正在加载仓库 README…
已展示 4 / 4 个已收集 Skill。
Use when the human asks for a coding task to run through shepherd's human-gated pipeline with durable run files under .shepherd/ instead of direct editing — features, bug fixes, refactors. Invoked on demand: /shepherd <task> starts a run, bare /shepherd…
原文语言：英语
HUMAN-ONLY shepherd design approval. Run after reviewing .shepherd/2-design.md, .shepherd/3-success-criteria.md, and .shepherd/_panel.json. Records the approved panel in _state.json, writes .shepherd/_design.approved, and hands control back to /shepherd. The…
原文语言：英语
Post-run analysis of one or more shepherd runs in the current session — per-stage cost, signal-per-stage counterfactuals, reviewer overlap, gate calibration, and ranked improvements. Run after a run reaches phase=done. Invoke as /shepherd-evaluate.
原文语言：英语
HUMAN-ONLY shepherd create-PR approval. Run after reviewing the change and .shepherd evidence. Writes .shepherd/_create_pr.approved and hands control back to /shepherd. The agent cannot invoke this.
原文语言：英语
复制这段 Prompt，发给你正在使用的 AI 助手。
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/apify/shepherd.暂时无法加载仓库 README。你仍可浏览下方的 Skill 目录。