Safely inspect and operate RunPod resources with runpodctl, live product data, and explicit approval before paid or destructive actions.
69%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./backend/cli/skills/cloud-compute/runpod/SKILL.mdUse this skill for RunPod identity, Pod, and related compute workflows. RunPod product surfaces and CLI commands evolve; distinguish Pods from Serverless and verify the current command reference for the requested product.
provider_compute with account, list_resources, resource_status, or list_availability for live account, Pod, Pod-detail, and GPU availability reads. OpenScience owns the exact reviewed runpodctl argv.runpodctl user.runpodctl executable. A normal user-owned Homebrew or manual install remains credential-only and cannot be used by provider_compute until a managed/native adapter exists.last_used only after the command succeeds.runpodctl --help
runpodctl userUse the installed runpodctl help and current official docs to select the current read-only list/status command, then again before constructing any mutation. Do not reuse remembered Pod create, Serverless, registry, or storage flags.
Never hardcode GPU types, prices, regions, availability, or startup times. Never silently substitute a different cloud type or offer after approval.
For an SSH-capable Pod, add the provider-reported connection in Customize > Compute > SSH. Pin the host key and use a literal identity path with restrictive permissions. OpenScience does not execute ProxyCommand or Match exec from user SSH config.
runpodctl --help and the relevant subcommand --helpsynthetic-sciences/openscience
40d8e07
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.