← Runpod (Official)CONTENT HISTORYWHAT CHANGED · RULE-BASED ANALYSIS
Update to Runpod (Official)
Snapshot Sep 30, 2026 · 23:02 UTC · version 1.1.2
Collection source: not recorded for this historical snapshot.
First saved snapshot
No earlier snapshot is available to establish a change.
Compare saved observations
Download comparison JSONFull technical diff · 0 changed fields
Full snapshot data
{
"name": "runpod-usage",
"description": "How Runpod works and how to work it — pods vs serverless, GPU/VRAM selection, storage, building a container, networking, plus the agentic pod development loop (provision → ssh-exec → set up → poll readiness) and on-pod install hygiene (uv/apt). Use to answer \"how does X work\", \"which GPU\", \"how do I build a container\", or \"how do I stand up a workload on a pod\". Guidance, not a tool — execute with runpodctl, runpod-mcp, or flash.",
"included_files": [
{
"relative_path": "evals/pod-service-loop.eval.md",
"size_in_bytes": 1318
},
{
"relative_path": "evals/verify-with-real-request.eval.md",
"size_in_bytes": 1353
},
{
"relative_path": "reference/building-images.md",
"size_in_bytes": 8794
},
{
"relative_path": "reference/concepts.md",
"size_in_bytes": 6040
},
{
"relative_path": "reference/development-loop.md",
"size_in_bytes": 3498
},
{
"relative_path": "reference/docker.md",
"size_in_bytes": 6740
},
{
"relative_path": "reference/endpoint-workflows.md",
"size_in_bytes": 4781
},
{
"relative_path": "reference/getting-started.md",
"size_in_bytes": 5751
},
{
"relative_path": "reference/gotchas.md",
"size_in_bytes": 10055
},
{
"relative_path": "reference/gpu-selection.md",
"size_in_bytes": 5739
},
{
"relative_path": "reference/networking.md",
"size_in_bytes": 5452
},
{
"relative_path": "reference/on-pod-setup.md",
"size_in_bytes": 4310
},
{
"relative_path": "reference/pod-workflows.md",
"size_in_bytes": 6302
},
{
"relative_path": "reference/storage.md",
"size_in_bytes": 6769
}
],
"skill_md_contents": "---\nname: runpod-usage\ndescription: >-\n How Runpod works and how to work it — pods vs serverless, GPU/VRAM selection,\n storage, building a container, networking, plus the agentic pod development loop\n (provision → ssh-exec → set up → poll readiness) and on-pod install hygiene\n (uv/apt). Use to answer \"how does X work\", \"which GPU\", \"how do I build a\n container\", or \"how do I stand up a workload on a pod\". Guidance, not a tool —\n execute with runpodctl, runpod-mcp, or flash.\nmetadata:\n author: runpod\n version: \"1.1.2\" # x-release-please-version\nlicense: Apache-2.0\n---\n\n# Runpod usage (concepts)\n\nBackground knowledge for making the right choice before you act. This skill runs\nnothing — once you know what to do, execute with **runpod-mcp**/**runpodctl**\n(infra), **flash** (your own code), or **companion-clis** (models/images/data).\n\nRead the one reference file that matches the question:\n\n| Question | Read |\n| --- | --- |\n| First-run setup / auth — get + set `RUNPOD_API_KEY`, SSH, companion creds | `reference/getting-started.md` |\n| Pods vs serverless, workers, cold starts, FlashBoot, queue vs load-balanced | `reference/concepts.md` |\n| **The development loop for ANY workload (start here)** — plan → prefer prebuilt → provision → verify → teardown | `reference/development-loop.md` |\n| **Stand up / iterate a workload on a pod** — the pod sub-loop | `reference/pod-workflows.md` |\n| **Deploy / iterate a serverless endpoint** — Hub vs flash vs custom, invoke + verify | `reference/endpoint-workflows.md` |\n| **Install software on a pod** — package hygiene, `uv`, non-interactive, caching | `reference/on-pod-setup.md` |\n| Build a Docker image Runpod can run (handler contract, Dockerfile, `--platform=linux/amd64`) | `reference/docker.md` |\n| **How to build an image well** — base image, layering, bake-in vs volume, pod vs serverless (queue/LB) contract | `reference/building-images.md` |\n| Where data lives — container disk vs network volume, model caching, S3 access | `reference/storage.md` |\n| Which GPU / how much VRAM / cost & availability / data centers | `reference/gpu-selection.md` |\n| Reaching a pod or endpoint over HTTP (proxy URLs, exposed ports) | `reference/networking.md` |\n| Common mistakes and how to avoid them | `reference/gotchas.md` |\n"
}SHA-256: 88d0e9fbc062df2c1f09974074d068d484d3eae44867c10ad62423455e7777cf