skill-sommelier

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations; the outer loop synthesizes results, identifies patterns, and steers research direction. Produces research presentations and papers. Use when asked to run autonomous research, design and execute ML experiments end-to-end, or generate a research report from a hypothesis.

Disciplined diagnosis loop for hard bugs and performance regressions: build a feedback loop → reproduce → hypothesise → instrument → fix → regression-test → cleanup. Use when the user says "diagnose this", "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression. Triggers on "diagnose", "debug", "broken", "throwing", "failing", "perf regression", "slow", "hangs".

Create a single-line install script with auto-update capability for CLI tools, Python packages, or applications. Generates shell scripts similar to uv or uw-s3 installers that handle installation, configuration, and optional dependencies. Use when users want to "create an install script", "make a single-line installer", "add auto-update", or "build an installer like uv". Triggers on "install script", "single-line installer", "curl installer", "auto-update script", "installer like uv", "install.sh".

Configure Python projects with modern tooling: uv, ruff, ty. Use when creating new Python projects, setting up pyproject.toml, migrating from pip/Poetry/mypy/black, or writing standalone scripts. Triggers on new Python project, setup Python, pyproject.toml, migrate from pip, migrate from Poetry, replace mypy, replace black, uv init, ruff config.

Convert Python scripts into production-ready Docker and Apptainer/Singularity containers with Pixi dependency management, automatic detection, multi-stage builds, and best practices. Supports GPU/CUDA configurations, multi-environment setups (CPU/GPU), HTCondor/SLURM integration, and .sif conversion for HPC. Use when users need to containerize Python applications, create Dockerfiles, generate Apptainer images, package Python code for deployment, need container configuration for Python projects, or want GPU-accelerated applications for HPC environments. Supports Pixi and pip workflows. Handles scripts, web apps, workers, services, and ML/data science workloads on Docker, Apptainer, and HPC systems.