doubt-driven-development

addyosmani/agent-skills/skills/doubt-driven-development

对非简单决策进行对抗性审查

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production auth, security-sensitive logic, a high-stakes migration, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.

把下面的话发给 Claude Code、Codex 或 Cursor。智能体会先检查内容，经你确认再安装。

请帮我安装这个 Agent Skill：https://github.com/addyosmani/agent-skills/tree/main/skills/doubt-driven-development

1. 先读取该目录下的 SKILL.md 和其他文件，检查是否有可疑内容（执行未知脚本、读取密钥、向外发送数据等），用中文告诉我它会做什么、需要哪些权限；
2. 等我确认后，再把整个目录安装到 ~/.claude/skills/doubt-driven-development/（如果你不是 Claude Code，安装到你自己约定的 skills 目录）；
3. 安装后告诉我怎么触发它。

安装到个人 Skill 目录（对所有项目生效）。只想在当前项目用，改为 .claude/skills/。

git clone --depth 1 --filter=blob:none --sparse https://github.com/addyosmani/agent-skills.git /tmp/doubt-driven-development-src
cd /tmp/doubt-driven-development-src && git sparse-checkout set "skills/doubt-driven-development"
mkdir -p ~/.claude/skills && cp -r "skills/doubt-driven-development" ~/.claude/skills/doubt-driven-development

Skill 可以让智能体执行脚本。安装第三方 Skill 前务必看一遍内容，详见「安全」一课。

SKILL.md

在 GitHub 查看

正在从 GitHub 读取……