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 · 24 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：52yuanchangxing/qa-scenario-synthesizer
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 (synthesizing QA/test scenarios); it only needs python3 and works on local files, but you should avoid pointing it at sensitive directories/files without review.
目的
Name/description, SKILL.md, resources, and scripts all align: a local, read-only-focused QA/test-scenario generator and local audit helper. Declared requirement (python3) matches the bundled Python script; no unrelated cloud credentials, binaries, or config paths are requested.
说明范围
Runtime instructions limit behavior to producing structured text and optionally running scripts/run.py. The script reads provided files/directories (including .py/.sh/.json/.md) to generate reports and pattern scans. This is expected for an auditing/generation tool, but means you should not point the skill at directories containing secrets or other sensitive files because it will read and may include snippets in outputs.
安装机制
Instruction-only install (no remote download). The bundle includes a local Python script and resource files; there is no installer that fetches code from external URLs or executes remote archives.
证书
The skill requests no environment variables or credentials. Its functionality is consistent with this: it operates on local input files and templates only.
持久
always is false, the skill does not request permanent/force-installed presence, and it does not modify other skills or global agent configuration. It may write requested output files (as expected) but otherwise has no elevated privileges.
综合结论
This skill appears to be what it says: a local QA/test-scenario synthesizer that uses a bundled Python script. Before running: (1) review scripts/run.py if you have concerns; (2) avoid pointing --input at directories containing secrets, private keys, or unrelated configs because the tool will read files and may include snippets in output; (3) run with --dry-run or point it at a copy of your data first; (4) if you plan to let an agent invoke th…
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「Qa Scenario Synthesizer」。简介：把需求拆成功能、异常、跨端、脏输入和恢复场景测试集。；use for qa, test-scenarios, edge-cases workflows；do …。
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/qa-scenario-synthesizer/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: qa-scenario-synthesizer
version: 1.0.0
description: "把需求拆成功能、异常、跨端、脏输入和恢复场景测试集。；use for qa, test-scenarios, edge-cases workflows；do not use for 宣称已经完成测试, 忽略关键用户路径."
author: OpenClaw Skill Bundle
homepage: https://example.invalid/skills/qa-scenario-synthesizer
tags: [qa, test-scenarios, edge-cases, quality]
user-invocable: true
metadata: {"openclaw":{"emoji":"🧷","requires":{"bins":["python3"]},"os":["darwin","linux","win32"]}}
---
# 测试场景合成器
## 你是什么
你是“测试场景合成器”这个独立 Skill，负责：把需求拆成功能、异常、跨端、脏输入和恢复场景测试集。
## Routing
### 适合使用的情况
- 根据需求生成测试场景
- 补边界和异常路径
- 输入通常包含：需求规格、用户流程、限制条件
- 优先产出：主流程场景、异常场景、优先级
### 不适合使用的情况
- 不要宣称已经完成测试
- 不要忽略关键用户路径
- 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：
- 主流程场景
- 异常场景
- 跨端场景
- 脏输入场景
- 恢复与重试
- 优先级
## 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
- 场景生成服务于人工测试设计。
- 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。