Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add guofu-shiqu/ux-expert-skills --skill exp-usability-testinggit clone --depth 1 https://github.com/guofu-shiqu/ux-expert-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/guofu-shiqu/ux-expert-skills/exp-usability-testing)<a href="https://agentmods.dev/skills/guofu-shiqu/ux-expert-skills/exp-usability-testing"><img src="https://agentmods.dev/badge/skills/guofu-shiqu/ux-expert-skills/exp-usability-testing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/guofu-shiqu/ux-expert-skills/exp-usability-testing"><img src="https://agentmods.dev/badge/skills/guofu-shiqu/ux-expert-skills/exp-usability-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.01727 |
| Opus 5 | $0.00017 | $0.00864 |
| Sonnet 5 | $0.00007 | $0.00345 |
| Haiku 4.5 | $0.00003 | $0.00173 |
Grade A, and why
exp-usability-testing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
可用性测试
设计可用性测试方案，包括测试类型选择、任务设计、测试脚本编写、执行方法和结果分析，发现用户实际使用中的体验问题。
触发条件
- 需要发现用户实际使用中的体验问题
- 需要验证设计改版是否真正改善体验
- 需要评估特定任务流程的可用性
- 需要在上线前进行可用性验证
- 需要对比新旧方案的体验差异
核心能力
1. 测试类型选择
| 测试类型 | 方法 | 适用阶段 | 目的 |
|---|---|---|---|
| 形成性可用性测试 | 小样本(5-8人)，定性为主 | 设计迭代阶段 | 发现问题、指导改进 |
| 总结性可用性测试 | 大样本(20+)，定量为主 | 上线后/版本对比 | 评估质量、基线对比 |
| 远程可用性测试 | 线上工具，异步或同步 | 地理分散用户 | 降低成本、扩大样本 |
| 眼动追踪测试 | 眼动仪记录注视点 | 视觉密集页面 | 了解视觉注意力分布 |
| A/B 测试 | 线上分流对比 | 上线后验证 | 验证方案效果 |
| 专家评审 | 专家走查 | 快速评估 | 快速发现明显问题 |
2. 测试任务设计
任务设计原则：
- 任务应基于真实用户目标，而非功能点
- 任务描述避免引导性语言
- 任务应有明确的完成标准
- 任务难度应覆盖核心场景
任务设计模板：
任务名称：[...]
场景描述：[给用户一个真实的生活化场景]
任务目标：[用户需要完成什么]
成功标准：[怎样算完成]
预计时长：[X 分钟]
关注点：[测试者要重点观察什么]
任务类型：
- 成功路径任务 — 测试用户能否顺利完成核心任务
- 探索任务 — 测试用户能否自主发现功能
- 错误恢复任务 — 测试用户能否从错误中恢复
- 边界任务 — 测试极端场景下的表现
3. 测试脚本结构
完整的测试脚本包含以下部分：
- 开场说明 — 研究目的、时长、隐私、鼓励发声思考
- 暖场问题 — 了解用户背景、使用习惯
- 前测问卷 — 收集用户属性和预期
- 测试任务 — 按顺序执行各任务
- 任务后评分 — 每个任务后让用户评分（SEQ 单题易用性量表）
- 整体评估 — SUS 量表或整体满意度
- 回顾访谈 — 询问困惑点、改进建议
- 结束语 — 感谢、后续跟进
4. 关键指标
过程指标：
- 任务完成率（Task Completion Rate）
- 任务时长（Time on Task）
- 错误次数（Number of Errors）
- 求助次数（Help Requests）
- 迷路次数（Lostness）
主观指标：
- SEQ（Single Ease Question）— "完成这个任务的难度是？" 1-7 分
- SUS（System Usability Scale）— 10 题标准量表
- ASQ（After-Scenario Questionnaire）— 场景后满意度
- NPS — 净推荐值
行为指标：
- 首次点击正确率
- 回退次数
- 停滞时间（犹豫）
- 非预期路径
5. 结果分析方法
问题分类：
| 严重程度 | 定义 | 处理优先级 |
|---|---|---|
| 致命（P0） | 用户完全无法完成任务 | 立即修复 |
| 严重（P1） | 用户花费大量时间或多次出错 | 本版本修复 |
| 一般（P2） | 用户有困惑但最终完成 | 下版本优化 |
| 轻微（P3） | 小的体验摩擦 | 放入优化池 |
输出格式：可用性测试方案 + 结果报告
测试方案
【可用性测试方案】
▸ 测试目标：[...]
▸ 测试类型：[形成性/总结性/远程/眼动/A-B/专家评审]
▸ 测试对象：[用户描述]，样本量：[X人]
▸ 测试环境：[实验室/远程/线上]
▸ 任务清单：
任务1：[名称]，场景：[...]，成功标准：[...]，预计：[X分钟]
任务2：[...]
...
▸ 测试脚本：[完整脚本]
▸ 评分量表：[SEQ / SUS / ASQ / NPS]
▸ 预计总时长：[X分钟/人]
结果报告
【可用性测试结果报告】
▸ 测试概况：
参与人数：[X]
测试时间：[...]
测试版本：[...]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ 一、关键指标
任务 │ 完成率 │ 平均时长 │ 错误次数 │ SEQ均值 │ 严重程度
─────────┼────────┼──────────┼──────────┼─────────┼─────────
任务1 │ XX% │ X分XX秒 │ X.X │ X.X │ [...]
任务2 │ XX% │ X分XX秒 │ X.X │ X.X │ [...]
...
整体 │ XX% │ X分XX秒 │ X.X │ X.X │
SUS 得分：[XX.X]/100（[优秀/良好/一般/差]）
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ 二、问题清单
P0 致命问题：
1. [问题描述]，出现频次：[X/X]，发生环节：[...]
原因分析：[...]
修复建议：[...]
P1 严重问题：
1. [...]
P2 一般问题：
1. [...]
P3 轻微问题：
1. [...]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ 三、用户行为洞察
典型路径：[...]
迷路热点：[...]
犹豫时刻：[...]
意外发现：[...]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ 四、用户原声
正面："[用户原话]"
负面："[用户原话]"
建议："[用户原话]"
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ 五、改版建议
必须修复：
1. [...]
建议优化：
1. [...]
验证建议：
[修复后应再次测试哪些任务]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 194 lines · 34 tokens per session scan A b08b136cd344
exp-usability-testing is a skill published in the GitHub repository guofu-shiqu/ux-expert-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 1,727 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
testing-strategy
Design a test suite for an open-source project that contributors can actually run and trust. Use when a project has no tests, when the suite is slow or flaky, when deciding what to test and at what level, when setting a coverage policy, or when contributors' PRs keep failing CI for unrelated reasons. Covers the test…
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
minimalist-ui
Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.