用户研究
100 / 100 · Low risk
Fine to try.
产品设计套件深挖工具。当用户是设计师想主动做用户研究(访谈 / 可用性测试 / 调研)—— 从规划研究问题、设计访谈大纲、到访谈后做主题归纳与洞察提炼时启动的 Skill。与 Signal(被动整理工单 / 评论)形成互补 —— Probe 是主动深挖少量样本(5-8 人深访),Signal 是被动整理海量样本(100-1000+ 条反馈)。 本 Skill 覆盖用户研究的三阶段全流程:① Plan(研究目标 / 方法选择 / 招募标准 / 时间表)→ ② Conduct(访谈大纲 5 段式 / 探针问题 / 反偏见提示)→ ③ Synthesize(亲和图法主题归纳 / JTBD 提炼 / 情感曲线 / 用户分层 / 洞察转设计机会)。核心差异化:每条洞察都附原话引用 + 情感强度 + 出现频次的证据链,下游 Brief / Journey / HMW 都能直接消费;并主动建议"哪些洞察该跑 Signal 做大样本验证"。x 支持 6 种研究方法(访谈 / 可用性测试 / 调研 / 卡片分类 / 日记研究 / A/B 测试),按"问题类型 + 时间预算 + 样本可获得性"匹配。 触…
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/'probe' ] || [ -L ~/.agents/skills/'probe' ]; then echo 'A skill folder named probe 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 "$d" checkout --quiet '5e45653f59a2e4a2a65f575e8aaf7637165674d5' -- 'qwenwork/experts/product-design/skills/probe' && mkdir -p ~/.agents/skills && cp -R "$d"/'qwenwork/experts/product-design/skills/probe' ~/.agents/skills/'probe' && 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/'probe' ~/.claude/skills/'probe' (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 |