用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/javimosch/open-claw-skills --skill preqstation命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | preqstation |
| description | Run Claude Code, Codex CLI, or Gemini CLI from natural-language OpenClaw requests for PREQSTATION work. |
| metadata | {"openclaw":{"requires":{"anyBins":"[Truncated]"}}} |
Use this skill for natural-language requests to execute PREQSTATION-related work with local CLI engines.
Trigger this skill when the user asks to:
claude, codex, or gemini for implementationpreq or preqstation anywhere in the message (case-insensitive)No fixed prefix is required.
Parse from user message:
engineclaude, codex, or geminiclaudetask<KEY>-<number> (example: PRJ-284)cwd (required to execute)project key from MEMORY.mdMEMORY.md project key, use that pathobjectiveMEMORY.md from this repository root.Projects table (key | cwd | note).MEMORY.md first, then confirm.Projects table only.| <key> | <absolute-path> | <note> |.Do not forward raw user text directly. Render this template:
Task ID: <task or N/A>
Project Key: <project key or N/A>
User Objective: <objective>
Execution Requirements:
1) Work only inside <cwd>.
2) Complete the requested work.
3) After completion, return a short completion summary.
claude --dangerously-skip-permissions -p "<rendered_prompt>"
codex exec --dangerously-bypass-approvals-and-sandbox "<rendered_prompt>"
GEMINI_SANDBOX=false gemini -p "<rendered_prompt>"
Return only a short completion summary.
Success format:
completed: <task or N/A> via <engine> at <cwd>
Failure format:
failed: <task or N/A> via <engine> at <cwd or N/A> - <short reason>
Do not dump raw stdout/stderr unless user explicitly asks.