Ports CPU-bound scientific Python to NVIDIA GPUs and proves the result is both correct and actually faster.
A safety-first guide and CLI toolkit for reading, writing, converting and de-identification-preflighting local DICOM data with pydicom 3.0.2.
Anthropic's official skill for researching, building, testing, and evaluating high-quality MCP servers in TypeScript or Python.
Analyzes every open issue and PR in parallel and writes permalink-backed triage reports to /tmp — without ever mutating anything on GitHub.
Scans, LSP-verifies and deletes unused TypeScript code, delegating per-file batches to parallel agents that commit atomically.
Runs five specialized sub-agents in parallel — goal verification, hands-on QA, code quality, security, and context mining — and only passes the review when all five pass.
Enforces strict typing, modern toolchains, and TDD discipline whenever Claude writes Python, Rust, TypeScript, or Go.
Strips AI-generated code smells from your branch diff, but only after regression tests lock the current behavior.
A hypothesis-driven debugging loop that demands real runtime evidence, per-runtime references, and a clean-up journal before declaring done.
Splits a task into the smallest mergeable PRs and drives each one end to end: isolated worktree, evidence-backed implementation, PR creation, CI/Cubic verification loop, merge and cleanup.
Splits a task into atomic PRs, implements each in an isolated git worktree, loops until CI and the review bot pass, then auto-merges and cleans up.
Design and review PyLabRobot lab-automation protocols offline, with a hard safety gate before any physical run.
Teaches Claude to build, simulate, noise-model, and deploy quantum circuits with Google's Cirq framework.
Helps you write correct ESM3, ESMC, and Forge/Biohub code for protein generation, folding, and embeddings.
An expert skill that guides Claude to build, register, debug, and operate bioinformatics workflows on the Latch platform.
An expert skill for designing, reviewing, migrating and safely planning MATLAB/Octave numerical workflows.
Guides Claude to build, simulate, transpile, and run quantum circuits with modern Qiskit 2.x and IBM Quantum Runtime.
Guides the full Stable Baselines3 workflow — algorithm choice, custom envs, callbacks, training and evaluation.
Gives Claude accurate, version-current PyTorch Geometric patterns for node/link/graph tasks, heterogeneous graphs, and large-scale sampling.
Writes and debugs TorchDrug 0.2.1 code for molecular property prediction, generation, retrosynthesis, protein and knowledge-graph learning.