executing-plans
executing-plans
Use 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
lov-thesis-polishPolish and elevate MBA thesis / dissertation to national outstanding thesis quality (全国优秀论文). Performs comprehensive improvement: academic language, argument structure, logical rigor, innovation highlights, and formatting. Input: markdown thesis text. Output: polished full text. Also trigger when the user mentions "论文润色", "MBA论文", "优秀论文", "thesis polish", "…
Independent GitHub snapshot · Automated classification · Original documentation governs
name: lov-thesis-polish category: Content Processing tagline: "MBA 论文全面润色,对标全国优秀论文标准。语言+结构+论证+创新四维提升。" description: > Polish and elevate MBA thesis / dissertation to national outstanding thesis quality (全国优秀论文). Performs comprehensive improvement: academic language, argument structure, logical rigor, innovation highlights, and formatting. Input: markdown thesis text. Output: polished full text. Also trigger when the user mentions "论文润色", "MBA论文", "优秀论文", "thesis polish", "dissertation improvement", "学术润色". license: MIT compatibility: > Pure instructions — no dependencies. Works with any Claude model. depends_on:
将 MBA 论文从初稿提升至全国优秀论文水准。涵盖语言润色、结构优化、论证强化、创新点凸显四个维度。
读取用户提供的论文文件(markdown 格式)。如果用户给的是文件路径,用 Read 工具读取。
通读全文后,先输出一份诊断报告(不超过 300 字),包含:
| 维度 | 当前水平 | 主要问题 | 提升方向 |
|---|---|---|---|
| 语言表达 | A/B/C | ... | ... |
| 论证逻辑 | A/B/C | ... | ... |
| 结构布局 | A/B/C | ... | ... |
| 创新贡献 | A/B/C | ... | ... |
| 文献运用 | A/B/C | ... | ... |
Use AskUserQuestion to confirm strategy BEFORE polishing.
向用户展示诊断报告后,询问:
按章节逐一润色,每章输出完整的润色后文本。润色时严格遵循以下标准:
将所有润色后的章节合并,输出完整的润色后全文(markdown 格式)。
如果用户需要保存为文件,使用 Write 工具写入,文件名遵循:
品牌方-mba-thesis-polished-{YYYY-MM-DD}-v0.1.md
[建议补充: ...] 标注运行前读取本 Skill 包的 skill.yaml,由宿主提供 skill-runtime/v1 上下文。字段解析顺序为:当前请求、项目上下文、个人 Preferences、品牌 Profile、通用默认值。
required: true 字段缺失时,按 Manifest 的问题配置向用户提出一个聚焦问题;用户明确同意后再保存回答。context_id、字段路径与来源,诊断内容避开秘密、完整私人路径和原始配置。用户在 Skill 驱动任务中提出修改意见时,继续当前产物前必须执行:
task-specific(仅本次)还是 reusable(可跨任务复用)。task-specific 只修改当前任务,不改 Skill。reusable 先确定作用域:领域规则先更新对应 canonical Skill;适用于所有 Skill 的规则先更新共享规范。reusable 修改会使此前的“确认”“继续”“发吧”失效;完成当前产物修改和回读后必须停下,等待用户下一步指示,不自动进入发布、提交或其他外部写入。