Modular skills for engineering codebases, ML infrastructure, and strict model reproduction workflows.
Skill Claude CodeCodex
Use this skill for general software engineering work where maintainable structure is the priority: starting or refactoring backend, frontend, library, CLI, or app codebases; splitting large files into focused modules; defining clear interfaces; or setting up a project that will evolve over multiple turns. Prefer it…
Skill Claude CodeCodex
Coordinate work across multiple servers, machines, repos, or disconnected workspaces when the whole project cannot live in one folder. Use this skill whenever the user mentions different servers, remote machines, split codebases, cross-workspace integration, handoff between assistant sessions, relay workflows, SSH/Git…
Skill Claude CodeCodex
Engineering patterns for ML/DL research and LLM training infrastructure. Use this skill when: (1) Building training pipelines (SFT, RLHF, DPO, etc.), (2) Creating ML experiment infrastructure, (3) Designing distributed training systems, (4) Research projects requiring reproducibility, (5) Any deep learning project…
Skill Claude CodeCodex
Strict skill for reproducing ML models. Use for: (1) Reproducing paper algorithms, (2) Porting open-source models, (3) Integrating multiple algorithms into one agent, (4) Adapting a model to downstream tasks. Core rule: engineering code may change (adapters, I/O, logging, config), but the algorithm must stay…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: