Dev & Coding
Finish NanoClaw v1 → v2 Migration
Walks Claude through the human-judgment half of a NanoClaw v1→v2 upgrade: owner seeding, legacy memory, container config, and fork triage.
PyLabRobot Lab Automation Assistant
Design and review PyLabRobot 0.2.1 liquid-handling protocols offline, with every physical device command locked behind an explicit operator safety gate.
ESM Protein Language Model Skill
Guides Claude through the `esm` Python SDK — ESM3 generation, ESM C embeddings, ESMFold2 folding, and Forge/Biohub hosted inference.
LatchBio Integration
Guides Claude to build, register, debug, and run bioinformatics workflows on the Latch platform via the Python SDK, CLI, Nextflow, Snakemake, and Latch MCP.
GPU Optimization for Python (NVIDIA)
Moves CPU-bound scientific Python to NVIDIA GPUs and proves the port is both correct and genuinely faster.
TorchDrug Workflow Assistant
Writes and debugs TorchDrug 0.2.1 code for molecular property prediction, generation, retrosynthesis, protein encoders, and knowledge graph reasoning.
PufferLib RL Guide
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.
Pi Agent Helper
A routing-style skill for installing, configuring, and building on Pi, the minimal terminal coding harness.
DNAnexus Integration
A skill for building, running and monitoring reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets and workflow importers.
Chaos Experiment Designer
An interactive wizard that designs a chaos engineering experiment, computes blast radius, and emits a peer-reviewable markdown plan.
PostgreSQL Zero-Downtime Migrations
A skill for planning, rehearsing, and safely executing PostgreSQL schema migrations on live production tables without locking them up.
Competitors Analysis
Clones and audits competitor repositories into evidence-based competitive intelligence with file:line citations.
CLAUDE.md Progressive Disclosurer
Restructures a bloated CLAUDE.md/AGENTS.md into a lean Level 1 plus on-demand Level 2 references with guaranteed zero information loss.
LLM Eval Harness
Measure any OpenAI- or Anthropic-compatible LLM endpoint across six dimensions: availability, request fidelity, speed, concurrency, protocol compliance, and quality regression.
GitHub Maintainer PR Review
A rigorous maintainer-grade workflow that re-reviews GitHub pull requests against the current base branch, binding every verdict to exact Git OIDs.
iOS/macOS App Developer
A field-tested guide for building iOS/macOS apps with XcodeGen, SwiftUI and SPM, plus Apple code signing, notarization and CI/CD fixes.
Frontend Visual QA
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.
Claude Code Hooks Playbook
A battle-tested guide to writing, testing, registering, and debugging Claude Code PreToolUse / PostToolUse / SessionStart / Stop hooks.