Token导航 LogoToken导航

Agent Skill · 研究检索

outreach-specialist(外展专家)

outreach-specialist 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。

outreach-specialist 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,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 18,972。

总安装 5,826周安装 238GitHub Stars 141下载 1,866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:outreach-specialist(外展专家)
来源仓库:https://github.com/ognjengt/founder-skills
仓库路径:skills/outreach-specialist
安装命令:
npx skills add https://github.com/ognjengt/founder-skills --skill outreach-specialist
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/ognjengt/founder-skills --skill outreach-specialist

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。

outreach-specialist 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词快速定位候选结果。通过 npx skills add 命令从指定 GitHub 仓库安装。使用前需确认权限范围、维护状态及是否触发联网或文件操作。

建议结合原始 README 核验具体用法和功能边界。

来源仓库内路径:skills/outreach-specialist

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/ognjengt/founder-skills --skill outreach-speci…;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

outreach-specialist 怎么安装?

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

outreach-specialist 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。

outreach-specialist 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。

outreach-specialist 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。

outreach-specialist 用的人多吗?

公开数据是累计安装 5,826 次,近一周安装 238 次,下载 1,866 次,GitHub 141 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。

outreach-specialist 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。
  • 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
outreach-specialist

外展专家 · 本页

5,826141只读未明确通过

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

Outreach Specialist

Purpose

Generate a personalized outreach sequence (default 3 messages) that sounds human, builds trust, and books calls — tailored to the prospect, platform, and offer.


Execution Logic

Check $ARGUMENTS first to determine execution mode:

If $ARGUMENTS is empty or not provided:

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.

If $ARGUMENTS contains content:

Proceed immediately to Task Execution (skip the "loaded" message).


Task Execution

When user requirements are available (either from initial $ARGUMENTS or follow-up message):

1. MANDATORY: Read Reference Files FIRST

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:

  • outreach-templates.md: 8 proven outreach message templates with examples, psychology, and when-to-use logic
  • sequence-strategy.md: Follow-up sequence structures, timing, and platform-specific rules

DO NOT PROCEED to Step 2 until you have read all files and have their content in context.

2. Check for Business Context

Check if FOUNDER_CONTEXT.md exists in the project root.

  • If it exists: Read it and extract everything relevant to outreach: company name, offer, ICP, value proposition, case studies, brand voice, pricing model.
  • If it doesn't exist: Proceed using defaults from "Defaults & Assumptions."

3. Analyze Input & Determine What's Missing

From the user's requirements, extract:

  • Who they're reaching out to (ICP, role, company type)
  • What they're offering (product, service, specific solution)
  • What platform (LinkedIn DM, email, X DM, Instagram DM, other)
  • The goal (book a call, get a reply, send a lead magnet, get a referral)
  • Available proof (case studies, results, testimonials, metrics)
  • Sequence length (default: 3 messages if not specified)

4. Ask Diagnostic Questions (If Needed)

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):

#QuestionWhy it mattersSkip if...
1Are you reaching out on LinkedIn, email, or another platform?Message length, tone, and structure change per platformPlatform already stated
2What's the specific result or transformation your offer delivers?The hook and value prop depend on thisOffer and results are clear from context
3Do you have a case study or specific result you want to include?Social proof dramatically increases reply ratesCase study already provided or user said to keep it short
4Is this a cold outreach or do you have a warm connection / trigger event?Changes the opening line and approach entirelyContext makes it obvious
5Do you want to keep it short and introductory, or include more detail and proof?Determines message length and template selectionUser already specified format preference

Ask up to 4 questions per batch. Stop as soon as you have enough to write a confident sequence.

5. Select Templates & Build the Sequence

Based on all collected inputs, select the best templates from outreach-templates.md:

Template Selection Logic:

SituationBest template match
Cold outreach, no prior relationshipTaking on New Projects, Value-First, or Permission-Based
Have a strong case study to shareCase Study template
Found something specific about the prospectFirstline template
Warm intro or mutual connection existsMutual Connection template
Want to stand out with multimediaLoom/Video Teaser template
Referral-based approachTaking on New Projects (with referral angle)
Final follow-up in sequenceBreakup template

Sequence Structure (default 3 messages):

  • Message 1 (Day 1): Initial outreach — the hook. Use the strongest template for the situation.
  • Message 2 (Day 3-4): Follow-up — add value, share proof, or reframe the ask. Never just "bumping this up."
  • Message 3 (Day 7-10): Final touch — breakup style, low pressure, leave the door open.

If the user requests more or fewer messages, adjust accordingly.

6. Write the Sequence

For each message in the sequence:

  1. Start from the selected template as your structural base
  2. Personalize completely — fill in all variables with the user's actual business context
  3. Follow all Writing Rules below
  4. Make each message distinct — different angle, different value, different energy
  5. Include clear next steps — every message needs a soft CTA

7. Format and Verify

  • Structure output according to Output Format section
  • Complete Quality Checklist self-verification before presenting output
  • Read each message out loud in your head — if it sounds like a template or like AI wrote it, rewrite it

Writing Rules

Hard constraints. No interpretation.

Core Rules

  • Sound human. If it reads like a template, it's bad. Every message should feel like one person wrote it to one other person.
  • No em dashes. Never use "—" in outreach messages. Use commas, periods, or line breaks instead.
  • No AI slang. Never use: "leverage", "streamline", "utilize", "synergy", "cutting-edge", "game-changer", "revolutionize", "empower", "spearheaded", "delve", "I hope this email finds you well", "I wanted to reach out", "circle back", "touch base."
  • Keep it short. LinkedIn DMs: under 300 characters for first message. Emails: under 100 words for cold first touch. Every word must earn its place.
  • One CTA per message. Never ask for two things. One clear next step.
  • Specific over vague. "Increased MRR by 11% in 45 days" beats "helped grow revenue." Always.
  • Lead with them, not you. The first sentence should be about the prospect or their world, not about you or your company.
  • No exclamation marks in first messages. They signal desperation. Save energy for follow-ups where appropriate.
  • Lower the commitment bar. "Quick 10-min chat" beats "schedule a call." "Can I send a 2-min video?" beats "let's set up a demo."
  • Active voice only. Never passive.

Platform-Specific Rules

  • LinkedIn DMs: Ultra-short. No subject line. First message under 300 characters. Conversational. No links in first message (LinkedIn suppresses them). Follow-up can include links.
  • Email: Subject line required. Keep it 3-5 words, lowercase, no clickbait. Body under 100 words for first touch. Signature should be minimal (name, title, company).
  • X/Twitter DMs: Even shorter than LinkedIn. Under 280 characters. Very casual tone. No formalities.
  • Instagram DMs: Short. Casual. Can reference their content. Under 200 characters.

Follow-Up Rules

  • Never say "just following up" or "bumping this up." Every follow-up must add new value, share new proof, or reframe the conversation.
  • Change the angle. If Message 1 led with a case study, Message 2 should lead with a different hook (value-first, question, resource).
  • Increase urgency gradually. Message 1 is soft. Message 2 adds a reason to act. Message 3 is the breakup — low pressure, high respect.
  • Space them out. Day 1, Day 3-4, Day 7-10. Never back-to-back days.

Tone Rules

  • Write like you're texting a professional friend, not writing a cover letter.
  • Friendly but not desperate. Confident but not arrogant.
  • Match the platform's native tone. LinkedIn is slightly more professional than X DMs.
  • If the user's FOUNDER_CONTEXT has a brand voice, blend it in naturally.

Output Format

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.

References

These files MUST be read using the Read tool before generating any messages (see Step 1):

FilePurpose
./references/outreach-templates.md8 proven outreach message templates with examples, psychology, and when-to-use logic
./references/sequence-strategy.mdFollow-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.


Quality Checklist (Self-Verification)

Before finalizing output, verify ALL of the following:

Pre-Execution Check

  • I read ./references/outreach-templates.md before writing messages
  • I read ./references/sequence-strategy.md before writing messages
  • I have all templates and sequence patterns in context
  • I only asked questions the context didn't already answer

Message Quality Check

  • Every message sounds like a real human wrote it, not AI
  • No em dashes anywhere in the output
  • No AI slang (leverage, streamline, utilize, synergy, etc.)
  • No "just following up" or "bumping this" in follow-ups
  • Each message has exactly ONE clear CTA
  • First sentence of each message is about the prospect, not about you
  • Specific numbers and results used where possible
  • Messages are within platform character/word limits

Sequence Check

  • Each message in the sequence has a different angle/hook
  • Follow-ups add new value (not just reminders)
  • Urgency increases gradually across the sequence
  • Timing between messages follows the recommended spacing
  • Final message is low-pressure breakup style

Personalization Check

  • Messages use the prospect's actual context (not generic placeholders)
  • FOUNDER_CONTEXT.md brand voice is blended in (if it exists)
  • Case studies/proof points are specific and real (from user input)
  • Platform tone matches (LinkedIn = professional casual, X = casual, Email = concise professional)

Output Check

  • Output matches the Output Format exactly
  • Every message is ready to copy-paste and send, no [brackets] or placeholders
  • Messages are appropriate length for the platform

If ANY check fails, revise before presenting.


Defaults & Assumptions

Use these unless the user overrides:

  • Sequence length: 3 messages (initial + 2 follow-ups)
  • Platform: LinkedIn DM (most common for B2B outreach)
  • Goal: Book a discovery call
  • Tone: Friendly, direct, peer-to-peer
  • First message length: Under 300 characters for DMs, under 100 words for email
  • Follow-up spacing: Day 1, Day 3-4, Day 7-10
  • CTA style: Low-commitment ask ("quick 10-min chat", "can I send a short video")
  • Approach: Cold outreach (no prior relationship assumed)

Document any assumptions made in the output.

平台分布

Codex

35.93%
按下载量换算670

Claude

30.76%
按下载量换算574

Cursor

19.04%
按下载量换算355

Gemini CLI

8.84%
按下载量换算165

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

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。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