Drive a kitty-graphics terminal app headlessly in a pty and produce a recorded video, timeline and checks summary as the deliverable.
A design-first workflow that sketches types, signatures and module boundaries, compares structurally distinct candidates, then implements against the chosen sketch.
Runs one holistic codex review against three focused passes (security, Ecto, LiveView) on the same branch diff, then classifies findings to prove whether the extra passes catch real misses.
Generates, annotates, reviews, repairs and validates synthesizable Verilog-2001 RTL behind a strict multi-gate quality pipeline.
Delegate prototyping, debugging, code review and live web/X research to xAI's Grok CLI from Claude Code, with structured JSON results and multi-turn sessions.
A bridge skill that lets Claude Code delegate prototyping, debugging, code review, and cross-model second opinions to Codex CLI.
A bridge skill that delegates prototyping, debugging, and code review to the Claude Code CLI headlessly with session continuity.
A decision guide for delegating code lookup, small edits, and diff reviews to compressed-output subagents so your Claude Code context lasts far longer.
A production-grade best-practices skill for camera/LiDAR/depth calibration and building multi-sensor robot perception pipelines.
A battle-tested playbook for containerizing ROS2 workspaces and running robot software stacks with Docker Compose.
Configures a robot's onboard computer to launch its full ROS2 stack on boot using systemd services, layered launch files, udev rules and health checks.
Applies abstract interpretation with interval, sign, congruence, octagon, and polyhedra domains to infer variable ranges and loop invariants without running the code.
Design, code and verify hash-seeded long-form generative artworks before minting on platforms like Art Blocks, Highlight or 256ART.
Hands-on skill for installing, running and benchmarking Mamba-1/Mamba-2 linear-complexity SSMs.
A skill that walks Claude through configuring and launching large-scale LLM pretraining with torchtitan — 4D parallelism (FSDP2/TP/PP/CP), Float8, and distributed checkpointing from 8 to 512+ GPUs.
A skill that walks you through loading, fine-tuning (LoRA/QLoRA), pretraining and deploying 20+ LLM architectures with Lightning AI's LitGPT.
An author-facing reference for how Claude Code plugins, skills, commands, agents, and hooks actually behave, with verified contracts and re-verification commands.
A four-layer project-memory playbook: search GitHub Discussions, the decision journal, and ADRs via verified GraphQL/ripgrep commands before re-investigating anything.
Scaffolds new process definitions for the babysitter event-sourced orchestration framework following official SDK patterns.
A reference skill that evaluates coupling across integration strength, distance, and volatility to guide split-or-merge and architecture decisions.