Ask targeted clarifying questions before executing a task so the agent and user align on scope, constraints, success criteria, and output format.
原文语言:英语
菜单
SkillsMP 已收集 az9713/agentic-workbench-skills 中的 7 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 7 / 7 个已收集 Skill。
Ask targeted clarifying questions before executing a task so the agent and user align on scope, constraints, success criteria, and output format.
原文语言:英语
Generate multiple high-quality variations of an answer, plan, design, prompt, implementation, or artifact so the user can select the best branch and iterate.
原文语言:英语
Improve future Claude Code behavior by extracting corrections, preferences, failures, and reusable workflow rules from the current session. Use at the end of a work session or when the user asks to calibrate, self-improve, update memory, or capture lessons.
原文语言:英语
Create or update a shared project workspace so multiple Claude Code sessions can work on the same project using shared context, session logs, decisions, and artifacts.
原文语言:英语
Play devil's advocate against a proposed plan, option, architecture, vendor, library, or argument. Use to counter sycophancy and surface risks before committing.
原文语言:英语
Load an existing shared project into the current Claude Code session by finding its project folder and reading context, session logs, decisions, and open questions.
原文语言:英语
Add an interactive HTML tuning panel to a visual artifact so the user can adjust design parameters with sliders and then bake the selected values back into the final design.
原文语言:英语