Token导航 LogoToken导航

Agent Skill · 研究检索

call-prep(通话准备)

call-prep 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。

call-prep 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,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 5,756。

总安装 24,480周安装 964GitHub Stars 11,727下载 7,920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:call-prep(通话准备)
来源仓库:https://github.com/anthropics/knowledge-work-plugins
仓库路径:skills/call-prep
安装命令:
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill call-prep
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/anthropics/knowledge-work-plugins --skill call-prep

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。

用于销售会前情报收集与提问策略生成,提升成交概率。支持公司动态、融资历史与组织架构深度调研能力。call-prep 属于研究检索类 Skill,可作为该场景下的辅助能力补充。提供开放式问题与封闭式问题配比建议优化对话节奏。安装需通过 GitHub 仓库,建议打通 CRM 获取历史交互记录。

涉及上市公司时应引用公开财报与新闻源确保信息准确。

来源仓库内路径:skills/call-prep

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/anthropics/knowledge-work-plugins --skill call…;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

call-prep 怎么安装?

在终端执行 npx skills add https://github.com/anthropics/knowledge-work-plugins --skill call-prep。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

call-prep 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。

call-prep 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。

call-prep 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。

call-prep 用的人多吗?

公开数据是累计安装 24,480 次,近一周安装 964 次,下载 7,920 次,GitHub 11,727 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。

call-prep 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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。
  • 来源仓库有 11,727 星,维护活跃度相对可查。
  • 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。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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
call-prep

通话准备 · 本页

24,48011,727只读未明确有提醒

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

Call Prep

Get fully prepared for any sales call in minutes. This skill works with whatever context you provide, and gets significantly better when you connect your sales tools.

How It Works

┌─────────────────────────────────────────────────────────────────┐
│                        CALL PREP                                 │
├─────────────────────────────────────────────────────────────────┤
│  ALWAYS (works standalone)                                       │
│  ✓ You tell me: company, meeting type, attendees                │
│  ✓ Web search: recent news, funding, leadership changes         │
│  ✓ Company research: what they do, size, industry               │
│  ✓ Output: prep brief with agenda and questions                 │
├─────────────────────────────────────────────────────────────────┤
│  SUPERCHARGED (when you connect your tools)                      │
│  + CRM: account history, contacts, opportunities, activities    │
│  + Email: recent threads, open questions, commitments           │
│  + Chat: internal discussions, colleague insights               │
│  + Transcripts: prior call recordings, key moments              │
│  + Calendar: auto-find meeting, pull attendees                  │
└─────────────────────────────────────────────────────────────────┘

Getting Started

When you run this skill, I'll ask for what I need:

Required:

  • Company or contact name
  • Meeting type (discovery, demo, negotiation, check-in, etc.)

Helpful if you have it:

  • Who's attending (names and titles)
  • Any context you want me to know (paste prior notes, emails, etc.)

If you've connected your CRM, email, or other tools, I'll pull context automatically and skip the questions.


Connectors (Optional)

Connect your tools to supercharge this skill:

ConnectorWhat It Adds
CRMAccount details, contact history, open deals, recent activities
EmailRecent threads with the company, open questions, attachments shared
ChatInternal chat discussions (e.g. Slack) about the account, colleague insights
TranscriptsPrior call recordings, topics covered, competitor mentions
CalendarAuto-find the meeting, pull attendees and description
No connectors? No problem. Just tell me about the meeting and paste any context you have. I'll research the rest.

Output Format

# Call Prep: [Company Name]

**Meeting:** [Type] — [Date/Time if known]
**Attendees:** [Names with titles]
**Your Goal:** [What you want to accomplish]

---

## Account Snapshot

| Field | Value |
|-------|-------|
| **Company** | [Name] |
| **Industry** | [Industry] |
| **Size** | [Employees / Revenue if known] |
| **Status** | [New prospect / Active opportunity / Customer] |
| **Last Touch** | [Date and summary] |

---

## Who You're Meeting

### [Name] — [Title]
- **Background:** [Career history, education if found]
- **LinkedIn:** [URL]
- **Role in Deal:** [Decision maker / Champion / Evaluator / etc.]
- **Last Interaction:** [Summary if known]
- **Talking Point:** [Something personal/professional to reference]

[Repeat for each attendee]

---

## Context & History

**What's happened so far:**
- [Key point from prior interactions]
- [Open commitments or action items]
- [Any concerns or objections raised]

**Recent news about [Company]:**
- [News item 1 — why it matters]
- [News item 2 — why it matters]

---

## Suggested Agenda

1. **Open** — [Reference last conversation or trigger event]
2. **[Topic 1]** — [Discovery question or value discussion]
3. **[Topic 2]** — [Address known concern or explore priority]
4. **[Topic 3]** — [Demo section / Proposal review / etc.]
5. **Next Steps** — [Propose clear follow-up with timeline]

---

## Discovery Questions

Ask these to fill gaps in your understanding:

1. [Question about their current situation]
2. [Question about pain points or priorities]
3. [Question about decision process and timeline]
4. [Question about success criteria]
5. [Question about other stakeholders]

---

## Potential Objections

| Objection | Suggested Response |
|-----------|-------------------|
| [Likely objection based on context] | [How to address it] |
| [Common objection for this stage] | [How to address it] |

---

## Internal Notes

[Any internal chat context (e.g. Slack), colleague insights, or competitive intel]

---

## After the Call

Run **call-follow-up** to:
- Extract action items
- Update your CRM
- Draft follow-up email

Execution Flow

Step 1: Gather Context

If connectors available:

1. Calendar → Find upcoming meeting matching company name
   - Pull: title, time, attendees, description, attachments

2. CRM → Query account
   - Pull: account details, all contacts, open opportunities
   - Pull: last 10 activities, any account notes

3. Email → Search recent threads
   - Query: emails with company domain (last 30 days)
   - Extract: key topics, open questions, commitments

4. Chat → Search internal discussions
   - Query: company name mentions (last 30 days)
   - Extract: colleague insights, competitive intel

5. Transcripts → Find prior calls
   - Pull: call recordings with this account
   - Extract: key moments, objections raised, topics covered

If no connectors:

1. Ask user:
   - "What company are you meeting with?"
   - "What type of meeting is this?"
   - "Who's attending? (names and titles if you know)"
   - "Any context you want me to know? (paste notes, emails, etc.)"

2. Accept whatever they provide and work with it

Step 2: Research Supplement

Always run (web search):

1. "[Company] news" — last 30 days
2. "[Company] funding" — recent announcements
3. "[Company] leadership" — executive changes
4. "[Company] + [industry] trends" — relevant context
5. Attendee LinkedIn profiles — background research

Step 3: Synthesize & Generate

1. Combine all sources into unified context
2. Identify gaps in understanding → generate discovery questions
3. Anticipate objections based on stage and history
4. Create suggested agenda tailored to meeting type
5. Output formatted prep brief

Meeting Type Variations

Discovery Call

  • Focus on: Understanding their world, pain points, priorities
  • Agenda emphasis: Questions > Talking
  • Key output: Qualification signals, next step proposal

Demo / Presentation

  • Focus on: Their specific use case, tailored examples
  • Agenda emphasis: Show relevant features, get feedback
  • Key output: Technical requirements, decision timeline

Negotiation / Proposal Review

  • Focus on: Addressing concerns, justifying value
  • Agenda emphasis: Handle objections, close gaps
  • Key output: Path to agreement, clear next steps

Check-in / QBR

  • Focus on: Value delivered, expansion opportunities
  • Agenda emphasis: Review wins, surface new needs
  • Key output: Renewal confidence, upsell pipeline

Tips for Better Prep

  1. More context = better prep — Paste emails, notes, anything you have
  2. Name the attendees — Even just titles help me research
  3. State your goal — "I want to get them to agree to a pilot"
  4. Flag concerns — "They mentioned budget is tight"

Related Skills

  • account-research — Deep dive on a company before first contact
  • call-follow-up — Process call notes and execute post-call workflow
  • draft-outreach — Write personalized outreach after research

平台分布

Codex

35.86%
按下载量换算2,840

Claude

32.12%
按下载量换算2,544

Cursor

19.24%
按下载量换算1,524

Gemini CLI

9.51%
按下载量换算753

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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