3 tagged autodl, measured the same way as everything else here.
Skill Claude CodeCodex
Move one experiment through RUN → VERIFY → DELIVER with the least control work that safely advances the user's outcome. This is the compute/control layer and owns one compute attempt. When the task spans several runs, nodes, independent side-effect lanes, or paper-wide closeout, route scheduling and state projection…
chengxi271-commits/autodl-research-pilot
Skill Codex
Inspect, select, rent, and observe AutoDL compute for a concrete research workload. Use when Codex must decide between local, existing, Pro, or Enterprise Elastic GPUs; validate disk, network, persistence, and runtime fit; or operate an approved AutoDL run through the API and SSH.
Skill Claude CodeCodex
Use AutoDL safely through its official developer APIs and documentation. Trigger for AutoDL balance, Container Instance Pro, elastic deployment, images, GPU stock, NFS, duration packages, WeChat notifications, container metrics, billing, storage, data retention, SSH/JupyterLab/VSCode, CUDA environments…