Token导航 LogoToken导航

Agent Skill · 研究检索

case-study-builder(案例研究构建者)

case-study-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。

case-study-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,权限为需要联网;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 66,724。

总安装 259周安装 11GitHub Stars 13下载 91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:case-study-builder(案例研究构建者)
来源仓库:https://github.com/sales-skills/sales
仓库路径:skills/case-study-builder
安装命令:
npx skills add https://github.com/sales-skills/sales --skill case-study-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/sales-skills/sales --skill case-study-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。

用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于根据关键词或任务场景进行信息检索与筛选的研究场景。通过 npx skills add 命令从指定仓库安装并使用。安装前建议确认权限范围和维护状态,注意可能触发联网或文件读写操作。

case-study-builder 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/case-study-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/sales-skills/sales --skill case-study-builder;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

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

case-study-builder 怎么安装?

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

case-study-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。

case-study-builder 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

case-study-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。

case-study-builder 用的人多吗?

公开数据是累计安装 259 次,近一周安装 11 次,下载 91 次,GitHub 13 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。

case-study-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。

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。

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
case-study-builder

案例研究构建者 · 本页

25913需要联网未明确通过

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

Case Study Builder

Everyone wants social proof. Nobody makes time to create it. You finish a project, the client's happy, you move on — and six months later you're in a sales call with nothing to show.

This skill fixes that. Give me the raw details. I'll produce three formats you can use immediately.


Mode

Detect from context or ask: *"Quick writeup, full case study, or full asset package?"*

ModeWhat you getBest for
quick1 format: paragraph summary for proposalsFast social proof, proposal inserts
standard3 formats: proposal blurb, social proof pull-quote, sales storyActive pitching, LinkedIn, website
deep3 formats + blog-ready case study + FAQ variant + campaign assetsContent marketing, SEO, sales enablement

Default: standard — use quick if they say "just need something fast." Use deep if they want to turn the win into a marketing asset.


Context Loading Gates

Before generating anything, collect all 8 fields:

FieldWhat to Collect
1. ClientIndustry, company size/stage, named or anonymized?
2. BeforeWhat was broken or painful? Any numbers?
3. ActionsWhat did you specifically do? Scope, timeline, role
4. AfterREQUIRED: at least one specific number
5. TimelineHow long to achieve the result?
6. QuoteDirect client quote if available
7. NamingCan we name the client, or must we anonymize?
8. Use caseWhere will this be used? (proposals / website / LinkedIn)

Outcome Extraction Protocol — enforced on Field 4:

If the user says "results were good" or "things improved," stop and ask:

"I need at least one number to make this credible. Pick one: - Revenue change (e.g., 'closed 3 new clients worth $15K') - Time saved (e.g., 'cut from 10 hours to 2 hours/week') - Lead volume (e.g., 'went from 0 to 5 inbound leads/month') - Rough estimate is fine — it doesn't have to be exact."

Do not draft until Field 4 has at least one number.


Phase 1: Situation Analysis

Before drafting, reason through:

  1. Result strength: Is the outcome a Tier 1 (hard metric), Tier 2 (soft metric), or Tier 3 (proxy)? This determines how confident the language should be.
  2. Hero check: Is the story told from the client's perspective, or yours? Client = hero, you = guide.
  3. Tension check: What made this hard? Without a challenge, there's no story — just a list.
  4. Format match: Which use case did they specify? That determines which format to optimize.

Tier system for results language:

TierTypeExampleLanguage
1Hard metric"Revenue +40%"State directly
2Soft metric"Team finally aligned""For the first time in years..."
3Proxy metric"Enabled Series A close""Contributed to..."
4Directional"Noticeable improvement""Significant improvement in..."

Phase 2: The Hero Principle

The client is the hero. You are the guide.

Before writing, flip the framing:

❌ Wrong: "I built a content system that generated leads." ✅ Right: "Sarah went from scrambling to fill her pipeline to getting 3 inbound inquiries per week — all from a content system we built in 6 weeks."

Every format should be written from what the CLIENT experienced, not what YOU delivered.


Phase 3: Generate Three Formats

Format 1: Two-Liner (Proposals & Bios)

Formula: [What was done] + [scale/scope] + [for who] + [result or timeframe]

[Strong action verb] [what was delivered] for [specific client descriptor].
[Outcome metric] in [timeframe].

Example:

Built a full content system for a Series B SaaS founder with no marketing team. 0 to 3 inbound leads/week in 6 weeks.

Format 2: Story Version (LinkedIn & Sales Calls)

Structure — 4 paragraphs, 150–250 words:

**Set the scene:** [Their situation when you arrived — 2-3 sentences with stakes]

**Show the complexity:** [What made this hard — 2-3 sentences]

**What happened:** [Specific actions taken — no feature lists, just moves]

**What changed:** [Outcome — the number + the transformation]

Format 3: Full Case Study (Website & Portfolio)

# Case Study: [Client Name or Descriptor]

## The Challenge
[2-3 paragraphs: situation, stakes, what wasn't working]

## The Approach
[Phases or steps — what happened and in what order]

## The Results
[Metrics, before/after comparison, named outcomes]

## Key Details
- Client: [Named or "A [descriptor] company"]
- Industry: [Sector]
- Timeline: [Duration]
- Scope: [What was delivered]

## What Made This Different
[Unique angle, unexpected obstacle, or pivotal insight]

## Client Quote
> "[Testimonial — or placeholder if not yet collected]"
> — [Name], [Title]

Phase 4: Self-Critique Pass (REQUIRED)

After generating all three formats, evaluate:

Two-liner:

  • Does it have a specific number? (Not "improved results" — a real metric)
  • Is it 2 sentences or fewer?
  • Would someone scanning a proposal stop and read it?

Story version:

  • Is the client the hero (not the author)?
  • Is there genuine tension — something that made this hard?
  • Does the closing paragraph include the key metric?

Full case study:

  • Does the Results section lead with numbers?
  • Is the Challenge section specific enough that a similar prospect recognizes their situation?
  • Is the client quote (or placeholder) present?

Flag any failure: "The story version has no tension — add one obstacle or unexpected challenge before the 'What happened' paragraph."


Phase 5: Distribution Plan

FormatBest locationsWhen to use
Two-linerProposals, email bios, LinkedIn About sectionAny sales context
StoryLinkedIn post, podcast intros, sales call openerWeekly content
Full case studyWebsite portfolio page, PDF download, RFP responseLate-stage buyer research

Output Structure

## Case Study: [Client Descriptor] — [Date]

### Situation Summary
[2-sentence analysis from Phase 1]
Result tier: [1/2/3/4]

---

### Format 1: Two-Liner
[Final copy]

### Format 2: Story Version
[Final copy]

### Format 3: Full Case Study
[Full markdown]

---

### Self-Critique Notes
- Two-liner: [pass/issue]
- Story: [pass/issue]
- Full: [pass/issue]

### Distribution Plan
[Where to use each]

### Next Step
[If no quote collected → run testimonial-collector]
[If strong story → suggest LinkedIn post from story format]

Cross-reference: If a client quote was captured here, run testimonial-collector to properly format and score it for your testimonial library.


*Skill by Brian Wagner | AI Marketing Architect | brianrwagner.com*

平台分布

Codex

37.27%
按下载量换算34

Claude

29.71%
按下载量换算27

Cursor

21.65%
按下载量换算20

Gemini CLI

9.35%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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