菜单
Implement the agreed slice. Use when the user invokes $execute-slice or wants to implement a slice agreed via slice-prd.
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。
基于 SOC 职业分类
Skill writing principles. Use when creating, editing, or reviewing any SKILL.md.
Skill rule extraction and creation. Use when the user says /learn.
Kysely database queries. Use when writing, reviewing, or debugging Kysely selects, mutations, joins, transactions, filters, or aggregates.
Frontend components and Tailwind. Use when creating, reviewing, refactoring, splitting, or organizing React components, shared components, component folders, or Tailwind classes.
TanStack Query in React. Use when implementing or reviewing queries, mutations, invalidation, or query hooks.
Lint and optimize existing skills. Use when the user says /skill-linter.
| name | execute-slice |
| description | Implement the agreed slice. Use when the user invokes $execute-slice or wants to implement a slice agreed via slice-prd. |
| disable-model-invocation | true |
Update the PRD only with new facts about the feature's end goal that came up in the grilling. The PRD describes the end state, never the path to it — do not list slices, build a roadmap, or use names from the implementation. Replace contradicting decisions.
Load every relevant skill before starting.
Implement the slice the user just agreed on, working autonomously without pausing for approval.
After finishing, mark the covered user stories as done and tell the user how to validate the delivered slice. Do not propose the next slice.
