Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Cloud Deploy Cn · yangge521 | DecimalAI

devopsby yangge521

Cloud Deploy Cn

yangge521/cloud-deploy-cn

Source yangge521/dev-skills-zh ↗License MIT

云服务器部署指南，涵盖阿里云/腾讯云/AWS 部署、GPU 云实例、CI/CD 自动化

SkillScore82Maintained

Automatic

DevOps & SRE pack

Last verified 8/3/2026

What it changes

Passed 18 of 22 test cases with the skill, and 14 of 22 without it.

Without skill64%

With skill82%

Checks it passed that the model alone missed

Includes checking root SSH access is disabled.
Includes checking firewall rules are configured.
Includes -e CUDA_VISIBLE_DEVICES=0 in the run command.

and 2 more in the full report

4 fixed14 passed either way4 still failing0 broke

Pass-rate lift: +18 pp
Tokens: +24%
Agent turns: 0%
Response time: -15%

Model gemini-3.6-flashMeasured 8/3/2026v118 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/yangge521-cloud-deploy-cn/SKILL.md https://app.decimal.ai/s/yangge521-cloud-deploy-cn/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add yangge521-cloud-deploy-cn, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/yangge521-cloud-deploy-cn/ and pins it in .decimal/skills.lock

decimalai skills add yangge521-cloud-deploy-cn

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/yangge521-cloud-deploy-cn/SKILL.md https://app.decimal.ai/s/yangge521-cloud-deploy-cn/SKILL.md

Raw file: /s/yangge521-cloud-deploy-cn/SKILL.md ↗ · machine-readable summary at /s/yangge521-cloud-deploy-cn.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

要在阿里云上部署轻量级的在线模型推理服务，预算有限，需要兼顾性价比，请问推荐选择哪种 GPU 实例规格及其大致每小时单价？

What was checked, without and with the skill
Checked	Without skill	With skill
Recommends Alibaba Cloud GN7 instance type.	Passed	Passed
Mentions reference price of approximately 5 RMB per hour.	Missed	Passed

case-09 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md84 linessingle file

云服务器部署指南

概述

提供主流云平台（阿里云、腾讯云、AWS）的部署指南，包含 GPU 实例选型、环境配置、CI/CD 自动化流程。

使用场景

GPU 推理服务上云：从本地部署迁移到云 GPU
弹性伸缩：根据流量自动增减 GPU 实例
多区域部署：不同区域部署推理服务降低延迟
灾备方案：主备云服务器故障切换
GPU 实例选型：对比不同云平台 GPU 性价比
混合云部署：本地 GPU + 云 GPU 混合调度

操作指南

1. GPU 云实例选型

平台	实例类型	GPU	显存	适用场景	参考价格
阿里云	GN10X	V100	16GB	深度学习训练	~15元/小时
阿里云	GN7	T4	16GB	推理/轻量训练	~5元/小时
腾讯云	GN10X	V100	16GB	训练	~14元/小时
AWS	p3.2xlarge	V100	16GB	训练	~$3.06/小时
AWS	g4dn.xlarge	T4	16GB	推理	~$0.526/小时

2. GPU 服务器环境初始化

安装 NVIDIA 驱动（nvidia-driver-535），安装 Docker 和 NVIDIA Container Toolkit，验证 nvidia-smi 和 Docker GPU 访问。

3. 推理服务部署

使用 docker run --gpus all -e CUDA_VISIBLE_DEVICES=0 -p 8000:8000 部署，挂载模型和数据目录，配置 --restart unless-stopped。

4. Nginx 反向代理 + SSL

安装 Nginx 和 Certbot，配置反向代理指向推理服务，certbot --nginx 自动 SSL。

5. CI/CD 自动化部署

Track record

Benchmark

18 / 22

test cases passed, vs 14 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

yangge521 / dev-skills-zh

skills/devops/cloud-deploy-cn/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.