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-user-segmentationgit 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-user-segmentation)<a href="https://agentmods.dev/skills/guofu-shiqu/ux-expert-skills/exp-user-segmentation"><img src="https://agentmods.dev/badge/skills/guofu-shiqu/ux-expert-skills/exp-user-segmentation/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-user-segmentation"><img src="https://agentmods.dev/badge/skills/guofu-shiqu/ux-expert-skills/exp-user-segmentation.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 | $0.00041 | $0.01074 |
| Opus 5 | $0.00020 | $0.00537 |
| Sonnet 5 | $0.00008 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
exp-user-segmentation 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.
What it actually says
用户分群与分层
基于用户特征、行为、需求和体验目标，将用户划分为有共性的群体，为每个群体设计差异化的体验策略。
触发条件
- 需要基于体验需求对用户进行分群
- 需要设计差异化体验策略
- 需要建立用户分层运营体系
- 用户群体差异大，需要精准定位
- 需要为不同群体设计不同的旅程
核心能力
1. 分群维度选择
根据体验目标选择合适的分群维度：
| 分群维度 | 数据来源 | 适用场景 | 体验策略意义 |
|---|---|---|---|
| 行为分群 | 使用频率、功能偏好、操作路径 | 精细化运营 | 不同行为偏好的体验设计 |
| 需求分群 | JTBD、任务目标、痛点 | 产品设计 | 不同需求的核心体验差异 |
| 能力分群 | 数字素养、领域知识 | 交互设计 | 不同能力水平的引导深度 |
| 生命周期分群 | 注册时间、使用阶段 | 全生命周期体验 | 不同阶段的核心体验目标 |
| RFM 分群 | 最近使用、频率、金额 | 商业化运营 | 高价值用户的体验保障 |
| 场景分群 | 使用场景、设备环境 | 场景化设计 | 不同场景的体验适配 |
| 态度分群 | NPS分组（推荐者/中立者/贬损者） | 忠诚度管理 | 不同态度群体的体验差异 |
2. 分群方法
数据驱动分群（推荐）
- 收集多维度用户数据
- 使用聚类算法（K-Means、层次聚类）识别群体
- 为每个群体赋予语义化标签
- 验证群体稳定性
人工分群
- 基于用户画像和 JTBD
- 团队讨论识别共性群体
- 适用于数据不充分阶段
3. 群体画像构建
为每个分群构建完整的体验画像：
- 群体名称和描述
- 群体规模（占比）
- 核心 JTBD
- 体验偏好和痛点
- 典型使用场景
- 旅程特征差异
4. 差异化体验策略
为每个群体设计差异化的体验策略：
- 核心流程的差异（简化/引导/定制）
- 信息呈现的差异（精简/详细/专业）
- 触达方式的差异（时机/渠道/内容）
- 支持方式的差异（自助/引导/人工）
输出格式：用户分群报告
【用户分群报告】
▸ 分群目标：[...]
▸ 分群维度：[...]
▸ 数据来源：[...]
▸ 群体数量：[X 个]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ 群体 1：[名称]
规模：[XX% 用户]
描述：[一句话描述]
JTBD：
功能任务：[帮我...]
情绪任务：[让我感到...]
体验偏好：
[偏好1]
[偏好2]
核心痛点：
[痛点1]
[痛点2]
典型场景：
[场景1]
[场景2]
旅程特征：
[与整体旅程的主要差异]
差异化体验策略：
流程：[...]
信息：[...]
触达：[...]
支持：[...]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ 群体 2：[...]
▸ 群体 3：[...]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
▸ 跨群体共性需求：
1. [...]
2. [...]
▸ 体验资源分配建议：
群体1（[XX%]）：[资源分配建议]
群体2（[XX%]）：[资源分配建议]
...
▸ 指标监测：
各群体的：[CSAT/NPS/CES/转化率/留存率]
使用方法
当需要为不同用户群体设计差异化体验时调用本 skill。分群结果可与旅程分析、场景化营销、体验编排等 skill 衔接，为每个群体设计针对性的体验方案。
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 · 130 lines · 41 tokens per session scan A 691666c4a9cb
exp-user-segmentation is a skill published in the GitHub repository guofu-shiqu/ux-expert-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 1,074 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…