Agent skill

Terraform CLI Setup

by agentscope-ai in agentscope-ai/QwenPaw

Detects whether Terraform is installed, installs it with the right method for macOS or Linux, then runs and verifies terraform init, leaving provider credentials to a separate skill.

Apache-2.0Auto-check: notesDevOps & Cloud

SKILL.md written in Chinese; this summary is our English description.

Install Terraform CLI Setup

skills CLI

$ npx skills add agentscope-ai/QwenPaw --skill terraform-cli-setup -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install agentscope-ai/QwenPaw terraform-cli-setup --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/bundle/cloudpaw/skills/terraform-cli-setup .claude/skills/terraform-cli-setup && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "terraform-cli-setup" agent skill from https://github.com/agentscope-ai/QwenPaw/tree/main/plugins/bundle/cloudpaw/skills/terraform-cli-setup into .claude/skills/terraform-cli-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "terraform-cli-setup", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/agentscope-ai/QwenPaw/tree/main/plugins/bundle/cloudpaw/skills/terraform-cli-setup

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add agentscope-ai/QwenPaw --skill terraform-cli-setup -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install agentscope-ai/QwenPaw terraform-cli-setup --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/bundle/cloudpaw/skills/terraform-cli-setup .agents/skills/terraform-cli-setup && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "terraform-cli-setup" agent skill from https://github.com/agentscope-ai/QwenPaw/tree/main/plugins/bundle/cloudpaw/skills/terraform-cli-setup into .agents/skills/terraform-cli-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "terraform-cli-setup", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add agentscope-ai/QwenPaw --skill terraform-cli-setup -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install agentscope-ai/QwenPaw terraform-cli-setup --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/bundle/cloudpaw/skills/terraform-cli-setup .cursor/skills/terraform-cli-setup && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "terraform-cli-setup" agent skill from https://github.com/agentscope-ai/QwenPaw/tree/main/plugins/bundle/cloudpaw/skills/terraform-cli-setup into .cursor/skills/terraform-cli-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "terraform-cli-setup", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/agentscope-ai/QwenPaw.git --path plugins/bundle/cloudpaw/skills/terraform-cli-setup

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add agentscope-ai/QwenPaw --skill terraform-cli-setup -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install agentscope-ai/QwenPaw terraform-cli-setup --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/bundle/cloudpaw/skills/terraform-cli-setup .gemini/skills/terraform-cli-setup && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "terraform-cli-setup" agent skill from https://github.com/agentscope-ai/QwenPaw/tree/main/plugins/bundle/cloudpaw/skills/terraform-cli-setup into .gemini/skills/terraform-cli-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "terraform-cli-setup", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install agentscope-ai/QwenPaw terraform-cli-setup

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add agentscope-ai/QwenPaw --skill terraform-cli-setup -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/bundle/cloudpaw/skills/terraform-cli-setup .github/skills/terraform-cli-setup && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "terraform-cli-setup" agent skill from https://github.com/agentscope-ai/QwenPaw/tree/main/plugins/bundle/cloudpaw/skills/terraform-cli-setup into .github/skills/terraform-cli-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "terraform-cli-setup", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add agentscope-ai/QwenPaw --skill terraform-cli-setup -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install agentscope-ai/QwenPaw terraform-cli-setup --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/bundle/cloudpaw/skills/terraform-cli-setup .opencode/skills/terraform-cli-setup && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "terraform-cli-setup" agent skill from https://github.com/agentscope-ai/QwenPaw/tree/main/plugins/bundle/cloudpaw/skills/terraform-cli-setup into .opencode/skills/terraform-cli-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "terraform-cli-setup", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: terraform-cli-setup
GitHub stars: 35k
Token cost: ~2k tokens
SKILL.md length: 458 words
Files: 2 (incl. scripts)
Skills in repo: 20
Repo updated: Sep 30, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Detects whether Terraform is installed, installs it with the right method for macOS or Linux, then runs and verifies terraform init, leaving provider credentials to a separate skill.

Works in 4 steps: 初始化 Backend — 配置状态存储（默认为本地） → 安装 Provider 插件 — 下载 .tf 中声明的 Provider → 下载模块 — 获取引用的远程模块 → …
Installing Terraform for the first time on a new machine
SKILL.md covers 目标, 何时触发此技能, 完整流程 and 自动化脚本, plus 7 more sections
Runs Python scripts from its folder; calls terraform, brew and apt-get; reaches releases.hashicorp.com and apt.releases.hashicorp.com

What it does

This Chinese-language skill checks whether the terraform command is available and, if not, installs it: Homebrew on macOS (or a manual binary download), and on Linux either a manual download, the APT repository for Debian and Ubuntu, or the YUM repository for RHEL, CentOS and Fedora, with architecture detection for each path. It triggers on a first use of Terraform, a command-not-found error, a provider download failure during init, an explicit reinstall request, or as a dependency check before a separate terraform-skill runs.

Once terraform is on the path, it guides running terraform init in a directory with .tf files, explaining the four things init does: initializing the backend for state storage, installing declared provider plugins, downloading referenced remote modules and writing the .terraform.lock.hcl lock file. Common options such as -upgrade are listed.

A verification table maps terraform version and validate output to next steps, including Error: Failed to query available provider packages (check network or mirror), Error: Inconsistent dependency lock file (rerun init -upgrade) and Error: No valid credential sources found, which this skill explicitly defers to the companion terraform-skill rather than handling itself, since provider credentials for AWS, Azure, GCP or Alibaba Cloud are out of scope here.

When your agent uses it

Installing Terraform for the first time on a new machine
Fixing a terraform command not found error
Running and verifying terraform init in a new working directory
Troubleshooting a provider download or lock file error during init

Example prompts

“Terraform 没装，帮我装一下并跑 init。”
“terraform init 报错 provider 下载失败，怎么办？”
“Install Terraform on this Ubuntu server and verify it with terraform validate.”

Requirements

macOS with Homebrew, or a Linux distribution with APT or YUM
Network access to download Terraform and its providers

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

初始化 Backend — 配置状态存储（默认为本地）
安装 Provider 插件 — 下载 .tf 中声明的 Provider
下载模块 — 获取引用的远程模块
创建锁文件 — 生成 .terraform.lock.hcl 锁定版本

What it can do on your machine

Read from SKILL.md and the folder at commit 80e412d. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- terraform
- brew
- apt-get
- curl
- yum
- wget
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- releases.hashicorp.com
- apt.releases.hashicorp.com
- mirrors.aliyun.com
- rpm.releases.hashicorp.com
- mirrors.tencent.com
Also links to:
- developer.hashicorp.com
- registry.terraform.io
- github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Terraform CLI Setup loads about 2k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 458 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~38
When it runs · the whole SKILL.md, loaded when a task matches: ~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteRuns commands with sudoSKILL.md:79

sudo apt-get update && sudo apt-get install -y gnupg software-properties-common

NoteRuns commands with sudoSKILL.md:81

gpg --dearmor | sudo tee /usr/share/keyrings/hashicorp-archive-keyring.gpg > /dev/null

NoteRuns commands with sudoSKILL.md:84

sudo tee /etc/apt/sources.list.d/hashicorp.list

NoteRuns commands with sudoSKILL.md:85

sudo apt-get update && sudo apt-get install terraform

NoteRuns commands with sudoSKILL.md:91
```
sudo yum install -y yum-utils
```

NoteRuns commands with sudoSKILL.md:92

sudo yum-config-manager --add-repo https://rpm.releases.hashicorp.com/RHEL/hashicorp.repo

NoteRuns commands with sudoSKILL.md:93
```
sudo yum -y install terraform
```

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from agentscope-ai/QwenPaw at commit 80e412d, republished under its Apache-2.0 licence (© agentscope-ai). 458 words, ~1,958 tokens.

Download SKILL.mdSave it as .claude/skills/terraform-cli-setup/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: terraform-cli-setup
description: Terraform CLI 安装与初始化技能。当用户本地未安装 Terraform 时自动完成安装，确保 terraform 命令可用并能执行 init/validate。不负责 Provider 凭证配置，凭证在实际使用时由 terraform-skill 引导。

Category: setup

Terraform CLI 安装与初始化

目标

检测本地是否已安装 terraform，未安装则自动安装
确保 terraform version 正常输出
引导完成 terraform init 初始化工作区
处理 Provider 下载、镜像配置等基础环境问题

关于 Provider 凭证配置：各云厂商的凭证配置（AWS/Azure/GCP/阿里云等）不在本技能范围内。Provider 凭证在实际使用 Terraform 时按需配置，请参考 terraform-skill 中的 Provider 凭证配置引导。

何时触发此技能

用户首次使用 Terraform 相关功能
执行 terraform 命令报错 command not found
terraform init 报 Provider 下载失败（网络/镜像问题）
用户主动要求安装或重新安装 Terraform
其他 Terraform 技能（terraform-skill）的前置依赖检查

完整流程

第 1 步：检测安装状态

bash

which terraform 2>/dev/null || echo "NOT_INSTALLED"

如果未安装，进入安装流程。如果已安装，跳到第 3 步。

第 2 步：安装 Terraform

macOS (Homebrew — 推荐)

bash

brew tap hashicorp/tap
brew install hashicorp/tap/terraform

macOS (手动下载)

bash

ARCH=$(uname -m)
case "$ARCH" in
    x86_64|amd64) ARCH="amd64" ;;
    arm64|aarch64) ARCH="arm64" ;;
esac
curl -fsSL "https://releases.hashicorp.com/terraform/1.14.6/terraform_1.14.6_darwin_${ARCH}.zip" -o /tmp/terraform.zip
mkdir -p ~/.local/bin
unzip -o /tmp/terraform.zip -d ~/.local/bin/
chmod +x ~/.local/bin/terraform
export PATH="$HOME/.local/bin:$PATH"

Linux (手动下载)

bash

ARCH=$(uname -m)
case "$ARCH" in
    x86_64|amd64) ARCH="amd64" ;;
    arm64|aarch64) ARCH="arm64" ;;
esac
curl -fsSL "https://releases.hashicorp.com/terraform/1.14.6/terraform_1.14.6_linux_${ARCH}.zip" -o /tmp/terraform.zip
mkdir -p ~/.local/bin
unzip -o /tmp/terraform.zip -d ~/.local/bin/
chmod +x ~/.local/bin/terraform
export PATH="$HOME/.local/bin:$PATH"

Linux (APT — Debian/Ubuntu)

bash

sudo apt-get update && sudo apt-get install -y gnupg software-properties-common
wget -O- https://apt.releases.hashicorp.com/gpg | \
  gpg --dearmor | sudo tee /usr/share/keyrings/hashicorp-archive-keyring.gpg > /dev/null
echo "deb [signed-by=/usr/share/keyrings/hashicorp-archive-keyring.gpg] \
  https://apt.releases.hashicorp.com $(lsb_release -cs) main" | \
  sudo tee /etc/apt/sources.list.d/hashicorp.list
sudo apt-get update && sudo apt-get install terraform

Linux (YUM — RHEL/CentOS/Fedora)

bash

sudo yum install -y yum-utils
sudo yum-config-manager --add-repo https://rpm.releases.hashicorp.com/RHEL/hashicorp.repo
sudo yum -y install terraform

安装后验证：

bash

terraform version

第 3 步：初始化 Terraform 工作区

在有 .tf 文件的目录中执行：

bash

terraform init

terraform init 会执行：

初始化 Backend — 配置状态存储（默认为本地）
安装 Provider 插件 — 下载 .tf 中声明的 Provider
下载模块 — 获取引用的远程模块
创建锁文件 — 生成 .terraform.lock.hcl 锁定版本

常见 init 选项：

bash

# 升级 Provider 和模块到约束范围内的最新版本
terraform init -upgrade

# 重新配置 Backend
terraform init -reconfigure

# 迁移 State 到新 Backend
terraform init -migrate-state

第 4 步：验证安装与初始化

bash

# 检查版本
terraform version

# 检查配置文件语法（需要先 init）
terraform validate

# 格式化代码
terraform fmt -check

验证结果判断：

输出	含义	处理方式
`Terraform vX.Y.Z`	版本正常	安装成功
`Success! The configuration is valid.`	validate 通过	初始化完成
`Error: Failed to query available provider packages`	Provider 下载失败	检查网络或配置镜像
`Error: Inconsistent dependency lock file`	锁文件不一致	执行 `terraform init -upgrade`
`Error: Module not installed`	模块未下载	执行 `terraform init`
`Error: No valid credential sources found`	Provider 凭证缺失	参考 terraform-skill 配置凭证

自动化脚本

本技能提供 scripts/setup_terraform.py，用于一键检测+安装（从本技能目录执行）：

bash

python scripts/setup_terraform.py

该脚本会：

检测 terraform 是否已安装
未安装则根据 OS/Arch 自动下载安装（macOS 优先用 Homebrew）
输出版本信息确认安装成功

Agent 决策指南

当你（AI Agent）执行此技能时，按以下决策树操作：

开始
 │
 ├── which terraform → 未找到?
 │     └── 根据操作系统自动选择最佳安装方式（无需询问用户）
 │           ├── macOS → 优先 brew install，brew 不可用则手动下载
 │           └── Linux → 优先手动下载 zip，检测到 apt/yum 则用包管理器
 │
 ├── terraform version → 正常输出?
 │     └── 是 → ✅ Terraform 已就绪
 │
 ├── 当前目录有 .tf 文件?
 │     ├── 是 → terraform init
 │     │      ├── 成功 → terraform validate
 │     │      │      ├── 成功 → ✅ 初始化完成
 │     │      │      └── 失败 → 根据错误信息自动判断修复方案并执行
 │     │      └── Provider 下载失败 → 自动配置阿里云镜像源并重试
 │     └── 否 → ✅ 安装完成，等用户创建 .tf 文件后再 init
 │
 └── 遇到 Provider 凭证错误?
       └── 引导用户参考 terraform-skill 进行凭证配置

自动决策原则

重要：在执行本技能时，Agent 应当自动判断并选择最合适的方案和配置，无需询问用户，直接执行。

安装方式自动选择逻辑

操作系统	判断条件	自动选择
macOS	`which brew` 存在	`brew install hashicorp/tap/terraform`
macOS	brew 不可用	手动下载对应架构的 zip 安装到 `~/.local/bin`
Linux (Debian/Ubuntu)	`which apt-get` 存在	APT 安装
Linux (RHEL/CentOS)	`which yum` 存在	YUM 安装
Linux (其他)	无包管理器	手动下载 zip 安装

Provider 下载失败自动处理

当 terraform init 因 Provider 下载失败时，自动配置阿里云镜像并重试：

bash

cat > ~/.terraformrc << 'EOF'
provider_installation {
  network_mirror {
    url = "https://mirrors.aliyun.com/terraform/"
  }
}
EOF
terraform init

init 错误自动修复

错误类型	自动修复操作
`Inconsistent dependency lock file`	自动执行 `terraform init -upgrade`
`Module not installed`	自动执行 `terraform init`
`Plugin reinitialization required`	自动执行 `terraform init -upgrade`
`Backend initialization required`	自动执行 `terraform init`
Provider 凭证错误	引导参考 terraform-skill 配置凭证

Show full SKILL.md (187 more words)Show less

执行原则

所有可自动判断的场景直接由 Agent 根据环境检测结果自动选择最优方案并执行，不向用户提问
安装方式根据操作系统和可用工具链自动决定
错误修复根据错误类型自动匹配最佳修复策略
镜像配置默认选择阿里云镜像
仅在遇到需要用户提供敏感信息（如凭证）或无法自动决策的极端情况时，才以纯文本方式向用户说明

Terraform 中国镜像配置

国内网络环境下载 Provider 可能较慢，可配置镜像。

创建或编辑 ~/.terraformrc：

hcl

# 阿里云镜像
provider_installation {
  network_mirror {
    url = "https://mirrors.aliyun.com/terraform/"
  }
}

或腾讯云镜像：

hcl

provider_installation {
  network_mirror {
    url = "https://mirrors.tencent.com/terraform/"
  }
}

常见问题快速修复

问题	快速修复
`command not found: terraform`	`brew install hashicorp/tap/terraform` 或参照安装流程
`Error: Failed to query available provider packages`	检查网络连接，或配置 Terraform Registry 镜像
`Error: Backend initialization required`	执行 `terraform init`
`Error: Plugin reinitialization required`	执行 `terraform init -upgrade`
`Error: Inconsistent dependency lock file`	执行 `terraform init -upgrade` 更新锁文件
`Error: state snapshot was created by Terraform vX.Y.Z`	升级 Terraform 版本
`Error: Module not installed`	执行 `terraform init` 或 `terraform get`
Provider 下载超时	配置 Terraform Registry 镜像（见上方）
`Error: No valid credential sources found`	此为 Provider 凭证问题，参考 terraform-skill

配置文件位置

文件	位置	说明
CLI 配置	`~/.terraformrc`（macOS/Linux）	全局 CLI 配置（镜像等）
Provider 缓存	`~/.terraform.d/plugins/`	下载的 Provider 插件缓存
工作区 Provider	`.terraform/providers/`	当前工作区的 Provider 插件
锁文件	`.terraform.lock.hcl`	Provider 版本锁定（应提交到 Git）
State 文件	`terraform.tfstate`	本地状态文件（不应提交到 Git）

与其他技能的关系

技能	职责
terraform-cli-setup（本技能）	Terraform CLI 的安装、init、镜像配置等基础环境
terraform-skill	Terraform 实际使用：编写配置、Provider 凭证配置、模块开发、测试、CI/CD

关于阿里云 ROS：阿里云资源编排服务（ROS）没有独立 CLI 工具，直接通过 aliyun ros <API> 使用 aliyun-cli 调用。如需使用 ROS，请确保 aliyun-cli 已安装（参考 alicloud_cli 技能）。

Interaction Tips

重要提示：在使用本技能时，请遵循以下规则：

自动决策优先：安装方式、镜像选择、错误处理等场景，Agent 应根据环境检测结果自动选择最优方案并直接执行，不向用户提问

执行过程中向用户简要说明正在做什么及原因，保持信息透明

仅在需要用户提供无法自动获取的敏感信息（如凭证）时才向用户询问

遇到错误时先自动尝试修复，修复失败后再向用户说明情况并提供建议

参考

Terraform 官方文档：https://developer.hashicorp.com/terraform
Terraform CLI 教程：https://developer.hashicorp.com/terraform/tutorials/cli
Terraform 安装指南：https://developer.hashicorp.com/terraform/install
Provider Registry：https://registry.terraform.io/
GitHub 仓库：https://github.com/hashicorp/terraform

Files

SKILL.md and 1 other file (scripts) in plugins/bundle/cloudpaw/skills/terraform-cli-setup of agentscope-ai/QwenPaw.

SKILL.md
scripts/setup_terraform.py

Open the folder on GitHubat commit 80e412d

Compare with similar skills

Terraform CLI Setup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Terraform CLI Setup compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Terraform CLI Setup this skillagentscope-ai/QwenPaw	35k	—	~2k	Automated safety check: Notes	Apache-2.0	7 days ago
Spa Create Configsplunk/splunk-platform-automator	137	—	~3.5k	Automated safety check: Pass	Proprietary	yesterday
Aegisops AIsickn33/agentic-awesome-skills	47k	2 repos	~1.3k	Automated safety check: Notes	MIT	yesterday
Terraform Skillantonbabenko/terraform-skill	2.4k	1 repos	~5.1k	Automated safety check: Pass	Apache-2.0	3 mo ago
Senior DevOps Toolkitmaslennikov-ig/claude-code-orchestrator-kit	259	6 repos	~1.1k	Automated safety check: Notes	Custom licence	7 mo ago
Cloudflarehodgef/apiker	127	7 repos	~2.2k	Automated safety check: Pass	MIT	1 mo ago

Similar skills

Spa Create Config
splunk/splunk-platform-automator
A skill your agent uses when creating or updating splunkconfig.yml, designing Splunk Enterprise lab topology, multisite IDXC, SHC layout, architecture plan before config, or AWS Terraform block for…
137 GitHub stars~3.5k tokensUpdated yesterday
DevOps & CloudAuto-check passed
Aegisops AI
sickn33/agentic-awesome-skills
Autonomous DevSecOps & FinOps Guardrails. An agent skill from sickn33/agentic-awesome-skills.
47k GitHub starsUsed in 2 repos~1.3k tokens
DevOps & CloudAuto-check: notes
Terraform Skill
antonbabenko/terraform-skill
A skill your agent uses when writing, reviewing, or debugging Terraform/OpenTofu modules, tests, CI, scans, or state ops - diagnoses failure mode (identity churn, secrets, blast radius, CI drift…
2.4k GitHub starsUsed in 1 repo~5.1k tokens
DevOps & CloudAuto-check passed
Senior DevOps Toolkit
maslennikov-ig/claude-code-orchestrator-kit
Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup…
259 GitHub starsUsed in 6 repos~1.1k tokens
DevOps & CloudAuto-check: notes
Cloudflare
hodgef/apiker
Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF…
127 GitHub starsUsed in 7 repos~2.2k tokens
DevOps & CloudAuto-check passed
Terravision Cloud Diagrams
patrickchugh/terravision
Draw cloud architecture diagrams for AWS, Azure or GCP with the official provider icon sets, using TerraVision.
1.6k GitHub stars~5.6k tokensUpdated today
DevOps & CloudAuto-check: notes

Questions about Terraform CLI Setup

What does Terraform CLI Setup do?

Detects whether Terraform is installed, installs it with the right method for macOS or Linux, then runs and verifies terraform init, leaving provider credentials to a separate skill. This Chinese-language skill checks whether the terraform command is available and, if not, installs it: Homebrew on macOS (or a manual binary download), and on Linux either a manual download, the APT repository for Debian and Ubuntu, or the YUM repository for RHEL, CentOS and Fedora, with architecture detection for each path. It triggers on a first use of Terraform, a command-not-found error, a provider download failure during init, an explicit reinstall request, or as a dependency check before a separate terraform-skill runs.

When should I use Terraform CLI Setup?

Terraform CLI Setup fits situations like: installing Terraform for the first time on a new machine; fixing a terraform command not found error; running and verifying terraform init in a new working directory; troubleshooting a provider download or lock file error during init.

How do I install Terraform CLI Setup in Claude Code?

Run `npx skills add agentscope-ai/QwenPaw --skill terraform-cli-setup -a claude-code`. Or copy the skill folder (plugins/bundle/cloudpaw/skills/terraform-cli-setup in agentscope-ai/QwenPaw) into .claude/skills/terraform-cli-setup in your project. Claude Code loads it when a task matches its description.

How do I install Terraform CLI Setup in Codex?

Run `npx skills add agentscope-ai/QwenPaw --skill terraform-cli-setup -a codex`. Or copy the skill folder (plugins/bundle/cloudpaw/skills/terraform-cli-setup in agentscope-ai/QwenPaw) into .agents/skills/terraform-cli-setup in your project. Codex loads it when a task matches its description.

Can I use Terraform CLI Setup in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentscope-ai/QwenPaw --skill terraform-cli-setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/terraform-cli-setup, .gemini/skills/terraform-cli-setup, .github/skills/terraform-cli-setup and .opencode/skills/terraform-cli-setup in your project.

What does Terraform CLI Setup need to run?

Going by SKILL.md and its folder, Terraform CLI Setup needs Python for the scripts in its folder and the command-line tools its instructions call (terraform, brew, apt-get, curl, yum and wget). Our summary lists: macOS with Homebrew, or a Linux distribution with APT or YUM; Network access to download Terraform and its providers.

Does Terraform CLI Setup access the network?

SKILL.md names 8 domains. In commands or code: releases.hashicorp.com, apt.releases.hashicorp.com, mirrors.aliyun.com, rpm.releases.hashicorp.com and mirrors.tencent.com; the agent is likely to contact these when it follows the instructions. As links in the text: developer.hashicorp.com, registry.terraform.io and github.com. This is read from the text; nothing was executed.

Is Terraform CLI Setup safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Terraform CLI Setup use?

Terraform CLI Setup is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Terraform CLI Setup use?

About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Terraform CLI Setup?

Skills that share tags, products or a category with Terraform CLI Setup: Spa Create Config (splunk/splunk-platform-automator, 137 stars), Aegisops AI (sickn33/agentic-awesome-skills, 47k stars), Terraform Skill (antonbabenko/terraform-skill, 2.4k stars) and Senior DevOps Toolkit (maslennikov-ig/claude-code-orchestrator-kit, 259 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Terraform CLI Setup?

agentscope-ai (a GitHub organization) maintains it in agentscope-ai/QwenPaw, which has 35,464 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on September 30, 2026.

Source: agentscope-ai/QwenPaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Terraform CLI Setup

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Terraform CLI 安装与初始化

目标

何时触发此技能

完整流程

第 1 步：检测安装状态

第 2 步：安装 Terraform

macOS (Homebrew — 推荐)

macOS (手动下载)

Linux (手动下载)

Linux (APT — Debian/Ubuntu)

Linux (YUM — RHEL/CentOS/Fedora)

第 3 步：初始化 Terraform 工作区

第 4 步：验证安装与初始化

自动化脚本

Agent 决策指南

自动决策原则

安装方式自动选择逻辑

Provider 下载失败自动处理

init 错误自动修复

执行原则

Terraform 中国镜像配置

常见问题快速修复

配置文件位置

与其他技能的关系

Interaction Tips

参考

Files

Compare with similar skills

Similar skills

More from agentscope-ai/QwenPaw

Related

Questions about Terraform CLI Setup