Moves CPU-bound scientific Python to NVIDIA GPUs and proves the port is both correct and genuinely faster.
Writes and debugs TorchDrug 0.2.1 code for molecular property prediction, generation, retrosynthesis, protein encoders, and knowledge graph reasoning.
Version-aware guidance for PufferLib RL work — environment adaptation, vectorization, PuffeRL training, and safe checkpoint review across the 3.0.0 release and 4.0 source line.
A routing-style skill for installing, configuring, and building on Pi, the minimal terminal coding harness.
A skill for building, running and monitoring reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets and workflow importers.
An interactive, resumable eight-phase journey that measures, untangles, and speeds up a working-but-slow codebase while logging every decision in docs/.
A skill for planning, rehearsing, and safely executing PostgreSQL schema migrations on live production tables without locking them up.
Restructures a bloated CLAUDE.md/AGENTS.md into a lean Level 1 plus on-demand Level 2 references with guaranteed zero information loss.
A workflow skill that decomposes repetitive, large-scale code changes into independent units and runs one parallel agent per isolated git worktree.
Measure any OpenAI- or Anthropic-compatible LLM endpoint across six dimensions: availability, request fidelity, speed, concurrency, protocol compliance, and quality regression.
A rigorous maintainer-grade workflow that re-reviews GitHub pull requests against the current base branch, binding every verdict to exact Git OIDs.
A field-tested guide for building iOS/macOS apps with XcodeGen, SwiftUI and SPM, plus Apple code signing, notarization and CI/CD fixes.
A rigorous visual QA protocol that audits already-rendered web, deck, dashboard, and Electron UIs with real-browser evidence and produces an evidence-backed defect report.
A battle-tested guide to writing, testing, registering, and debugging Claude Code PreToolUse / PostToolUse / SessionStart / Stop hooks.
A macOS network-debugging skill that isolates and fixes Tailscale conflicts with Shadowrocket/Clash/Surge/OrbStack — route hijacks, proxy env vars, SSH double tunnels, Docker proxy propagation and stalled DNS.
Installs, authenticates and enables OpenAI Codex (app-server) as a first-class agent backend in NanoClaw, switchable per group.
Spawns five mutually hostile agents for a three-round critique debate, keeps only the insights that survive, then hands them to a dedicated `plan` agent for an executable plan.
Wires a stdio MCP server into the NanoClaw agent-runner so the containerized agent can call local models served by the Atomic Chat desktop app.
An installer skill that wires an Emacs channel into NanoClaw over a local HTTP bridge, giving you a chat buffer and org-mode integration inside Emacs.
Scans a TypeScript project for unused code, confirms each candidate via LSP, then removes it through parallel per-file batches with atomic commits.