Menü
Query RunPod GPU availability and suggest matching GPUs/datacenters.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Ask OpenAI Codex CLI for an autonomous second AI opinion. "ask codex", "codex と相談" などで起動。
Request GitHub Copilot review on a Pull Request. "PR レビュー依頼", "copilot review" などで起動。
Extract VTT transcript from a Zoom recording share page. "zoom transcript", "zoom 文字起こし" などで起動。
Download the video (MP4) from a Zoom recording share page. "zoom video download", "zoom 録画 ダウンロード", "zoom 動画 ダウンロード" などで起動。
Round-trip code review through difit. Use when the user mentions "difit", "diff review", "open the diff", "let me look at this", or "review this PR locally". Launch mode arg — "open" (default, no comments at launch), "explain" (AI annotates its own change), "review" (AI posts findings on human code).
Stop tool execution before exhausting your Claude usage — set a 5h/7d usage-% or per-session cost threshold.
| name | stocks |
| description | Query RunPod GPU availability and suggest matching GPUs/datacenters. |
| metadata | {"author":"pokutuna","compatibility":"RunPod API (requires ~/.runpod/config.toml or RUNPOD_API_KEY)"} |
| allowed-tools | Bash(uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py *) |
Check RunPod GPU availability by datacenter and suggest GPUs matching requirements.
Set RunPod API key via either:
RUNPOD_API_KEY~/.runpod/config.toml (set via runpod CLI)${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py
# All datacenter × GPU availability
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py
# Filter by memory (80GB+)
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --min-memory 80
# Filter by GPU name (partial match, multiple allowed)
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --gpu h100 5090
# Network Volume (S3) supported datacenters only
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --storage
# Filter by stock level
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --stock high # High only
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --stock medium # High + Medium
# Filter by GPU generation
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --gen hopper # H100, H200
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --gen blackwell # B200, RTX 5090, etc.
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --gen ada # RTX 4090, L40, etc.
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --gen ampere # A100, RTX 3090, etc.
# Combined filters
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --min-memory 80 --storage --stock high
# JSON output
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --json
Datacenter Location GPU Mem Gen Stock Storage Price
---------------------------------------------------------------------------------------------------------
EU-CZ-1 Europe RTX 5090 32GB blackwell High ✓ $0.69
EU-RO-1 Europe RTX 5090 32GB blackwell High ✓ $0.69
US-CA-2 United States RTX 5090 32GB blackwell High ✓ $0.69
US-NC-1 United States RTX 5090 32GB blackwell High ✓ $0.69
Found 4 options across 4 datacenters, 1 GPU types
| Option | Description |
|---|---|
--min-memory GB | Minimum VRAM (GB) |
--gpu KEYWORD... | Filter by GPU name (partial match, multiple) |
--storage | Network Volume supported only |
--stock {high,medium,low} | Stock level |
--gen {blackwell,hopper,ada,ampere,volta,amd} | GPU generation |
--secure-cloud | Secure Cloud only |
--community-cloud | Community Cloud only |
--json | JSON output |
| Generation | GPUs |
|---|---|
| blackwell | B200, B300, RTX PRO 6000, RTX 5090, RTX 5080 |
| hopper | H100, H200 |
| ada | RTX 4090, RTX 4080, L40, L40S, RTX 6000 Ada, etc. |
| ampere | A100, A40, RTX 3090, RTX A6000, L4 |
| volta | V100 |
| amd | MI300X |
User: "Where can I use RTX 5090 with Network Volume?"
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --gpu 5090 --storage
User: "Which 80GB+ GPUs are in stock?"
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --min-memory 80 --stock high
User: "Hopper generation with Storage support"
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --gen hopper --storage
User: "Compare H100 and A100 availability"
uv run --script ${CLAUDE_PLUGIN_ROOT}/skills/stocks/scripts/fetch_gpu_stocks.py --gpu h100 a100 --storage
stockStatus is unreliable: API often returns "High" regardless of actual availabilityUser communication: When returning results, inform users that stockStatus is from the API and may not reflect actual availability. Recommend checking the Web UI for real-time status.