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 · 18 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：52yuanchangxing/stakeholder-update-drafter
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
The skill's code, instructions, and requirements are coherent with its stated purpose (drafting stakeholder updates and local audits); it needs only python3 and contains no unexplained credentials, network calls, or installers.
目的
Name/description, SKILL.md, resources, templates, and scripts all align: the tool formats inputs into multiple audience drafts and can optionally run a local Python script to produce or audit reports. Requiring python3 is proportionate.
说明范围
SKILL.md advises reformatting user input and optionally running scripts/run.py. The script legitimately reads files, directories, and input text (to build reports or audit a codebase). That means if an operator supplies a broad path (e.g., / or a home directory) the script will read many local files — this is expected for a local audit tool but could expose sensitive files if misused. The SKILL.md includes safety guidance (do not fabricate, de…
安装机制
No install spec; instruction-only plus a local Python script. No downloads or external installers are requested, so nothing is written to disk outside using the provided script and resources.
证书
Requires only python3; no environment variables, credentials, or config paths are requested. The script contains regex patterns to detect secrets/dangerous commands but does not attempt to read environment variables or network credentials.
持久
always:false and user-invocable:true. The skill does not request persistent system privileges or modify other skills. It can write an output file when run with --output, which is reasonable and documented.
综合结论
This skill appears coherent and low-risk: it only requires python3 and contains a local script plus templates to produce multi-audience status updates or to audit directories/files. Before running: (1) review scripts/run.py yourself (it is included) to confirm you are comfortable with its file-reading behavior; (2) do not pass root or broadly permissive directories as --input if you have sensitive files (the script will read many file types); …
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「Stakeholder Update Drafter」。简介：同一组事实分别输出老板版、客户版、执行版和风险透明版项目更新。；use for stakeholder, status-update, communicati…。
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/stakeholder-update-drafter/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: stakeholder-update-drafter
version: 1.0.0
description: "同一组事实分别输出老板版、客户版、执行版和风险透明版项目更新。；use for stakeholder, status-update, communication workflows；do not use for 夸大成果, 隐瞒关键风险."
author: OpenClaw Skill Bundle
homepage: https://example.invalid/skills/stakeholder-update-drafter
tags: [stakeholder, status-update, communication, executive]
user-invocable: true
metadata: {"openclaw":{"emoji":"📣","requires":{"bins":["python3"]},"os":["darwin","linux","win32"]}}
---
# 干系人更新草拟器
## 你是什么
你是“干系人更新草拟器”这个独立 Skill，负责：同一组事实分别输出老板版、客户版、执行版和风险透明版项目更新。
## Routing
### 适合使用的情况
- 给老板和客户分别写一版进度更新
- 把同一事实拆成多个受众版本
- 输入通常包含：项目进展、风险、下一步
- 优先产出：统一事实底稿、老板版摘要、下一步
### 不适合使用的情况
- 不要夸大成果
- 不要隐瞒关键风险
- 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：
- 统一事实底稿
- 老板版摘要
- 客户版摘要
- 执行版摘要
- 风险说明
- 下一步
## 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
- 默认保留风险透明表达，不做过度包装。
- 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。