ShaftHQ
ShaftHQ/SHAFT_ENGINE
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/ShaftHQ/SHAFT_ENGINE --skill chaos-engine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。
Optional local coding loop as a mechanical or default delegate. Use when the decider model wants a cheap local coder and a hardware probe says the host can run one.
Use when opening or rewriting a work item on any git-based SCM. Source-control agnostic; GitHub, GitLab, and Azure Boards are adapters only.
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
基于 SOC 职业分类
正在显示 SKILL.md
| name | chaos-engine |
| description | Load the canonical ChaosEngine policy and this repository's selected project profile before every task. |
Follow the canonical portable entrypoint, review the profiles catalog, then load the selected SHAFT profile. The repository harness map inventories every local adapter and enforcement surface.