Back to Details

sourcing-outreach

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Sourcing Outreach

人才寻访外联

When to Use

何时使用

Activate when the user asks to write cold outreach to potential candidates (LinkedIn InMails, cold emails), craft referral request messages, build a multi-touch follow-up sequence, or improve response rates on existing recruiting outreach. Also activate when the user is sourcing for a specific role and needs help personalizing messages at scale.
当用户要求为潜在候选人撰写冷外联消息（LinkedIn InMails、冷邮件）、撰写内推请求消息、构建多触点跟进序列，或提升现有招聘外联消息的回复率时，启用此功能。当用户正在为特定职位寻访人才，并需要大规模个性化消息方面的帮助时，也应启用。

Context Required

所需上下文

  • From startup-context: Company name, one-line mission, stage/funding, notable investors or customers, recent milestones, and team size.
  • From user: Role being hired for, the candidate's name and background (LinkedIn profile, blog posts, talks, open-source work), what specifically drew the user to this candidate, and the communication channel (LinkedIn, email, Twitter DM).
  • From startup-context： 公司名称、一句话使命、阶段/融资情况、知名投资者或客户、近期里程碑和团队规模。
  • From user： 正在招聘的职位、候选人的姓名和背景（LinkedIn 个人资料、博客文章、演讲、open-source 工作）、哪些具体因素吸引用户关注该候选人，以及沟通渠道（LinkedIn、邮件、Twitter DM）。

Workflow

工作流

  1. Research the candidate — Review the candidate details provided by the user. Identify 1-2 specific, genuine connection points: a project they shipped, a talk they gave, an open-source contribution, a blog post, or a career pattern that signals fit.
  2. Choose the outreach template — Select from: cold LinkedIn InMail, cold email, warm intro request, referral ask, or follow-up. Each has different length and tone constraints.
  3. Draft the message — Write a short, personalized message using the PRC framework (see below). Keep LinkedIn InMails under 300 characters for the preview. Keep cold emails under 150 words.
  4. Add a clear, low-friction CTA — The ask should be small: a 15-minute call, a reply with interest level, or permission to send more details. Never ask for a resume or formal application in cold outreach.
  5. Build the follow-up sequence — Draft 2-3 follow-ups spaced 4-7 days apart. Each follow-up adds new information (a company milestone, a team blog post, a relevant data point) rather than just "bumping" the thread.
  6. Review for tone — Ensure the message sounds human, not templated. Check that personalization is specific enough that it could only apply to this candidate.
  1. 研究候选人 — 查看用户提供的候选人详情。找出 1-2 个具体且真实的关联点：他们交付过的项目、做过的演讲、开源贡献、博客文章，或能够体现其岗位匹配度的职业发展模式。
  2. 选择外联模板 — 从以下类型中选择：LinkedIn 冷 InMail、冷邮件、熟人引荐请求、内推请求或跟进消息。每种类型都有不同的长度和语气限制。
  3. 起草消息 — 使用 PRC 框架（见下文）撰写一条简短且个性化的消息。LinkedIn InMail 应控制在 300 个字符以内，以确保预览完整显示。冷邮件应控制在 150 个单词以内。
  4. 添加清晰且低摩擦的 CTA — 请求应保持轻量，例如安排一次 15 分钟的通话、回复其兴趣程度，或征得同意后发送更多详情。冷外联中绝不要要求候选人发送简历或进行正式申请。
  5. 构建跟进序列 — 起草 2-3 条间隔 4-7 天的跟进消息。每条跟进都应增加新信息，例如公司里程碑、团队博客文章或相关数据点，而不是简单地“催促”对方回复。
  6. 检查语气 — 确保消息听起来自然、不像模板。检查个性化程度是否足够具体，使内容只适用于该候选人。

Output Format

输出格式

  • A primary outreach message (ready to send)
  • 2-3 follow-up messages with suggested send timing
  • Notes on personalization elements used and why they were chosen
  • 一条可直接发送的主要外联消息
  • 2-3 条跟进消息，并附建议发送时间
  • 对所采用的个性化元素及其选择原因的说明

Frameworks & Best Practices

框架与最佳实践

The PRC Framework

PRC 框架

Every outreach message should contain three elements in roughly this order:
  • Personalization (P): A specific, genuine observation about the candidate's work that shows you did your homework. Not "I saw your impressive profile" — something like "Your talk on event sourcing at StrangeLoop changed how I think about our own data pipeline."
  • Relevance (R): Why this role connects to their career trajectory. Bridge from what they've done to what they'd do at your company.
  • Call-to-action (C): A single, low-commitment ask. "Would you be open to a 15-minute call this week?" is better than "Apply at our careers page."
每条外联消息都应大致按以下顺序包含三个要素：
  • Personalization（P）： 对候选人工作作出具体、真实的观察，表明你做过充分研究。不要写“我看过你令人印象深刻的履历”，而应类似于“你在 StrangeLoop 上关于 event sourcing 的演讲，改变了我对我们自身 data pipeline 的思考方式”。
  • Relevance（R）： 说明该职位为何与其职业发展方向相契合。将其过往经历与加入公司后将从事的工作连接起来。
  • Call-to-action（C）： 提出一个单一且低投入的请求。“你本周方便进行一次 15 分钟的通话吗？”优于“请前往我们的招聘页面申请”。

Channel-Specific Guidelines

各渠道专项指南

LinkedIn InMail:
  • Subject line matters more than body — keep it intriguing and specific (e.g., "Your Kafka work + our real-time pipeline" not "Exciting opportunity").
  • InMail preview shows ~300 characters. Front-load the personalization.
  • Do not connect-and-pitch simultaneously. Either send an InMail or send a connection request with a note — not both at once.
Cold Email:
  • Subject: Short, specific, no clickbait. "Quick question about [their project]" or "[Mutual connection] suggested I reach out."
  • Keep body under 150 words. Three short paragraphs max.
  • Plain text outperforms HTML templates. No logos, no signatures with 10 links.
  • Send from a real person's email (founder@, not recruiting@).
Warm Intro / Referral Request:
  • Make it easy for the connector: provide a forwardable blurb they can send with zero editing.
  • Include context on why you think the candidate is a fit so the connector can vouch meaningfully.
  • Always give the connector an out: "No pressure at all if this doesn't feel right."
LinkedIn InMail：
  • 主题行比正文更重要——应保持有趣且具体，例如“你的 Kafka 工作 + 我们的实时 pipeline”，而不是“令人兴奋的机会”。
  • InMail 预览约显示 300 个字符。应将个性化内容放在开头。
  • 不要同时发送连接请求并进行推销。要么发送 InMail，要么发送带附言的连接请求，不能两者同时进行。
冷邮件：
  • 主题：简短、具体，不使用标题党。例如“关于[他们的项目]，有个问题想请教”或“[共同联系人]建议我联系你”。
  • 正文控制在 150 个单词以内，最多三个简短段落。
  • 纯文本的效果优于 HTML 模板。不要添加 logo，也不要使用包含 10 个链接的签名档。
  • 使用真人的邮箱发送（founder@，而不是 recruiting@）。
熟人引荐/内推请求：
  • 让引荐人使用起来更轻松：提供一段无需修改即可直接转发的简介。
  • 说明你为什么认为该候选人适合该职位，以便引荐人能够有依据地为其推荐。
  • 始终给引荐人留出拒绝余地：“如果感觉不合适，也完全不用有压力。”

Personalization Research Checklist

个性化调研清单

Before writing, look for:
  • Recent talks, podcast appearances, or conference presentations
  • Blog posts or technical writing
  • Open-source contributions (GitHub, GitLab)
  • Career trajectory patterns (e.g., "you've gone deep on infrastructure at two companies in a row")
  • Mutual connections or shared communities
  • Company or product they built that you genuinely admire
撰写消息前，查找以下信息：
  • 近期演讲、播客客串或会议演讲
  • 博客文章或技术写作
  • 开源贡献（GitHub、GitLab）
  • 职业发展轨迹模式（例如，“你连续在两家公司深入专注 infrastructure 领域”）
  • 共同联系人或共同社群
  • 由其打造且你真正欣赏的公司或产品

Follow-Up Sequence Design

跟进序列设计

  • Follow-up 1 (Day 4-5): Add a new piece of information — a recent company milestone, a blog post from the team, or a specific project they'd work on. Keep it to 2-3 sentences.
  • Follow-up 2 (Day 9-11): Try a different angle. If the first message was about the role, this one could be about the team or a technical challenge. Ask a question rather than making a pitch.
  • Follow-up 3 (Day 16-20): A graceful close. "I don't want to crowd your inbox — just wanted to leave the door open. If timing is ever better, I'd love to chat." This gets surprisingly high response rates.
  • Never send more than 3 follow-ups to a candidate who hasn't responded.
  • 第一次跟进（第 4-5 天）： 增加一条新信息，例如近期公司里程碑、团队发布的博客文章，或他们将要参与的具体项目。控制在 2-3 个句子以内。
  • 第二次跟进（第 9-11 天）： 尝试换一个角度。如果第一条消息围绕职位展开，这次可以围绕团队或技术挑战展开。提出一个问题，而不是直接推销。
  • 第三次跟进（第 16-20 天）： 体面收尾。“我不想占用你的收件箱——只是想给你留个机会。如果时机更合适，我很想聊聊。”这种消息的回复率出人意料地高。
  • 对于未回复的候选人，绝不要发送超过 3 次跟进。

Anti-Patterns to Avoid

应避免的反模式

  • Spray and pray: Sending identical messages to 200 people. Response rates plummet below 5%. Batch personalization into tiers instead.
  • The humble brag opener: "We just raised $50M from Sequoia" as your first sentence. Lead with the candidate, not yourself.
  • Fake personalization: "I was really impressed by your background" is worse than no personalization because it signals a template.
  • Overselling: Don't describe the role as "once in a lifetime." Be honest and specific about what makes it compelling.
  • Asking for too much: "Please send your resume and three references" in a cold message guarantees no reply.
  • 广撒网式碰运气（Spray and pray）： 向 200 个人发送完全相同的消息。回复率会跌破 5%。应改为将个性化内容分层并批量处理。
  • 谦虚式炫耀开场： 以“我们刚从 Sequoia 融资 5000 万美元”作为第一句。应从候选人切入，而不是从自己切入。
  • 虚假个性化： “你的背景真的给我留下了很深的印象”比不个性化更糟糕，因为它会暴露模板痕迹。
  • 过度推销： 不要将职位描述为“一生一次的机会”。应诚实且具体地说明它为何具有吸引力。
  • 索要过多： 在冷消息中要求“请发送你的简历和三位推荐人”，必然得不到回复。

Related Skills

相关 Skills

  • job-description
    — The JD provides the source material for what makes the role compelling in outreach.
  • interview-kit
    — Mention the candidate-friendly interview process in outreach to reduce friction.
  • job-description
    — JD 提供了说明该职位为何适合用于外联的核心素材。
  • interview-kit
    — 在外联消息中提及对候选人友好的面试流程，以减少沟通和参与阻力。

Examples

示例

Prompt: "Write a cold LinkedIn InMail for a senior ML engineer. She gave a talk at NeurIPS on efficient fine-tuning and currently works at Stripe."
Good output snippet:
Subject: Your NeurIPS talk on efficient fine-tuning

Hi [Name],

Your NeurIPS presentation on LoRA variants for production models stuck
with me — especially the bit about keeping inference costs flat while
scaling model complexity. We're solving a similar problem at [Company]:
building real-time ML models for [use case] and need someone who thinks
about efficiency as a first-class constraint.

We're 18 people, Series A, and this would be our second ML hire. You'd
own the model architecture end to end.

Would you be open to a 15-minute call to see if there's a fit?

— [Your name]
Prompt: "Write a referral request email I can send to a mutual connection."
Good output snippet:
Subject: Quick ask — know anyone strong in product design?

Hi [Connector],

We're hiring our first product designer at [Company] and I thought of
you since you work with strong designers regularly. Here's what we're
looking for: [1-2 sentences on the role].

If anyone comes to mind, I'd be grateful for an intro. Here's a
forwardable blurb:

---
"[Your name] is the CEO of [Company] ([one-liner]). They're hiring a
founding product designer to own the end-to-end user experience. The
team is 14 people, Series A, remote-first. Here's the JD: [link]"
---

No pressure at all — and thanks either way.

[Your name]
提示词： “为一位高级 ML 工程师撰写一封冷启动 LinkedIn InMessage。她曾在 NeurIPS 上发表关于高效微调的演讲，目前就职于 Stripe。”
优质输出片段：
Subject: Your NeurIPS talk on efficient fine-tuning

Hi [Name],

Your NeurIPS presentation on LoRA variants for production models stuck
with me — especially the bit about keeping inference costs flat while
scaling model complexity. We're solving a similar problem at [Company]:
building real-time ML models for [use case] and need someone who thinks
about efficiency as a first-class constraint.

We're 18 people, Series A, and this would be our second ML hire. You'd
own the model architecture end to end.

Would you be open to a 15-minute call to see if there's a fit?

— [Your name]
提示词： “写一封内推请求邮件，我要发送给一位共同联系人。”
优质输出片段：
Subject: Quick ask — know anyone strong in product design?

Hi [Connector],

We're hiring our first product designer at [Company] and I thought of
you since you work with strong designers regularly. Here's what we're
looking for: [1-2 sentences on the role].

If anyone comes to mind, I'd be grateful for an intro. Here's a
forwardable blurb:

---
"[Your name] is the CEO of [Company] ([one-liner]). They're hiring a
founding product designer to own the end-to-end user experience. The
team is 14 people, Series A, remote-first. Here's the JD: [link]"
---

No pressure at all — and thanks either way.

[Your name]