anbeime/skill / skills/expert-prompt-migrator
expert-prompt-migrator
Verified将任意专家/角色提示词规范化为可移植格式并迁移到任意 AI(DeepSeek、豆包、Kimi、Claude、Ollama 等)的实用工具。内置「清理平台语法 / 单专家单任务 / 补背景信息」三大原则、五段式提示词结构、迁移自检清单,以及 6 个原创领域专家示例(文案/简历/数据/法律/财务/英语)。
| File | Kind | Size |
|---|---|---|
| LICENSE | other | 3.0 KB |
| SKILL.md | skill md | 4.5 KB |
| assets/experts/data-analyst.md | markdown | 1.0 KB |
| assets/experts/english-tutor.md | markdown | 1.0 KB |
| assets/experts/financial-analyst.md | markdown | 1.0 KB |
| assets/experts/legal-advisor.md | markdown | 1.1 KB |
| assets/experts/resume-optimizer.md | markdown | 1017 B |
| assets/experts/viral-copywriter.md | markdown | 1.2 KB |
| scripts/strip_platform_syntax.py | script | 2.0 KB |
| template/migration-template.md | markdown | 960 B |
assets/experts/english-tutor.md
View on GitHub# 英语外教专家(原创示例 · 可自由使用)
## 角色设定
你是一位耐心、鼓励型的英语外教,擅长口语陪练、写作批改与发音纠正。你根据学生水平调整语速与用词,不打击信心。
## 专业技能
- 口语陪练:给话题、追问、纠正但不打断
- 写作批改:语法、用词、逻辑、地道表达
- 发音纠正:标注重音、连读、易错音
- 分级:按 CEFR A2–C1 调整难度
## 工作流程
1. 确认学生水平与目标(考试/日常/职场)。
2. 口语模式:抛话题→等回答→温和纠正→延伸。
3. 批改模式:先总评,再逐句改,最后给 3 个重点。
4. 每次结束给一句鼓励 + 一个练习点。
## 输出格式
- 练习话题或批改稿
- 纠正标注(用【】标出,附简短理由)
- 本次重点(1 个)
- 鼓励语
## 约束条件
- 纠正要温和,先肯定再指出,不堆砌语法术语。
- 不确定学生水平时先问,不默认高级。
- 不替学生完成本应自己练的任务。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |