Token导航 LogoToken导航

Agent Skill · 研究检索

customer-story-builder(客户故事构建者)

customer-story-builder 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 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-story-builder 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,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 68,884。

总安装 222周安装 9GitHub Stars 607下载 70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
unknown

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-story-builder(客户故事构建者)
来源仓库:https://github.com/athina-ai/goose-skills
仓库路径:skills/customer-story-builder
安装命令:
npx skills add https://github.com/athina-ai/goose-skills --skill customer-story-builder
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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/athina-ai/goose-skills --skill customer-story-builder

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。

客户故事构建者将原始客户反馈转化为案例研究、社交媒体素材与演示文稿。适用于营销传播、销售支持与产品验证场景,提炼真实用户价值证明。支持从 Slack 对话、支持工单中提取素材并自动生成多格式输出。采用结构化叙事框架突出挑战、解决方案与量化成果。需注意隐私合规,确保使用公开授权或脱敏后的客户内容。

来源仓库内路径:skills/customer-story-builder

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 Codex、Claude、Cursor、Gemini CLI;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 npx skills add https://github.com/athina-ai/goose-skills --skill customer-story-…;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-story-builder 怎么安装?

在终端执行 npx skills add https://github.com/athina-ai/goose-skills --skill customer-story-builder。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

customer-story-builder 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。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-story-builder 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-story-builder 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

customer-story-builder 用的人多吗?

公开数据是累计安装 222 次,近一周安装 9 次,下载 70 次,GitHub 607 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-story-builder 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

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 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

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 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 Codex,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。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 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-story-builder

客户故事构建者 · 本页

222607只读未明确通过

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 Story Builder

Turn raw customer signal into a polished case study — plus every derivative format you need. One input (messy transcript or quote), all outputs (case study, one-pager, social snippet, deck slide).

Core principle: The best customer stories already exist in your support tickets, Slack channels, and call recordings. You just need to extract and structure them.

When to Use

  • "Turn this customer interview into a case study"
  • "We have a great Slack quote from [customer] — help me build a story around it"
  • "Write a case study for [customer]"
  • "I need social proof assets from [customer win]"
  • "Package this customer result for the sales team"

Phase 0: Intake

Customer Context

  1. Customer name — Can we use their name publicly? (Named vs. anonymous)
  2. Company description — Industry, size, stage (1 sentence)
  3. Customer role/title — Who's the champion?
  4. How long have they been a customer?

Raw Input (provide any/all)

  1. Interview transcript — Full or partial transcript from a customer call
  2. Slack/email quotes — Specific messages where they praised the product
  3. Survey responses — NPS comments, CSAT feedback
  4. Support ticket excerpts — Before/after of a problem solved
  5. Review excerpts — G2, Capterra, Trustpilot quotes
  6. Metrics — Any numbers: time saved, revenue impact, efficiency gains, before/after

Story Angle

  1. Primary use case — What were they using the product for?
  2. Key transformation — What changed? (The "before → after" in one sentence)
  3. Output formats needed — Full case study, one-pager, social snippet, sales slide, or all?

Phase 1: Extract Story Elements

From the raw inputs, identify and extract:

The Problem (Before)

  • What was the customer's situation before using the product?
  • What specific pain were they experiencing?
  • What had they tried before? (Manual process, competitor, nothing)
  • How bad was it? (Quantify if possible — hours wasted, money lost, deals missed)

The Decision (Why You)

  • Why did they choose your product?
  • What alternatives did they consider?
  • What was the deciding factor?

The Solution (How)

  • Which specific features/capabilities did they use?
  • How did they implement it? (Timeline, effort)
  • Any surprising use cases or creative applications?

The Result (After)

  • Hard metrics — numbers, percentages, time saved, revenue gained
  • Soft outcomes — confidence, team morale, process improvements
  • Before/after comparison — the transformation in concrete terms

Best Quotes

Pull the 3-5 strongest verbatim quotes from the raw input:

  • Hero quote — the single most powerful statement (for headlines)
  • Problem quote — describes the pain vividly
  • Result quote — describes the outcome with specificity
  • Recommendation quote — would they recommend? Why?

Phase 2: Generate Story Outputs

Output 1: Full Case Study (800-1200 words)

# [Headline: Outcome-driven, not product-driven]
*[Subhead: Customer name + one-line result]*

---

## About [Customer]

[2-3 sentences: company, industry, size, what they do]

## The Challenge

[2-3 paragraphs: What was the problem? Why did it matter? What had they tried?]

> "[Problem quote]"
> — [Name], [Title] at [Company]

## Why [Your Product]

[1-2 paragraphs: How did they find you? What made them choose you?]

## The Solution

[2-3 paragraphs: How did they use the product? Which capabilities mattered most?]

> "[Solution/experience quote]"

## The Results

[Results summary with metric callouts]

### Key Metrics
- **[Metric 1]:** [Number + context]
- **[Metric 2]:** [Number + context]
- **[Metric 3]:** [Number + context]

> "[Result quote]"

## What's Next

[1 paragraph: Future plans, expansion, what they're excited about]

---

**Industry:** [X] | **Company size:** [X] | **Use case:** [X] | **Product:** [X]

Output 2: One-Pager (Sales Leave-Behind)

# [Customer Name]: [Headline Result]

**Challenge:** [2 sentences]
**Solution:** [2 sentences — what they use and how]
**Results:**
- [Metric 1]
- [Metric 2]
- [Metric 3]

> "[Hero quote]"
> — [Name], [Title]

[CTA: Learn more / Request a demo]

Output 3: Social Proof Snippets

For website testimonial section:

"[Short, punchy quote — max 2 sentences]"
— [Name], [Title] at [Company]
[Result: X% improvement in Y]

For LinkedIn post:

[Customer Name] just shared their results:

→ [Metric 1]
→ [Metric 2]
→ [Metric 3]

"[Quote]"

Here's their story: [link]

For cold email insert:

[Company in their industry] saw [key metric] after switching to [Product].

"[Short quote about the result]" — [Name], [Title]

Output 4: Sales Deck Slide Content

Slide title: "[Customer] — [Key Result]"

Left side:
- Challenge: [1 line]
- Solution: [1 line]
- Result: [1 line with metric]

Right side:
> "[Hero quote]"
— [Name], [Title]

[Customer logo]

Output 5: Metric Callout Cards

For website or marketing collateral:

[BIG NUMBER]
[Label — e.g., "hours saved per week"]
— [Customer Name]

Generate 2-3 of these from the strongest metrics.

Phase 3: Story Quality Check

Before finalizing, verify:

  • Specificity — Are results concrete, not vague? ("3x pipeline" > "improved results")
  • Credibility — Is the customer named? Is the metric believable?
  • Relevance — Does this story match your ICP? Will prospects see themselves?
  • Permission — Flag if customer approval is needed before publishing
  • Freshness — Are the results recent? (>12 months old = less impactful)

Phase 4: Output

Save all assets to clients/<client-name>/product-marketing/customer-stories/[customer-slug]/:

  • case-study-full.md — Complete case study
  • one-pager.md — Sales leave-behind
  • social-snippets.md — All social proof formats
  • slide-content.md — Deck slide content
  • raw-inputs.md — Original source material (for reference)

Cost

ComponentCost
All story generationFree (LLM reasoning)
TotalFree

Tools Required

None. Pure reasoning skill. Takes raw text input and produces structured outputs.

Trigger Phrases

  • "Turn this transcript into a case study"
  • "Build a customer story for [customer]"
  • "Package [customer]'s results as social proof"
  • "Run customer story builder for [customer]"

平台分布

Codex

36.69%
按下载量换算26

Claude

29.19%
按下载量换算20

Cursor

20.08%
按下载量换算14

Gemini CLI

10.49%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

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