@firerlagi/traeclawinstall
A统一执行 Traeclaw 仓库的 OpenClaw 安装、启动、验收与排障流程;当用户希望在本仓库一站式完成部署或检查时调用。
Install
agr install @firerlagi/traeclawinstall --target claudeWrites 5 files into .claude/skills/, pinned to git-420ae733.
- .claude/skills/traeclawinstall/.gitignore
- .claude/skills/traeclawinstall/CONTRIBUTING.md
- .claude/skills/traeclawinstall/LICENSE
- .claude/skills/traeclawinstall/README.md
- .claude/skills/traeclawinstall/SKILL.md
Document
name: "TraeClawInstall" description: "统一执行 Traeclaw 仓库的 OpenClaw 安装、启动、验收与排障流程;当用户希望在本仓库一站式完成部署或检查时调用。"
OpenClaw 仓库一体化技能
技能目标
将本仓库视为一个整体,统一完成 OpenClaw 的平台识别、安装、启动、验收与排障,不再拆分多个独立技能。
适用场景(何时调用)
- 用户要求“在本地部署openclaw”
- 用户要求“按这个仓库整体流程执行”
- 用户希望在 Trae IDE 内一站式完成部署和验证
- 用户未明确平台细节,但希望直接得到可执行路径
- 用户出现安装/启动异常,需要按仓库标准流程排障
输入前提
- 当前工作目录为仓库根目录
- 可使用终端执行命令
- 可访问仓库文档与脚本
决策路由
- 识别平台:
- Windows:优先 WSL2,走
scripts/windows/wsl/*.sh - macOS:走
scripts/macos/*.sh - Linux:走
scripts/linux/*.sh
- Windows:优先 WSL2,走
- 校验基线:
node --version主版本需>=22npm --version可用openclaw --version若不存在则由 setup 安装
- 执行标准三步:
setup -> start -> check
- 执行最小验收:
openclaw doctoropenclaw statusopenclaw dashboard
- 任一步失败则进入统一排障流程
标准执行步骤(SOP)
Step 0:读取关键入口
README.mddocs/common/trae-ide-guide.mddocs/common/acceptance.mddocs/common/troubleshooting.mddocs/common/install-config-checklist.md- 对应平台
docs/platforms/<platform>/README.md
Step 1:按平台脚本执行
- Windows(WSL2):
bash scripts/windows/wsl/setup.shbash scripts/windows/wsl/start.shbash scripts/windows/wsl/check.sh
- macOS:
bash scripts/macos/setup.shbash scripts/macos/start.shbash scripts/macos/check.sh
- Linux:
bash scripts/linux/setup.shbash scripts/linux/start.shbash scripts/linux/check.sh
如需 dashboard,可在 check 步骤追加 --dashboard。
Step 2:验收判定
- 必须完成
doctor/status/dashboard三项检查 - 结论分为:通过 / 失败待修复
Step 3:失败分诊
- 保存首次报错行
- 重跑:
openclaw doctoropenclaw status
- 核对:
which node || truewhich openclaw || truenode --version || trueopenclaw --version || true
- 按
docs/common/troubleshooting.md对应章节修复 - 每次只改一个变量并复验
输出约定
- 成功:给出平台、执行步骤、验收结果与可访问状态
- 失败:给出首个错误、已验证动作、下一步修复建议
约束
- 优先复用仓库现有文档和脚本,不创建平行流程
- 不写入真实密钥,仅使用示例配置
- Windows 场景优先在 WSL2 Linux 文件系统执行
Trustgrade A
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- passLicense
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-420ae733c5272026-07-31