可用性测试
100 / 100 · Low risk
Fine to try.
产品设计套件 Validate 阶段。当用户是设计师想做可用性测试(验证已有设计或原型是否好用)—— 从测试方案设计、任务剧本编写、现场观察记录、到严重度评级与修复优先级输出时启动的 Skill。与 Probe(探索性用研,设计前)形成阶段互补 —— Probe 挖"用户是谁、为什么",Test 验"这个设计能不能用、卡在哪"。与 Check(设计师自查走查)的区别:Check 不需要真实用户,Test 必须真实用户操作。 本 Skill 覆盖可用性测试三阶段全流程:① Plan(测试目的 / 类型选择 / 招募 / 环境 / 设备)→ ② Script(3-7 个任务剧本 + 主持人脚本 + Think-Aloud 协议 + 反偏见提示)→ ③ Analyze(任务级数据汇总 / Nielsen 0-4 级严重度评级 / 频次矩阵 / 修复优先级 / 设计回流建议)。核心差异化:每条 finding 都附"任务 ID + 严重度 + 频次 + 原话 + 截图时间戳 + 建议修复方向"的证据链;输出 task_success_rate 等量化基线,直接喂给 Metric 做上线后对照…
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'test' ] || [ -L ~/.agents/skills/'test' ]; then echo 'A skill folder named test already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/ahang1598/doubao-workbuddy-qwenwork-skills' "$d" && git -C "$d" checkout --quiet '5e45653f59a2e4a2a65f575e8aaf7637165674d5' -- 'qwenwork/experts/product-design/skills/test' && mkdir -p ~/.agents/skills && cp -R "$d"/'qwenwork/experts/product-design/skills/test' ~/.agents/skills/'test' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'test' ~/.claude/skills/'test' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/ahang1598/doubao-workbuddy-qwenwork-skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | 5e45653 | 100 |