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-satisfaction-statsgit 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-satisfaction-stats)<a href="https://agentmods.dev/skills/guofu-shiqu/ux-expert-skills/exp-satisfaction-stats"><img src="https://agentmods.dev/badge/skills/guofu-shiqu/ux-expert-skills/exp-satisfaction-stats/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-satisfaction-stats"><img src="https://agentmods.dev/badge/skills/guofu-shiqu/ux-expert-skills/exp-satisfaction-stats.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 | $0.00038 | $0.02338 |
| Opus 5 | $0.00019 | $0.01169 |
| Sonnet 5 | $0.00008 | $0.00468 |
| Haiku 4.5 | $0.00004 | $0.00234 |
Grade A, and why
exp-satisfaction-stats 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
满意度统计与分析
对 CSAT、NPS、CES 等满意度指标进行统计计算、分组分析、趋势追踪和报告生成。
触发条件
- 需要计算 CSAT、NPS、CES 等满意度指标
- 需要生成满意度统计报告
- 需要进行满意度趋势分析
- 需要进行不同维度的满意度对比
- 需要设定满意度预警阈值
核心能力
1. CSAT（客户满意度）统计
定义： 衡量用户对特定任务、触点或体验的满意程度。
计算公式：
CSAT = （回答"满意"及"非常满意"的人数 ÷ 总回答人数）× 100%
标准 5 分制：
1 = 非常不满意
2 = 不满意
3 = 一般
4 = 满意
5 = 非常满意
→ CSAT = （4分和5分人数 ÷ 总人数）× 100%
适用场景： 任务完成后、服务结束后、功能使用后
关键分析维度：
- 整体 CSAT 得分
- 各分档占比分布（1-5 分各占多少）
- 按用户分层对比（新老用户/付费免费等）
- 按场景/触点对比
- 按时间趋势追踪
2. NPS（净推荐值）统计
定义： 衡量用户向他人推荐产品/服务的意愿，反映忠诚度。
计算公式：
NPS 分组（0-10 分）：
推荐者（9-10 分）：积极推荐的用户
中立者（7-8 分）：被动满意的用户
贬损者（0-6 分）：可能负面评价的用户
NPS = （推荐者占比 - 贬损者占比）× 100
= （推荐者人数 ÷ 总人数 × 100）- （贬损者人数 ÷ 总人数 × 100）
结果范围：-100 到 +100
适用场景： 整体产品体验、品牌体验、周期性追踪
关键分析维度：
- 整体 NPS 得分
- 三组占比分布（推荐者/中立者/贬损者）
- 按用户分层对比
- 按时间趋势追踪
- 贬损者原因分析（配合开放题）
- 推荐者特征分析（识别高价值用户特征）
NPS 基准参考：
| 行业 | 优秀 NPS | 平均 NPS |
|---|---|---|
| 互联网/SaaS | 50+ | 30 |
| 电商 | 45+ | 25 |
| 金融服务 | 40+ | 20 |
| 电信 | 30+ | 10 |
| 旅游/酒店 | 45+ | 30 |
3. CES（客户费力度）统计
定义： 衡量用户完成任务所花费的费力程度，反映体验的顺畅度。
计算公式：
CES 5 分制（正向）：
1 = 非常不同意（很费力）
2 = 不同意
3 = 一般
4 = 同意
5 = 非常同意（很不费力）
→ CES = 平均分（1-5 分）
或 CES 7 分制：
1 = 非常费力 → 7 = 非常不费力
→ CES = 平均分（1-7 分）
或 CES 百分比法：
CES = （选择"同意/非常同意"的人数 ÷ 总人数）× 100%
适用场景： 任务完成后、问题解决后、流程体验后
关键分析维度：
- 整体 CES 得分
- 各分档占比分布
- 按任务类型对比（不同任务的费力度差异）
- 按时间趋势追踪
- 高费力度任务识别（优先改善）
4. 综合分析框架
将 CSAT、NPS、CES 组合分析：
| 组合模式 | 解读 | 策略方向 |
|---|---|---|
| CSAT 高 + NPS 高 + CES 低 | 体验优秀，用户忠诚 | 保持优势，放大口碑 |
| CSAT 高 + NPS 低 + CES 低 | 满意但不忠诚 | 强化情感连接和差异化 |
| CSAT 低 + NPS 低 + CES 高 | 体验差且费力 | 紧急改善核心流程 |
| CSAT 低 + NPS 高 + CES 高 | 满意度低但忠诚 | 可能缺少替代品，有流失风险 |
| CSAT 高 + NPS 高 + CES 高 | 满意且忠诚但费力 | 优化效率，降低费力度 |
5. 统计显著性检验
在对比分析时，进行统计显著性检验：
- 样本量要求 — NPS 至少 100+ 样本，CSAT 至少 50+ 样本才有统计意义
- 置信区间 — 计算 95% 置信区间
- 显著性检验 — 两组对比时进行 Z 检验或 T 检验
- 效应量 — 评估差异的实际意义（Cohen's d）
6. 趋势追踪
建立满意度趋势追踪机制：
- 追踪频率 — 周/月/季度
- 趋势方向 — 上升/持平/下降
- 变化幅度 — 与上一周期对比
- 异常波动 — 识别突然下降并预警
- 归因分析 — 下降时分析可能原因
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 · 264 lines · 38 tokens per session scan A 0f333422f25e
exp-satisfaction-stats is a skill published in the GitHub repository guofu-shiqu/ux-expert-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 2,338 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
api-design
Design public interfaces for libraries and tools that other people depend on. Use when designing or reviewing a public API surface, deciding what to export, naming functions and CLI flags, adding configuration options, planning deprecations, or when the user asks "is this a good API" or "how do I change this without…
code-review
Review a pull request the way a good open-source maintainer does. Use when reviewing an incoming PR, when the user asks "review this PR" or "is this ready to merge", when triaging a stale PR queue, or when writing review feedback to an external contributor. Covers what to check and in what order, severity levels…
governance-and-sustainability
Keep a project and its maintainers alive over years. Use when deciding how decisions get made, writing GOVERNANCE.md or a code of conduct enforcement process, adding or removing maintainers, handling burnout or stepping away, setting up funding (GitHub Sponsors, Open Collective, a foundation), handling a fork or a…
open-source
Generates the complete open-source governance of a repository: README, LICENSE, REUSE.toml and SPDX headers, CONTRIBUTING, SECURITY, CODEOFCONDUCT, GOVERNANCE, CHANGELOG, .github issue/PR templates, GitHub Actions, Dependabot, conventional commits, GPG/DCO signing, git flow and ADRs. Use whenever the user wants to…
contributor-experience
Turn users into contributors and make their first PR succeed. Use when a project gets stars but no contributions, when first-time PRs stall or get abandoned, when writing or improving CONTRIBUTING.md, when setting up a dev environment that works on the first try, or when the user asks "how do I get contributors" or…
dependency-hygiene
Manage a project's dependencies so they stay small, current, and safe. Use when deciding whether to add a dependency, auditing an existing dependency tree, configuring Dependabot or Renovate, dealing with upgrade churn or a flood of bot PRs, resolving version conflicts, choosing between dependency ranges and pinning…