Token导航 LogoToken导航

Agent Skill · 研究检索

customer-persona-copy-map(客户角色复制图)

customer-persona-copy-map 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

customer-persona-copy-map 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为只读;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 38,524。

总安装 1,548周安装 62GitHub Stars 1下载 501核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:customer-persona-copy-map(客户角色复制图)
来源仓库:https://github.com/harrylabsj/customer-persona-copy-map
安装命令:
openclaw skills install customer-persona-copy-map
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install customer-persona-copy-map

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

将受众研究转化为详细的文案矩阵,关联客户角色与定制化营销语言。适合市场文案策划、广告素材生成和用户沟通策略制定。自动匹配痛点、利益点和行动号召话术,并提供证据支持。需用户提供真实客户画像资料,避免虚构受众特征。customer-persona-copy-map 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install customer-persona-copy-map;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

customer-persona-copy-map 怎么安装?

在终端执行 openclaw skills install customer-persona-copy-map。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

customer-persona-copy-map 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

customer-persona-copy-map 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

customer-persona-copy-map 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

customer-persona-copy-map 用的人多吗?

公开数据是累计安装 1,548 次,近一周安装 62 次,下载 501 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

customer-persona-copy-map 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
customer-persona-copy-map

客户角色复制图 · 本页

1,5481只读MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Customer Persona Copy Map

Purpose

This skill turns audience research and customer signals into a practical copy matrix that maps different personas to their specific pain points, motivations, objections, preferred benefits, and CTA language. Instead of one-size-fits-all copy, it helps teams segment messaging across product pages, ad creative, email flows, and landing pages — all while clearly labeling what's evidence-based vs. assumed.

Triggers

  • "Map copy to different customer personas"
  • "Create persona-based messaging for my product"
  • "Build a copy matrix for audience segments"
  • "Segment my product messaging by buyer type"
  • "Write persona-specific ad copy"
  • "Create messaging for different customer types"

Workflow

  1. Audience signal collection — Gather known customer segments, demographic/behavioral signals, purchase data patterns (if available), review themes by customer type, support ticket themes, and any existing persona research.
  2. Evidence vs. assumption separation — For each persona, clearly separate: what data supports this segment (reviews, sales data, survey results) vs. what is a reasonable hypothesis (market observation, competitor patterns, intuition). Assumptions must be labeled.
  3. Persona card creation — For each distinct persona, create a card with: name/descriptor, primary need/job-to-be-done, dominant purchase barrier, emotional driver, trust requirement, and preferred channel.
  4. Pain-benefit-message matrix — Create a cross-reference matrix: persona → top pain points → product benefits that address them → message framing → CTA language → best channel.
  5. Copy snippet drafting — Write persona-specific copy snippets: above-the-fold headline, key benefit statement, objection pre-handler, and CTA. Each snippet should feel natural for that persona.
  6. Channel recommendation — For each persona-message pair, recommend the best channel(s) and format (e.g., "gift-buyer persona → Instagram Story with gift-guide angle").

Prompt Templates

1. Persona Copy Matrix Builder (persona_matrix)

Purpose: Build a complete persona-to-copy matrix from audience data.

Input:

  • ${product_name} — Product name
  • ${product_category} — Product category
  • ${personas} — List of customer persona descriptions (2–5 personas)
  • ${product_benefits} — Key product benefits
  • ${channels} — Available marketing channels
  • ${evidence_sources} — (Optional) data sources supporting persona definitions

Output: Complete matrix with persona cards, pain/benefit/message map, copy snippets, and channel recommendations.

2. Persona Expander (persona_expand)

Purpose: Expand a thin persona description into a full messaging profile.

Input:

  • ${persona_name} — Persona name or descriptor
  • ${known_traits} — What's known about this persona
  • ${product_context} — What this product does for them

Output: Expanded persona card with messaging angles, objections, and copy snippet drafts.

3. Message Adapter (message_adapt)

Purpose: Adapt one core message to multiple persona framings.

Input:

  • ${core_message} — The central product message
  • ${personas} — List of personas with key motivations
  • ${channels} — Target channels for adaptation

Output: Persona-specific message adaptations with rationale for changes.

4. Assumption Auditor (assumption_audit)

Purpose: Audit a persona set for untested assumptions that could lead to wasted spend.

Input:

  • ${persona_set} — Complete persona definitions with messaging
  • ${evidence_available} — What data actually supports each persona

Output: Each persona scored by evidence strength (High/Medium/Low), with assumptions highlighted and test recommendations for low-evidence personas.

Output Format

## Persona Copy Map: [Product Name]
**Category:** [Category] | **Personas:** [N personas]

### Persona Cards

**Persona 1: [Name/Descriptor]**
- **Primary Need:** [Job-to-be-done]
- **Dominant Barrier:** [What keeps them from buying]
- **Emotional Driver:** [What feeling motivates them]
- **Trust Requirement:** [What proof they need]
- **Preferred Channel:** [Where they're most reachable]
- **Evidence Strength:** [High/Medium/Low] — [what data supports this]

**Persona 2: [...]**
...

### Pain-Benefit-Message Matrix

| Persona | Top Pain | Product Benefit | Message Frame | CTA Language | Best Channel |
|---|---|---|---|---|---|
| Persona 1 | [Pain] | [Benefit] | [How to frame] | "[CTA]" | [Channel] |
| Persona 2 | [Pain] | [Benefit] | [How to frame] | "[CTA]" | [Channel] |
| ... | ... | ... | ... | ... | ... |

### Copy Snippets

**For [Persona 1]:**
- 🎯 Headline: "[Above-the-fold headline]"
- 💡 Benefit: "[Key benefit statement]"
- 🛡️ Objection handler: "[Pre-handle common objection]"
- 🚀 CTA: "[Call to action]"

**For [Persona 2]:**
...

### Channel Recommendations
- **[Channel]:** Best for personas [X, Y] — format: [suggestion]
- **[Channel]:** Best for persona [Z] — format: [suggestion]

### Assumption Audit
- ✅ Persona 1: [Evidence strength] — supported by [sources]
- ⚠️ Persona 2: Medium evidence — [assumptions] need validation via [test idea]
- ❓ Persona 3: Low evidence — consider deprioritizing until [validation method]

Safety Rules

  • ALWAYS clearly label assumptions vs. evidence — unvalidated personas can waste budget and alienate real customers
  • NEVER stereotype based on protected characteristics (age, gender, race, religion, disability, sexual orientation) when the data doesn't support it
  • NEVER create personas for sensitive categories (health conditions, financial distress, personal crises) without extreme care and explicit disclosure of limitations
  • ALWAYS avoid manipulative messaging that exploits persona vulnerabilities (e.g., insecurity-based marketing to teens, fear-based messaging to elderly)
  • NEVER present assumed personas as "proven by AI" — clearly state the evidence basis for every segment

Examples

Example 1: Skincare Serum (3 Personas)

Input: Product="Vitamin C Brightening Serum", Personas="(1) Skincare Beginner — wants results without complexity, (2) Ingredient Nerd — researches every component, (3) Gift Buyer — buying for someone else, wants safe choice"

Output: Matrix showing: Beginner → pain="too many choices, don't know what works" → message="One serum, proven ingredients, simple routine" → CTA="Start your 2-step routine" → channel=Instagram/TikTok. Ingredient Nerd → pain="skeptical of marketing claims" → message="15% L-AA + E + ferulic, airless pump, dermatologist-tested — here's the data" → CTA="See the full ingredient breakdown" → channel=blog/email. Gift Buyer → pain="will they like it? will it work for their skin?" → message="Universally loved, fragrance-free, suitable for most skin types, beautiful packaging" → CTA="Gift the glow" → channel=Facebook/Instagram.

Example 2: Kitchen Gadget (2 Personas)

Input: Product="Air Fryer Liners", Personas="(1) Convenience Cook — wants faster cleanup, (2) Eco-Conscious Cook — wants to reduce waste (aluminum foil/paper)"

Output: Matrix: Convenience → pain="air fryer cleanup is annoying" → message="Cook, eat, toss the liner — no scrubbing" → CTA="Make cleanup optional" → channel=TikTok. Eco-Conscious → pain="using disposable foil/paper feels wasteful" → message="Reusable silicone liners replace hundreds of foil sheets" → CTA="Cook cleaner, waste less" → channel=Instagram/blog. Assumption audit flags that "Eco-Conscious" is partially assumed — recommended survey validation.

Related Skills

平台分布

OpenClaw

90.3%
按下载量换算452

安全审计

VirusTotal

未展示

ClawScan

通过

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills