Teaches Claude Code to build, deploy and scale Python and AI/ML workloads on Modal's serverless GPU cloud.
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.
Guides Claude to use SymPy for exact symbolic algebra, calculus, equation solving, and code generation.
A skill for building, differentiating and training quantum circuits with PennyLane across IBM, Google, Rigetti and IonQ backends.
Version-aware guidance for PufferLib: wrapping environments, vectorization, PuffeRL training plans, and safe checkpoint review across the 3.0.0 release and the 4.0 source line.
Scans a repository and produces an interactive knowledge graph of its architecture, components and relationships.
A phase-based playbook for shipping pull requests that maintainers of third-party open-source repos actually merge.
Restructures a bloated CLAUDE.md / AGENTS.md into a lean Level 1 plus on-demand Level 2 references, with verified zero information loss.
A quality gate for Claude Code skills: audits your own or others' skills against official best practices and can even open an improvement PR.
An evidence-driven, falsification-first playbook for network, streaming and protocol bugs where the obvious cause is probably wrong.
A Git forensics skill that recovers lost commits, branches and stashes — and proves by content that cleanup won't drop any work.
Sets up, audits, and enforces internationalization in React/Next.js/Vue codebases — from framework config to replacing hard-coded strings and verifying locale key parity.
Measure any OpenAI- or Anthropic-compatible endpoint across six dimensions — availability, request fidelity, speed, concurrency, protocol compliance, and quality regression.
Sets up and runs Promptfoo-based LLM evaluations, from config files to custom Python and LLM-rubric assertions.
Sets up an end-to-end QA process—test strategy, AAA-style test cases, execution tracking, P0–P4 bug triage, and quality-gate reporting—from ready-made templates and scripts.
Diagnoses and repairs broken repository setups, then standardizes onboarding docs and safe Git workflows.
A battle-tested guide to writing, testing, registering and debugging Claude Code PreToolUse/PostToolUse/SessionStart/Stop hooks.