- name
SKILL.md
O arquivo da skill permanece no repositório do publicador.
Cole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add digitalsamba/claude-code-video-toolkit --skill runpod -a cursor -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add digitalsamba/claude-code-video-toolkit --skill runpod -a claude-code -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add digitalsamba/claude-code-video-toolkit --skill runpod -a codex -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add digitalsamba/claude-code-video-toolkit --skill runpod -a grok -yEnvie a mensagem copiada em um chat do Grok Bot. O Bot busca este SKILL.md no GitHub e o adiciona às skills que todos os seus Bots compartilham.
Install this skill: https://github.com/digitalsamba/claude-code-video-toolkit/tree/HEAD/.claude/skills/runpodDo publicador
Run open-source AI models on cloud GPUs via RunPod serverless. Pay-per-second, no minimums.
# 1. Create account at https://runpod.io
# 2. Add API key to .env
echo "RUNPOD_API_KEY=your_key_here" >> .env
# 3. Deploy any tool with --setup
uv run tools/image_edit.py --setup
uv run tools/upscale.py --setup
uv run tools/dewatermark.py --setup
uv run tools/sadtalker.py --setup
uv run tools/qwen3_tts.py --setup
Each --setup command:
.env (e.g. RUNPOD_QWEN_EDIT_ENDPOINT_ID)All images are public on GHCR — no authentication needed.
Total monthly cost: Rarely exceeds $10 even with heavy use.
All tools follow the same pattern:
Local CLI → Upload input to cloud storage → RunPod API → Poll for result → Download output
R2_ACCOUNT_ID, R2_ACCESS_KEY_ID, R2_SECRET_ACCESS_KEY, R2_BUCKET_NAME), falling back to free upload services/run endpoint, then poll /status/{job_id} until completeworkersMin: 0 — Scale to zero when idle (no cost)
workersMax: 1 — Max concurrent jobs (increase for throughput)
idleTimeout: 5 — Seconds before worker scales down
Across all endpoints, you share a total worker pool based on your RunPod plan. If you hit limits, reduce workersMax on endpoints you're not actively using.
Each tool stores its endpoint ID in .env:
To free worker slots without deleting the endpoint, set workersMax=0 via the RunPod dashboard or GraphQL API.
Use these to query and manage endpoints programmatically. RunPod disables GraphQL introspection, so these field names are verified and must be exact.
All API calls require Authorization: Bearer $RUNPOD_API_KEY.
POST https://api.runpod.io/graphqlhttps://api.runpod.ai/v2/{endpoint_id}/...List all endpoints:
query { myself { endpoints { id name gpuIds templateId workersMax workersMin } } }
Current spend rate:
query { myself { currentSpendPerHr spendDetails { localStoragePerHour networkStoragePerHour gpuComputePerHour } } }
List pods:
query { myself { pods { id name runtime { uptimeInSeconds } machine { gpuDisplayName } desiredStatus } } }
Common mistakes: Field names are camelCase with full words —
localStoragePerHournotlocalStoragePerHr. Endpoints areendpointsnotserverlessWorkers.spendingis not a field — usecurrentSpendPerHrandspendDetails.
Update endpoint GPU or config:
mutation { saveEndpoint(input: {
id: "endpoint_id",
name: "endpoint-name",
templateId: "template_id",
gpuIds: "AMPERE_24",
workersMin: 0,
workersMax: 1
}) { id gpuIds } }
saveEndpoint requires name and templateId even for updates — query first to get current values.
Health response includes job counts and worker state:
{
"jobs": { "completed": 16, "failed": 1, "inProgress": 0, "inQueue": 2, "retried": 0 },
"workers": { "idle": 0, "initializing": 1, "ready": 0, "running": 0, "throttled": 0 }
}
Note:
/requestsonly returns pending/queued jobs. Completed job history is not available via the API — check the RunPod web console for logs.
Availability note: ADA_24 (4090) is frequently throttled/unavailable on RunPod. Always configure endpoints with multiple fallback GPU types (comma-separated) to avoid jobs getting stuck in queue indefinitely:
gpuIds: "AMPERE_24,ADA_24" # Try 3090 first, fall back to 4090
All toolkit tools also enforce a 5-minute queue timeout — if no GPU is available within 300 seconds, the job is automatically cancelled to prevent runaway billing from failed initialization cycles.
R2 uses the S3-compatible API but requires --region auto:
AWS_ACCESS_KEY_ID="$R2_ACCESS_KEY_ID" \
AWS_SECRET_ACCESS_KEY="$R2_SECRET_ACCESS_KEY" \
aws s3api list-objects-v2 \
--bucket "$R2_BUCKET_NAME" \
--endpoint-url "https://${R2_ACCOUNT_ID}.r2.cloudflarestorage.com" \
--region auto
Common mistake: Omitting
--region autocausesInvalidRegionNameerror. R2 valid regions:wnam,enam,weur,eeur,apac,oc,auto.
When you push a new Docker image version, RunPod may still use the cached old one. To force a pull:
imageName to use @sha256:DIGEST notation:latest tag after confirmingIf cold starts are a problem, set workersMin: 1 (costs money when idle).
The model needs more VRAM than the GPU provides. Options:
--resize-ratio (default 0.5 for safety)--stepsYou've hit your plan's concurrent worker limit. Either:
workersMax=0 on endpoints you're not usingAll Dockerfiles live in docker/runpod-*/. Images use runpod/pytorch as the base to share layers across tools.
Building for RunPod (from Apple Silicon Mac):
docker buildx build --platform linux/amd64 -t ghcr.io/conalmullan/video-toolkit-<name>:latest docker/runpod-<name>/
docker push ghcr.io/conalmullan/video-toolkit-<name>:latest
GHCR packages default to private — you must manually make them public for RunPod to pull them. Go to GitHub > Packages > Package Settings > Change Visibility.
workersMin: 0 on all endpoints (scale to zero)workersMax=0 to disable idle endpoints without deleting themCloud GPU processing via RunPod serverless. Use when setting up RunPod endpoints, deploying Docker images, managing GPU resources, troubleshooting endpoint issues, or understanding costs. Covers all 5
---name: runpoddescription: Cloud GPU processing via RunPod serverless. Use when setting up RunPod endpoints, deploying Docker images…---# .claude/skills/runpod/SKILL.mdVisão geral
Cloud GPU processing via RunPod serverless. Use when setting up RunPod endpoints, deploying Docker images, managing GPU resources, troubleshooting endpoint issues, or understanding costs. Covers all 5 toolkit images (qwen-edit, realesrgan, propainter, sadtalker, qwen3-tts).
Perguntas frequentes
Baixe .claude/skills/runpod/SKILL.md do publicador ou copie o caminho e abra o repositório. O PlugMCP lista a skill e não hospeda o arquivo.
O publicador o mantém em https://github.com/digitalsamba/claude-code-video-toolkit.
Claude, Cursor, Codex e Grok Build conseguem ler um SKILL.md que você adiciona a partir do repositório do publicador. O Grok Bot o instala quando você envia em um chat o link da pasta da skill no GitHub.