技能详情（站内镜像，无评论）
作者：vx：17605205782 @52YuanChangXing
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 0 · 36 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：52yuanchangxing/follow-up-commander
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
The skill's code, instructions, and requirements align with its stated purpose (generating structured follow-up items and drafts); it only requires python3 and contains a local script that reads local inputs to produce text outputs.
目的
Name/description (follow-up, meeting, email workflows) match the provided resources and the included Python script. Requiring python3 and bundling a local script/resources is proportionate to producing structured reports, templates, and draft emails.
说明范围
SKILL.md confines behavior to generating text and advises not to send emails or fake statuses. It permits running scripts when the environment allows (python3 scripts/run.py). The bundled script accepts files or directories and can scan many text file types; this is reasonable for producing structured summaries but does allow the agent (when instructed to run the script) to read arbitrary files beneath the provided input path. Recommend avoidi…
安装机制
No install spec; instruction-only plus a local Python script. This is low risk — no network downloads or external package installation are performed by the skill.
证书
The skill requests no environment variables or credentials, which matches its purpose. However, the script includes pattern scanning (including a 'secret_like' regex) and can read workspace files; if you point it at directories containing secrets or credentials it may surface them in reports. The skill itself does not request credentials.
持久
always is false and the skill does not request persistent system-level privileges or modify other skills. The script can write output files (normal for a reporting tool) but does not alter system-wide config or enable permanent background behavior.
综合结论
This skill appears to do what it claims: generate structured follow-up checklists, owner mappings, and draft emails using a local Python script. Before installing or running it, review the scripts/run.py file (already included) and only invoke the script on intended input files or a dedicated project directory — do not point it at system directories or repositories that contain secrets (API keys, tokens, passwords). If you want extra caution, …
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Follow Up Commander」。简介：把会后事项拆成行动清单、催办节奏、邮件草稿和下次同步议题。；use for followup, meeting, email workflows；do not…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/52yuanchangxing/follow-up-commander/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: follow-up-commander
version: 1.0.0
description: "把会后事项拆成行动清单、催办节奏、邮件草稿和下次同步议题。；use for followup, meeting, email workflows；do not use for 直接发送邮件, 伪造完成状态."
author: OpenClaw Skill Bundle
homepage: https://example.invalid/skills/follow-up-commander
tags: [followup, meeting, email, action-items]
user-invocable: true
metadata: {"openclaw":{"emoji":"📨","requires":{"bins":["python3"]},"os":["darwin","linux","win32"]}}
---
# 会后跟进指挥官
## 你是什么
你是“会后跟进指挥官”这个独立 Skill，负责：把会后事项拆成行动清单、催办节奏、邮件草稿和下次同步议题。
## Routing
### 适合使用的情况
- 把会后事项整理成行动清单和邮件草稿
- 按负责人拆分 follow-up
- 输入通常包含：会议纪要、参与角色、优先级
- 优先产出：行动清单、负责人映射、未决问题
### 不适合使用的情况
- 不要用来直接发送邮件
- 不要用来伪造完成状态
- 如果用户想直接执行外部系统写入、发送、删除、发布、变更配置，先明确边界，再只给审阅版内容或 dry-run 方案。
## 工作规则
1. 先把用户提供的信息重组成任务书，再输出结构化结果。
2. 缺信息时，优先显式列出“待确认项”，而不是直接编造。
3. 默认先给“可审阅草案”，再给“可执行清单”。
4. 遇到高风险、隐私、权限或合规问题，必须加上边界说明。
5. 如运行环境允许 shell / exec，可使用：
- `python3 "{baseDir}/scripts/run.py" --input <输入文件> --output <输出文件>`
6. 如当前环境不能执行脚本，仍要基于 `{baseDir}/resources/template.md` 与 `{baseDir}/resources/spec.json` 的结构直接产出文本。
## 标准输出结构
请尽量按以下结构组织结果：
- 行动清单
- 负责人映射
- 建议邮件草稿
- 升级与催办规则
- 下次同步议题
- 未决问题
## 本地资源
- 规范文件：`{baseDir}/resources/spec.json`
- 输出模板：`{baseDir}/resources/template.md`
- 示例输入输出：`{baseDir}/examples/`
- 冒烟测试：`{baseDir}/tests/smoke-test.md`
## 安全边界
- 默认只生成文本，不直接调用外部邮箱。
- 默认只读、可审计、可回滚。
- 不执行高风险命令，不隐藏依赖，不伪造事实或结果。