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 · 23 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal：Pending · OpenClaw ：良性
Package：52yuanchangxing/skill-smoke-test-author
安全扫描（ClawHub）
- VirusTotal：Pending
- OpenClaw ：良性
OpenClaw 评估
The skill's files, instructions, and required resources are consistent with its stated purpose (generating smoke-test templates and doing local audits); it doesn't request credentials or perform network calls, but it does read local files so you should avoid pointing it at sensitive system paths.
目的
Name/description match the included resources and code: the repo contains a template, spec, examples, tests, and a Python script that generates structured reports and audits. Requiring only python3 is proportionate to this functionality.
说明范围
SKILL.md instructs running the bundled scripts or generating output from bundled templates. The included script reads arbitrary files/directories you point it at (files under the given input path), lists and samples textual files, and emits findings. That behavior fits an auditing/smoke-test tool, but it means the skill can read any local files you give it (so do not pass sensitive system directories or files).
安装机制
No install spec and only a python3 requirement; the skill is instruction-only with a local script. No network downloads or third-party package installs are present.
证书
No environment variables, credentials, or config paths are requested. The script only uses local filesystem access, standard library modules, and input arguments — proportional to the stated purpose.
持久
always is false and the skill does not request any persistent platform privileges. It can be invoked by the model (normal for skills), but it doesn't modify other skills or global configuration.
综合结论
This skill is coherent with its stated purpose and appears safe to inspect or run on non-sensitive project directories. Before running: (1) avoid pointing the script at home (/home), root (/), or other system directories that may contain secrets; run it only against the project or a checked-out workspace. (2) Use the --dry-run option or redirect output to files you can audit. (3) Review generated output for any accidental inclusion of secrets …
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「Skill Smoke Test Author」。简介：自动为 Skill 生成 smoke test 模板，覆盖依赖缺失、空输入和标准路径。；use for skills, testing, smoke-test…。
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/skill-smoke-test-author/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: skill-smoke-test-author
version: 1.0.0
description: "自动为 Skill 生成 smoke test 模板，覆盖依赖缺失、空输入和标准路径。；use for skills, testing, smoke-test workflows；do not use for 写无法执行的测试, 忽略失败路径."
author: OpenClaw Skill Bundle
homepage: https://example.invalid/skills/skill-smoke-test-author
tags: [skills, testing, smoke-test, qa]
user-invocable: true
metadata: {"openclaw":{"emoji":"🧪","requires":{"bins":["python3"]},"os":["darwin","linux","win32"]}}
---
# Skill 冒烟测试作者
## 你是什么
你是“Skill 冒烟测试作者”这个独立 Skill，负责：自动为 Skill 生成 smoke test 模板，覆盖依赖缺失、空输入和标准路径。
## Routing
### 适合使用的情况
- 为这个 skill 写一份 smoke test
- 覆盖依赖缺失和空输入
- 输入通常包含：skill 功能描述、依赖、脚本入口
- 优先产出：测试范围、正常路径、回归建议
### 不适合使用的情况
- 不要写无法执行的测试
- 不要忽略失败路径
- 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：
- 测试范围
- 正常路径
- 依赖缺失路径
- 空输入路径
- 输出校验
- 回归建议
## 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
- 输出为 Markdown 测试模板。
- 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。