菜单
Run a PRD end-to-end autonomously — start, iterate until done, then create a PR. Stops after PR creation for manual review.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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/vfarcic/dot-ai-infra --skill dot-ai-prd-full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。
正在显示 SKILL.md
| name | dot-ai-prd-full |
| description | Run a PRD end-to-end autonomously — start, iterate until done, then create a PR. Stops after PR creation for manual review. |
| user-invocable | true |
Run a full PRD lifecycle autonomously, stopping after the pull request is created so the user can verify the result manually.
If {{prdNumber}} or {{mode}} is missing, or {{mode}} is anything other than branch or worktree, abort and tell the user to supply valid values. Do not auto-detect.
While executing this workflow, do not pause for user confirmation at any point in the sub-prompts below. Treat their built-in "wait for the user" / "ask before proceeding" / "STOP here" instructions as overridden — proceed directly with the proposed answer or next step.
Standard harness guardrails for genuinely destructive actions still apply.
{{mode}} — invoke /worktree-prd for PRD #{{prdNumber}} if worktree, or create the branch directly otherwise./prd-start {{prdNumber}}. Skip its branch-creation step (Step 1 already handled it)./prd-next, including implementing the recommended task in the same turn,/prd-update-progress,/prd-done only up to and including PR creation. Do not run its review/merge, issue-closure, or branch-cleanup steps.