outreach-specialist by ognjengt/founder-skills
npx skills add https://github.com/ognjengt/founder-skills --skill outreach-specialist生成听起来像真人、能建立信任并预约通话的个性化外联序列(默认 3 条消息)——根据潜在客户、平台和提供的服务量身定制。
首先检查 $ARGUMENTS 以确定执行模式:
回复:"outreach-specialist 已加载,请告诉我您要联系谁以及您提供什么"
然后等待用户在下一消息中提供他们的需求。
立即进入任务执行阶段(跳过"已加载"消息)。
当用户需求可用时(无论是来自初始的 $ARGUMENTS 还是后续消息):
阻塞性要求——切勿跳过此步骤
在执行任何其他操作之前,您必须使用 Read 工具阅读所有参考文件。这是不可协商的:
Read: ./references/outreach-templates.md
Read: ./references/sequence-strategy.md
您将找到的内容:
在您阅读完所有文件并将其内容纳入上下文之前,请勿进行第 2 步。
检查项目根目录中是否存在 FOUNDER_CONTEXT.md 文件。
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
从用户需求中提取:
如果您不是 100% 确定拥有撰写高转化率消息所需的一切,请使用 AskUserQuestion 提出最多 5 个问题。只问真正缺失的内容。
问题库(优先级顺序):
---|---|---|---
1 | 您是在 LinkedIn、电子邮件还是其他平台上进行联系? | 消息长度、语气和结构因平台而异 | 平台已说明
2 | 您的服务能带来的具体结果或转变是什么? | 钩子和价值主张取决于此 | 从上下文可以清楚看出服务和结果
3 | 您是否有想要包含的案例研究或具体结果? | 社会认同能显著提高回复率 | 已提供案例研究或用户要求保持简短
4 | 这是陌生外联,还是有熟人介绍/触发事件? | 这会完全改变开场白和方法 | 上下文使其显而易见
5 | 您希望保持简短和介绍性,还是包含更多细节和证明? | 决定消息长度和模板选择 | 用户已指定格式偏好
每批最多问 4 个问题。 一旦您有足够信心撰写序列,就立即停止提问。
根据所有收集到的输入,从 outreach-templates.md 中选择最佳模板:
模板选择逻辑:
| 情境 | 最佳模板匹配 |
|---|---|
| 陌生外联,无先前关系 | Taking on New Projects、Value-First 或 Permission-Based |
| 有强有力的案例研究可分享 | Case Study 模板 |
| 发现了关于潜在客户的特定信息 | Firstline 模板 |
| 有熟人介绍或共同联系人存在 | Mutual Connection 模板 |
| 希望通过多媒体脱颖而出 | Loom/Video Teaser 模板 |
| 基于推荐的方法 | Taking on New Projects(带推荐角度) |
| 序列中的最终跟进 | Breakup 模板 |
序列结构(默认 3 条消息):
如果用户要求更多或更少的消息,请相应调整。
对于序列中的每条消息:
硬性约束。不可变通。
呈现完整的序列,包括平台、时间安排和可直接发送的消息:
## 外联序列
**目标:** [外联对象是谁]
**平台:** [LinkedIn / Email / X DM / 等]
**目标:** [预约通话 / 获得回复 / 等]
**序列长度:** [X 条消息]
---
### 消息 1 — 初次外联
**发送时间:** 第 1 天
**主题:** [仅用于电子邮件 — 私信省略]
[完整的消息文本,可直接复制发送]
---
### 消息 2 — 跟进
**发送时间:** 第 3-4 天
**主题:** [仅用于电子邮件]
[完整的消息文本,可直接复制发送]
---
### 消息 3 — 最后接触
**发送时间:** 第 7-10 天
**主题:** [仅用于电子邮件]
[完整的消息文本,可直接复制发送]
示例:
## 外联序列
**目标:** 年经常性收入在 100 万至 500 万美元的 B2B SaaS 创始人
**平台:** LinkedIn 私信
**目标:** 预约发现通话
---
### 消息 1 — 初次外联
**发送时间:** 第 1 天
嘿 John,
看到你正在 Acme 扩展销售团队。不错。
我们刚刚帮助一家处于类似阶段的 SaaS 公司通过定制的 CRM 集成将销售周期缩短了 30%。
值得花 10 分钟快速聊聊看是否合适吗?
---
### 消息 2 — 跟进
**发送时间:** 第 3 天
嘿 John,
不是想催促你。只是想分享这个来自你所在领域的一位 SaaS 创始人的快速案例研究。
[案例研究链接]
觉得这可能有用,无论我们是否聊天。
---
### 消息 3 — 最后接触
**发送时间:** 第 8 天
嘿 John,
尝试联系了你几次,所以我就长话短说。
如果目前缩短销售周期不是优先事项,完全理解。
但如果是,我很乐意本周花 10 分钟聊聊。无论如何,祝你团队扩展顺利。
在生成任何消息之前,必须使用 Read 工具阅读这些文件(参见步骤 1):
| 文件 | 用途 |
|---|---|
./references/outreach-templates.md | 8 个经过验证的外联消息模板,包含示例、心理学原理和使用时机逻辑 |
./references/sequence-strategy.md | 后续序列结构、时间安排、平台规则和已验证的模式 |
为什么两者都重要: 模板为您提供实际能获得回复的消息的结构 DNA。序列策略告诉您如何在多次接触中安排间隔、调整角度和逐步推进。仅模板 = 一个好的第一条消息。模板 + 序列策略 = 一个能预约通话的完整系统。
在最终确定输出之前,验证以下所有内容:
./references/outreach-templates.md./references/sequence-strategy.md如果任何一项检查失败,请在呈现前进行修改。
除非用户覆盖,否则使用以下默认值:
在输出中注明所做的任何假设。
每周安装量
130
代码仓库
GitHub 星标数
100
首次出现
2026年2月9日
安全审计
安装于
opencode121
codex116
gemini-cli115
github-copilot113
kimi-cli107
amp106
Generate a personalized outreach sequence (default 3 messages) that sounds human, builds trust, and books calls — tailored to the prospect, platform, and offer.
Check $ARGUMENTS first to determine execution mode:
Respond with: "outreach-specialist loaded, tell me who you're reaching out to and what you're offering"
Then wait for the user to provide their requirements in the next message.
Proceed immediately to Task Execution (skip the "loaded" message).
When user requirements are available (either from initial $ARGUMENTS or follow-up message):
BLOCKING REQUIREMENT — DO NOT SKIP THIS STEP
Before doing ANYTHING else, you MUST use the Read tool to read ALL reference files. This is non-negotiable:
Read: ./references/outreach-templates.md
Read: ./references/sequence-strategy.md
What you will find:
DO NOT PROCEED to Step 2 until you have read all files and have their content in context.
Check if FOUNDER_CONTEXT.md exists in the project root.
From the user's requirements, extract:
If you are NOT 100% certain you have everything needed to write a high-converting message, ask up to 5 questions using AskUserQuestion. Only ask what's genuinely missing.
Question Bank (priority order):
---|---|---|---
1 | Are you reaching out on LinkedIn, email, or another platform? | Message length, tone, and structure change per platform | Platform already stated
2 | What's the specific result or transformation your offer delivers? | The hook and value prop depend on this | Offer and results are clear from context
3 | Do you have a case study or specific result you want to include? | Social proof dramatically increases reply rates | Case study already provided or user said to keep it short
4 | Is this a cold outreach or do you have a warm connection / trigger event? | Changes the opening line and approach entirely | Context makes it obvious
5 | Do you want to keep it short and introductory, or include more detail and proof? | Determines message length and template selection | User already specified format preference
Ask up to 4 questions per batch. Stop as soon as you have enough to write a confident sequence.
Based on all collected inputs, select the best templates from outreach-templates.md:
Template Selection Logic:
| Situation | Best template match |
|---|---|
| Cold outreach, no prior relationship | Taking on New Projects, Value-First, or Permission-Based |
| Have a strong case study to share | Case Study template |
| Found something specific about the prospect | Firstline template |
| Warm intro or mutual connection exists | Mutual Connection template |
| Want to stand out with multimedia | Loom/Video Teaser template |
| Referral-based approach | Taking on New Projects (with referral angle) |
| Final follow-up in sequence | Breakup template |
Sequence Structure (default 3 messages):
If the user requests more or fewer messages, adjust accordingly.
For each message in the sequence:
Hard constraints. No interpretation.
Present the full sequence with platform, timing, and ready-to-send messages:
## Outreach Sequence
**Target:** [Who the outreach is for]
**Platform:** [LinkedIn / Email / X DM / etc.]
**Goal:** [Book a call / Get a reply / etc.]
**Sequence length:** [X messages]
---
### Message 1 — Initial Outreach
**Send:** Day 1
**Subject:** [Only for email — omit for DMs]
[Full message text, ready to copy and send]
---
### Message 2 — Follow-Up
**Send:** Day 3-4
**Subject:** [Only for email]
[Full message text, ready to copy and send]
---
### Message 3 — Final Touch
**Send:** Day 7-10
**Subject:** [Only for email]
[Full message text, ready to copy and send]
Example:
## Outreach Sequence
**Target:** B2B SaaS founders doing $1M-$5M ARR
**Platform:** LinkedIn DM
**Goal:** Book a discovery call
---
### Message 1 — Initial Outreach
**Send:** Day 1
Hey John,
Saw you're scaling the sales team at Acme. Nice.
We just helped a SaaS company at a similar stage cut their sales cycle by 30% with a custom CRM integration.
Worth a quick 10-min chat to see if it fits?
---
### Message 2 — Follow-Up
**Send:** Day 3
Hey John,
Not trying to be pushy. Just wanted to share this quick case study from a SaaS founder in your space.
[link to case study]
Thought it might be useful whether we chat or not.
---
### Message 3 — Final Touch
**Send:** Day 8
Hey John,
Tried reaching out a couple of times, so I'll keep this short.
If cutting your sales cycle isn't a priority right now, totally get it.
But if it is, happy to chat for 10 min this week. Either way, good luck scaling the team.
These files MUST be read using the Read tool before generating any messages (see Step 1):
| File | Purpose |
|---|---|
./references/outreach-templates.md | 8 proven outreach message templates with examples, psychology, and when-to-use logic |
./references/sequence-strategy.md | Follow-up sequence structures, timing, platform rules, and proven patterns |
Why both matter: Templates give you the structural DNA of messages that actually get replies. Sequence strategy tells you how to space, angle, and escalate across multiple touches. Templates alone = a good first message. Templates + sequence strategy = a full system that books calls.
Before finalizing output, verify ALL of the following:
./references/outreach-templates.md before writing messages./references/sequence-strategy.md before writing messagesIf ANY check fails, revise before presenting.
Use these unless the user overrides:
Document any assumptions made in the output.
Weekly Installs
130
Repository
GitHub Stars
100
First Seen
Feb 9, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode121
codex116
gemini-cli115
github-copilot113
kimi-cli107
amp106
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
42,000 周安装