compose-outreach外联内容生成工具：基于Common Room信号自动创建个性化邮件、通话脚本和LinkedIn消息

compose-outreach by anthropics/knowledge-work-plugins

310 周安装量

10,300 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/anthropics/knowledge-work-plugins --skill compose-outreach

内容创作自动化营销

🇨🇳中文介绍

撰写外联内容

基于 Common Room 信号，为特定公司或联系人生成三种个性化的外联格式——电子邮件、通话脚本和 LinkedIn 消息。

外联流程

步骤 1：查找目标

使用 Common Room MCP 工具查找并检索目标（公司和/或特定联系人）的数据。提取：

近期产品活动和参与度信号
社区活动（帖子、问题、反应）
第三方意向信号（招聘信息、新闻、融资）
关系历史记录（先前联系、会议、邮件打开情况）

如果用户指定了个人，则进行联系人级别的调研。如果只给出了公司名称，则根据职位、参与度和角色确定最佳联系人目标。

步骤 2：搜索外部切入点（如果 CR 信号薄弱）

如果 CR 返回了强信号（近期活动、参与度、产品使用情况），这些应作为个性化的驱动因素——跳过网络搜索。如果 CR 信号薄弱或潜在客户在 CR 中活动很少，则运行网络搜索以寻找外部切入点：

搜索内容：

"[公司名称]" funding OR acquisition OR launch OR announcement — 最近 30 天
"[联系人全名]" "[公司名称]" — 查找近期文章、采访、LinkedIn 帖子或会议演讲

优先考虑以下外部切入点：

非常近期的（< 2 周）——潜在客户可能仍在思考此事
公开可见的——他们知道你可能已经看到了
预示变化的——增长、新角色、新产品、新市场

如果用户明确要求进行网络搜索或寻找外部切入点，则无论 CR 信号丰富与否，都应执行此操作。

步骤 3：Spark 数据增强（如果可用）

如果 Spark 可用，则对目标联系人运行数据增强，以获取人物角色分类、背景和影响力信号。使用这些信息来调整语气和消息角度。

步骤 4：确定最佳切入点

从信号数据中，确定 1-3 个最强的个性化切入点。按以下标准排序：

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

步骤 5：生成所有三种格式

使用最强的切入点来撰写所有三种格式。每种格式都有不同的限制和惯例——请遵循 references/outreach-formats-guide.md 中的特定格式指南。

始终生成所有三种格式，并清晰标注。

当用户的公司上下文可用时（参见 references/my-company-context.md），请将价值桥梁和推介内容基于用户特定的产品和定位。

步骤 6：注释你的选择

在完成三个草稿后，包含一个简短的说明（2-4 句话），解释：

使用了哪些信号以及选择它们的原因
所做的任何假设（例如，推断的通话目标）
如果主要切入点效果不佳，可替代的角度

## 面向 [姓名 / 公司] 的外联内容

### 📧 电子邮件

**主题：** [主题行]

[邮件正文 — 3–5 句话]

---

### 📞 通话脚本

**开场白：**
[开场白 — 对话式，1–2 句话]

**价值桥梁：**
[致电原因及为何是现在 — 2–3 句话，与某个信号关联]

**请求：**
[单一、低门槛的请求 — 例如，15 分钟通话、具体问题]

---

### 💼 LinkedIn 消息

[少于 300 字符。热情、个性化、不推销。]

---

### 信号说明
[2–4 句话：使用了哪些信号、原因以及任何替代角度]

当信号数据稀疏时

如果 Common Room 返回的目标数据极少（例如，只有姓名、职位、标签——没有活动、没有评分、没有 Spark）：

不要凭空起草外联内容。 基于虚构信号的外联内容比没有外联更糟糕。
首先进行网络搜索 —— 这将成为你主要的个性化信息来源。查找近期新闻、LinkedIn 帖子、会议演讲、公司公告。

如果网络搜索也返回很少信息，请如实呈现你已有的信息，并向用户询问上下文：

## 面向 [姓名 / 公司] 的外联内容 — 数据有限

**我找到的信息：**
[仅来自 CR 和网络搜索的真实数据]

**我目前没有足够的信号来起草个性化的外联内容。** 要写出有力的内容，我需要：
- 近期的活动或参与度信号
- 您从先前对话中获得的上下文
- 现在进行联系的具体原因

您能分享以上任何信息吗？

每条消息都必须提及具体内容——通用的外联内容是不可接受的输出
语气要符合上下文：对于入站/社区信号，要热情且对话式；对于陌生/高管外联，要更正式
LinkedIn 消息必须少于 300 字符——没有例外
通话脚本必须能自然地说出来——在心里默读以检查节奏
切勿捏造信号——仅引用从 Common Room 或网络搜索中检索到的数据

references/outreach-formats-guide.md — 每个渠道的详细格式规则、示例和语气指南

🇺🇸English

Compose Outreach

Generate three personalized outreach formats — email, call script, and LinkedIn message — grounded in Common Room signals for a specific company or contact.

Outreach Process

Step 1: Look Up the Target

Use Common Room MCP tools to find and retrieve data for the target (company and/or specific contact). Pull:

Recent product activity and engagement signals
Community activity (posts, questions, reactions)
3rd-party intent signals (job postings, news, funding)
Relationship history (prior contact, meetings, email opens)

If the user specified a person, run contact-level research. If only a company was given, identify the best contact to target based on title, engagement, and role.

Step 2: Web Search for External Hooks (If CR Signals Are Thin)

If CR returned strong signals (recent activity, engagement, product usage), those should drive personalization — skip web search. If CR signals are thin or the prospect has little CR activity, run a web search for external hooks:

What to search:

"[company name]" funding OR acquisition OR launch OR announcement — last 30 days
"[contact full name]" "[company name]" — look for recent articles, interviews, LinkedIn posts, or conference talks

Prioritize external hooks that are:

Very recent (< 2 weeks) — the prospect is likely still thinking about it
Publicly visible — they know you could have seen it
Change-signaling — growth, new role, new product, new market

If the user explicitly asks for web search or external hooks, run it regardless of CR signal richness.

Step 3: Spark Enrichment (If Available)

If Spark is available, run enrichment on the target contact to get persona classification, background, and influence signals. Use this to calibrate tone and message angle.

Step 4: Identify the Best Hooks

From the signal data, identify the 1–3 strongest personalization hooks. Rank by:

Recency — happened in the last 7–14 days
Specificity — a concrete action they took, not a general trend
Relevance — connects directly to a value your product delivers

Good hooks: posted a question in the community about X, just hired 5 engineers, recently started using [feature], company just raised Series B, trial nearing expiration, champion just changed jobs.

Bad hooks: "I noticed you're a customer" or generic industry trends.

Step 5: Generate All Three Formats

Use the strongest hooks to write all three formats. Each format has different constraints and conventions — follow the format-specific guidelines in references/outreach-formats-guide.md.

Always produce all three, clearly labeled.

When the user's company context is available (see references/my-company-context.md), ground the value bridge and pitch in the user's specific product and positioning.

Step 6: Annotate Your Choices

After the three drafts, include a brief note (2–4 sentences) explaining:

Which signals were used and why they were chosen
Any assumptions made (e.g., inferred call objective)
Alternative angles if the primary hook doesn't land

Output Format

## Outreach for [Name / Company]

### 📧 Email

**Subject:** [Subject line]

[Email body — 3–5 sentences]

---

### 📞 Call Script

**Opening:**
[Opening line — conversational, 1–2 sentences]

**Value Bridge:**
[Why you're calling and why now — 2–3 sentences tied to a signal]

**Ask:**
[Single, low-friction ask — e.g., 15-minute call, specific question]

---

### 💼 LinkedIn Message

[Under 300 characters. Warm, personal, no pitch.]

---

### Signal Notes
[2–4 sentences: which signals were used, why, and any alternative angles]

When Signal Data Is Sparse

If Common Room returns minimal data on the target (e.g., just name, title, tags — no activity, no scores, no Spark):

Do not draft outreach from thin air. Outreach grounded in fabricated signals is worse than no outreach.
Run web search first — this becomes your primary personalization source. Look for recent news, LinkedIn posts, conference talks, company announcements.
If web search also returns little , present what you have honestly and ask the user for context:

## Outreach for [Name / Company] — Limited Data

**What I found:**
[Only the real data from CR and web search]

**I don't have enough signal to draft personalized outreach yet.** To write something strong, I'd need:
- Recent activity or engagement signals
- Context you have from prior conversations
- A specific reason for reaching out now

Can you share any of the above?

Quality Standards

Every message must reference something specific — generic outreach is not acceptable output
Match tone to context: warm and conversational for inbound/community signals; more formal for cold/executive outreach
The LinkedIn message must be under 300 characters — no exceptions
The call script must be speakable naturally — read it aloud mentally to check rhythm
Never fabricate signals — only reference data retrieved from Common Room or web search

Reference Files

references/outreach-formats-guide.md — detailed format rules, examples, and tone guidelines for each channel

Weekly Installs

Repository

anthropics/know…-plugins

GitHub Stars

9.0K

First Seen

Feb 24, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

codex91

opencode90

kimi-cli89

gemini-cli89

github-copilot89

cursor89

营销心理学与心智模型应用指南 | 提升营销决策与客户行为理解

37,100 周安装