB)SA workflow with explicit MCP handoffs and optional analysis.

molclaw-protein-openmm

Run OpenMM protein MD and extract evenly spaced trajectory frames for downstream structural analysis.

molclaw-protein-protein-mmpbsa

Execution-ready protein-protein MM/GB(PB)SA workflow with MCP-exposed tool names, strict file validation, and failure guards.

molclaw-protein-sequence-retrieve

Search the target protein sequence information from the input gene name or uniprot id.

molclaw-protein-structure-retrieve

Retrieve and download protein structure file (pdb format) using gene name, Uniprot ID or PDB ID.

molclaw-proteinmpnn-tool

Design or score protein sequences from PDB structures using a ProteinMPNN workflow wrapper.

molclaw-pulchura-rebuild

Rebuilds incomplete protein PDB structures with PULCHRA for downstream docking and simulation preparation.

molclaw-quickvina-docking

Perform molecular docking using QuickVina2-GPU between target protein structure and small molecules.

molclaw-residue-mapper

Map residue numbering between UniProt canonical, PDB author, and tool-internal sequential numbering schemes. Essential for correctly interpreting ProLIF/PLIP results from predicted structures (ESMFold, Boltz-2, Chai-1) and RCSB PDB files with non-trivial…

molclaw-rgroup-optimization

Goal-directed R-group optimization using reinforcement learning. Generates scaffold-decorated molecules optimized toward QED, property constraints, and optional similarity targets, with R-group-level controls.

molclaw-rgroup-sampling

Generate new molecules by decorating a scaffold with R-groups at specified attachment points, using LibInvent for scaffold-constrained molecular generation.

molclaw-run-bioemu

Run BioEmu sequence sampling and extract ensemble structures for downstream conformation analysis.

molclaw-scp-server

All tools utilized within molclaw skills connect via the MCP protocol. This skill serves as a unified guide for using the MCP Server. This skill must be loaded to create the MCP server before invoking any tools.

molclaw-sequence-valid-check

Check if the input protein sequence is valid.

molclaw-similarity-optimization

Goal-directed molecular optimization using reinforcement learning (staged_learning). Generates molecules similar to a target while optimizing multiple physicochemical properties simultaneously via weighted scoring components.

molclaw-smiles-fg-editor

Edit molecular structures in SMILES notation by adding, deleting, or replacing functional groups. Use this skill whenever the user asks to modify a molecule's SMILES by manipulating functional groups (e.g., "delete hydroxyl", "add nitrile", "replace amine…

molclaw-smiles-valid-check

Check if the input molecule SMILES string is valid.