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-heuristic-evaluationgit 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-heuristic-evaluation)<a href="https://agentmods.dev/skills/guofu-shiqu/ux-expert-skills/exp-heuristic-evaluation"><img src="https://agentmods.dev/badge/skills/guofu-shiqu/ux-expert-skills/exp-heuristic-evaluation/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-heuristic-evaluation"><img src="https://agentmods.dev/badge/skills/guofu-shiqu/ux-expert-skills/exp-heuristic-evaluation.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 | $0.00040 | $0.01497 |
| Opus 5 | $0.00020 | $0.00749 |
| Sonnet 5 | $0.00008 | $0.00299 |
| Haiku 4.5 | $0.00004 | $0.00150 |
Grade A, and why
exp-heuristic-evaluation 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 12d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
启发式评估
基于 Nielsen 十大可用性原则、Shneiderman 八大黄金法则等业界成熟框架，系统性评估产品可用性，快速发现体验问题。
触发条件
- 需要快速评估产品可用性
- 专家资源有限，需要成本较低的评估方法
- 需要在用户测试前快速发现明显问题
- 需要建立标准化的可用性检查清单
- 需要向团队传达明确的可用性问题
核心能力
1. 评估框架选择
根据产品类型和评估目标，选择合适的启发式框架：
| 框架 | 原则数量 | 适用场景 | 特点 |
|---|---|---|---|
| Nielsen 十大原则 | 10 | 通用产品 | 最经典、最广泛认可 |
| Shneiderman 八大法则 | 8 | 交互界面 | 侧重交互设计 |
| ISO 9241-110 | 7 | 专业/工业软件 | 国际标准 |
| 移动端启发式 | 10+ | App/移动端 | 考虑移动特性 |
| 无障碍启发式 | 符合 WCAG | 无障碍产品 | 考虑障碍用户 |
| 自定义框架 | 按需 | 特定领域 | 结合行业特点 |
Nielsen 十大原则速查：
- 系统状态可见性 — 用户应随时知道系统正在做什么
- 系统与真实世界的匹配 — 使用用户语言而非系统语言
- 用户控制与自由 — 提供"紧急出口"（撤销、返回）
- 一致性与标准 — 遵循平台规范和内部一致性
- 防错 — 比良好的错误提示更好的是防止错误发生
- 识别而非回忆 — 让用户看到选项而非记住信息
- 使用的灵活性与效率 — 为新手和专家都提供路径
- 美观与极简设计 — 对话不应包含无关或低频信息
- 帮助用户识别、诊断并从错误中恢复 — 错误信息应说清问题并提供解决方案
- 帮助与文档 — 即使系统不需要文档，也应提供
2. 评估执行流程
- 准备阶段 — 明确评估范围、选择启发式框架、准备评估清单
- 独立评估 — 评估者独立走查，记录发现的问题
- 问题记录 — 为每个问题标注违反的原则、严重程度、影响范围
- 汇总会议 — 多名评估者汇总发现，去重和优先级排序
- 报告输出 — 输出结构化的评估报告
3. 问题记录格式
每个发现的问题应包含：
- 违反的原则 — 违反了哪条启发式原则
- 问题描述 — 具体描述问题
- 严重程度 — 0-4 分（0=无，4=致命）
- 影响范围 — 影响哪些用户/场景
- 修复建议 — 如何修复
4. 评估者数量建议
| 评估者数量 | 发现问题覆盖率 | 说明 |
|---|---|---|
| 1 名 | ~35% | 快速初评，易漏问题 |
| 3-5 名 | ~75% | 性价比最高 |
| 5+ 名 | >75% | 边际收益递减 |
建议 ≥3 名评估者，且评估者应包含：UX 专家、领域专家、新手用户。
输出格式：启发式评估报告
【启发式评估报告】
▸ 评估概况：
评估范围：[...]
评估框架：[Nielsen / Shneiderman / ISO / 自定义]
评估者：[X 名]，背景：[UX专家/领域专家/新手]
评估时间：[...]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ 一、问题总览
严重程度 │ 问题数 │ 占比
─────────┼────────┼──────
4-致命 │ X │ XX%
3-严重 │ X │ XX%
2-一般 │ X │ XX%
1-轻微 │ X │ XX%
0-提示 │ X │ XX%
─────────┼────────┼──────
合计 │ X │ 100%
未违反原则：[...]
高频违反原则：[...]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ 二、问题清单（按严重程度排序）
问题 #[X] [严重程度：X/4]
─────────────────────────────
违反原则：[原则名称]
问题描述：[...]
发生位置：[页面/流程/功能]
影响范围：[影响哪些用户/场景]
截图/描述：[...]
修复建议：[...]
修复成本：[高/中/低]
优先级：[P0/P1/P2/P3]
问题 #[X] [...]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ 三、按原则汇总
原则1：系统状态可见性
违反次数：[X]
主要问题：[...]
修复建议：[...]
原则2：系统与真实世界的匹配
...
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ 四、快速修复清单（P0 + P1）
1. [问题]，修复：[...]，预计：[X天]
2. [...]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ 五、附加评估
整体可用性评分：[X/100]（基于问题数量和严重程度估算）
主要优势：[...]
主要短板：[...]
建议下一步：[用户测试 / 专家评审 / 直接修复]
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.
- 12d ago First seen · 149 lines · 40 tokens per session scan A 2feeaad1f62d
exp-heuristic-evaluation is a skill published in the GitHub repository guofu-shiqu/ux-expert-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 1,497 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
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.
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
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…
imagegen-frontend-mobile
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured…
imagegen-frontend-web
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not…
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.