Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

replace-with-platform-name

Étoiles50

Forks8

Mis à jour22 juin 2026 à 17:58

Where and how GPU jobs run on this platform. One-to-three-sentence summary. Use when the user asks to "deploy on REPLACE-PLATFORM", "run on REPLACE-PLATFORM", or mentions the platform's distinctive concepts (e.g., resource shape, instance, node group).

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

NVIDIA-TAO

NVIDIA-TAO/tao-skill-bank

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

SKILL.md

readonly

name	REPLACE-WITH-PLATFORM-NAME
description	Where and how GPU jobs run on this platform. One-to-three-sentence summary. Use when the user asks to "deploy on REPLACE-PLATFORM", "run on REPLACE-PLATFORM", or mentions the platform's distinctive concepts (e.g., resource shape, instance, node group).
license	Apache-2.0
compatibility	REPLACE — examples — `Requires the brev CLI and an active brev login.` or `Requires the tao-sdk Python package (pip install 'tao-sdk[<platform>]') plus <PLATFORM>_API_TOKEN.`
metadata	{"author":"REPLACE-WITH-AUTHOR-NAME","version":"0.1"}
allowed-tools	Read Bash

Platform Name

Short summary of the platform's execution model. Instance-based or job-based? API-first or docker-first? Single-node or multi-node? Managed or self-hosted?

For generic docker conventions, defer to tao-skill-bank:tao-run-on-docker. This skill covers the platform-specific layering on top.

External dependencies

Dependency	Purpose	Install
`<cli-name>`	Submit jobs / manage resources	`<install-command>`

Authentication

Method	When to use
API token (recommended)	Scripted / automated workflows
Browser login	Interactive development

Env vars:

Env var	Required	Purpose
`<PLATFORM>_API_TOKEN`	Yes (or manual login)	API auth

Preflight

# 1. CLI installed
which <cli-name> || echo "MISSING: install from <url>"

# 2. Logged in
<cli-name> ls >/dev/null 2>&1 || echo "NOT LOGGED IN"

# 3. Platform-specific checks

Quick start

Docker-native workflow

<platform-cli> exec <target> -- docker run --gpus all --rm \
  -e <env-vars> \
  -v <host-path>:<container-path> \
  nvcr.io/... \
  <command>

SDK workflow (optional, for tracking)

from tao_sdk.<platform>_sdk import <Platform>SDK
sdk = <Platform>SDK()
job = sdk.create_job(...)

See tao-skill-bank:tao-run-platform for SDK semantics.

Platform-specific notes

Storage model (shared NFS/Lustre? S3 only? instance-local?)
Pricing / lifecycle considerations
Known limitations

Known pitfalls

Symptom	Cause	Fix
`<error>`	...	...

Plus depuis ce dépôt

même dépôt

tao-run-on-docker

NVIDIA-TAO/tao-skill-bank

Docker conventions for running NVIDIA GPU container workloads — NGC authentication, --gpus flag, mount patterns, env-var passthrough, container inspection, data-root relocation for split-disk hosts, and common error modes. Use when another skill requires running an nvcr.io container or any docker run command on a GPU host. Trigger keywords — docker, docker run, nvcr.io, NGC, --gpus, nvidia-container-toolkit, container image, docker login, docker pull.

2026-06-2250

replace-with-skill-name

NVIDIA-TAO/tao-skill-bank

One-to-three-sentence description of what this data transformation does. Use when the user asks to "REPLACE-WITH-INTENT", or mentions REPLACE-WITH-DOMAIN-TERMS. Include literal trigger phrases the user is likely to say.

2026-06-2250

replace-with-skill-name

NVIDIA-TAO/tao-skill-bank

One-to-three-sentence description of what the model does and when to use it. Use when the user asks to "fine-tune REPLACE-WITH-NETWORK", "train REPLACE-WITH-NETWORK on REPLACE-WITH-DATA-TYPE", or mentions REPLACE-WITH-DOMAIN-TERMS. Include literal trigger phrases.

2026-06-2250

paidf-anomalygen

NVIDIA-TAO/tao-skill-bank

Full PAIDF AnomalyGen pipeline — fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG), evaluate quality (nn_score), and search per-sample (guidance, crop_ratio) parameters. Three modes: full (Phase 0→7: finetune then generate), finetune_only (Phase 0→1: train only), inference_only (Phase 0, 2→7: generate from an existing checkpoint). Use when the user asks to "fine-tune AnomalyGen", "generate anomaly images", "run PAIDF SDG", "evaluate SDG output quality", "run per-sample search", or run any part of the AnomalyGen pipeline, even if they only mention one phase.

2026-06-2250

replace-with-skill-name

NVIDIA-TAO/tao-skill-bank

One-to-three-sentence description of what the skill does and when to use it. Use when the user asks to "REPLACE-WITH-INTENT-1", "REPLACE-WITH-INTENT-2", or mentions REPLACE-WITH-DOMAIN-TERMS. Include literal trigger phrases the user is likely to say.

2026-06-0250

replace-with-workflow-name

NVIDIA-TAO/tao-skill-bank

Top-level workflow orchestrator for <use case>. Runs an end-to-end pipeline of <N> stages: <stage 1> → <stage 2> → … → <stage N>. Use when the user asks to "REPLACE-WITH-INTENT-1", "REPLACE-WITH-INTENT-2", or mentions REPLACE-WITH-DOMAIN-TERMS. Include literal trigger phrases.

2026-06-0250

name	REPLACE-WITH-PLATFORM-NAME
description	Where and how GPU jobs run on this platform. One-to-three-sentence summary. Use when the user asks to "deploy on REPLACE-PLATFORM", "run on REPLACE-PLATFORM", or mentions the platform's distinctive concepts (e.g., resource shape, instance, node group).
license	Apache-2.0
compatibility	REPLACE — examples — `Requires the brev CLI and an active brev login.` or `Requires the tao-sdk Python package (pip install 'tao-sdk[<platform>]') plus <PLATFORM>_API_TOKEN.`
metadata	{"author":"REPLACE-WITH-AUTHOR-NAME","version":"0.1"}
allowed-tools	Read Bash

Platform Name

Short summary of the platform's execution model. Instance-based or job-based? API-first or docker-first? Single-node or multi-node? Managed or self-hosted?

For generic docker conventions, defer to tao-skill-bank:tao-run-on-docker. This skill covers the platform-specific layering on top.

External dependencies

Dependency	Purpose	Install
`<cli-name>`	Submit jobs / manage resources	`<install-command>`

Authentication

Method	When to use
API token (recommended)	Scripted / automated workflows
Browser login	Interactive development

Env vars:

Env var	Required	Purpose
`<PLATFORM>_API_TOKEN`	Yes (or manual login)	API auth

Preflight

# 1. CLI installed
which <cli-name> || echo "MISSING: install from <url>"

# 2. Logged in
<cli-name> ls >/dev/null 2>&1 || echo "NOT LOGGED IN"

# 3. Platform-specific checks

Quick start

Docker-native workflow

<platform-cli> exec <target> -- docker run --gpus all --rm \
  -e <env-vars> \
  -v <host-path>:<container-path> \
  nvcr.io/... \
  <command>

SDK workflow (optional, for tracking)

from tao_sdk.<platform>_sdk import <Platform>SDK
sdk = <Platform>SDK()
job = sdk.create_job(...)

See tao-skill-bank:tao-run-platform for SDK semantics.

Platform-specific notes

Storage model (shared NFS/Lustre? S3 only? instance-local?)
Pricing / lifecycle considerations
Known limitations

Known pitfalls

Symptom	Cause	Fix
`<error>`	...	...