Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计提醒

cold-outreach-sequence冷外展序列

Agent Skill

cold-outreach-sequence 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。

总安装

1,764

周安装

75

GitHub Stars

262

下载量

618
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:cold-outreach-sequence(冷外展序列)
来源仓库:https://github.com/brianrwagner/ai-marketing-skills
仓库路径:skills/cold-outreach-sequence
安装命令:
npx skills add https://github.com/brianrwagner/ai-marketing-skills --skill cold-outreach-sequence
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/brianrwagner/ai-marketing-skills --skill cold-outreach-sequence

简介

cold-outreach-sequence 构建人性化外展序列,替代群发式无效触达。

  • 区分单 prospects 双触点系统与多目标批量自动化两种模式。
  • 强调十分钟前期研究投入,引用具体公司细节打破 cold 印象。
  • 支持 A/B 测试与转化追踪,持续迭代优化 message 效果。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Cold Outreach Sequence

Here's what I've learned about cold outreach: the word "cold" is the problem.

Spray-and-pray templates don't work. 10 minutes of research + a specific reference = not cold anymore. This skill builds the second kind.


Mode

Detect from context or ask: *"One message, full sequence, or full outreach system?"*

ModeWhat you getBest for
quick1 connection request + 1 follow-up for a single prospectTesting an angle, one-off outreach
standardFull 4-touch sequence for a single prospectActive pipeline, individual targets
deepMulti-prospect sequence system + A/B variants + tracking frameworkLaunching an outreach campaign

Default: standard — use quick if they give you one name and say "draft something." Use deep if they're building a repeatable outreach engine.


Context Loading Gates

Before writing any message, collect:

  • Prospect name and company — full name, company, role/title
  • Research signals — run tool calls first (see below); do not write without them
  • Sender positioning — what does the sender do, for whom, with what result? (Use positioning-basics output if available)
  • Platform — LinkedIn DM, email, or both?
  • Batch size — how many prospects? (determines tier assignment)

Research tool calls — run before writing:

web_search('[Company] [Founder/Name] news 2026')
web_search('[Company] funding recent')
web_search('[Person name] [Company] LinkedIn')

Personalization constraint: Do not write a Tier 1 message without a named specific signal from research. If search yields 0 signals, default to Tier 3 and say so explicitly.


Phase 1: Research & Signal Assessment

For each prospect, document findings before drafting:

Signal types (ranked by message strength):

  1. Recent news event (funding, launch, hire, press) → strongest signal
  2. Recent LinkedIn post activity → strong signal
  3. Company stage/growth data → medium signal
  4. Role + industry awareness only → weak signal (Tier 3)

Personalization tier assignment:

Research ResultTierApproach
Named signal (news + post + context)Tier 1Fully custom, reference signal in every message
Company info + role contextTier 2Template + personalized opener
No signals foundTier 3Volume template, minimal customization

Phase 2: Sequence Generation

Connection Request (LinkedIn) — 300 chars max

Formula: [Specific observation from research] + [Simple reason to connect]

Rules:

  • No pitching
  • Prove you did research (name the signal)
  • One sentence, conversational
  • Never "I'd love to pick your brain"

By signal type:

Recent funding: "Congrats on the Series A — the [investor] backing is a smart signal. Would love to connect."

Recent post: "Your post on [specific topic] resonated — been thinking the same thing. Happy to connect."

News/launch: "Saw the [product] launch — [specific detail] is smart positioning. Would love to connect."

First Message (After Accept — Wait 24-48 Hours)

Formula: [Thanks] + [Bridge to relevance] + [Light value] + [Soft question]

Template:

Thanks for connecting. I work with [ICP description] on [specific outcome].

Curious — is [relevant function] something you own directly at [Company],
or is that still founder-led?

Happy to share what I'm seeing work at similar-stage companies either way.

Follow-Up #1 (Day 7)

Formula: [Light nudge] + [New signal or angle] + [Easy out]

Constraint: Do NOT write "following up" with nothing new. Add one new piece:

  • A relevant article or trend
  • A related insight you recently had
  • A connection to something they posted

Template:

Bumping this up — came across [specific article/trend/insight] and
thought of your situation at [Company].

[One sentence on why it's relevant to them.]

Happy to share more if useful. If not, no worries.

Follow-Up #2 (Day 14)

Shift to email if LinkedIn hasn't converted, or try a different angle.

Subject line options:

  • "[Company]'s [function] as you scale"
  • "Saw your [post/news] — quick thought"
  • "Question about [specific thing they're doing]"

Email structure:

[1-line hook tied to their specific situation]

[2-3 sentences: why you're reaching out + one proof point]

[Soft CTA — 1 sentence]

Break-Up Message (Day 21)

I'll assume timing isn't right — totally get it.

If [relevant pain point] becomes a priority down the road, happy to reconnect.
Best of luck with [specific thing they're working on based on research].

Post-break-up action: Add to 6-month re-engagement list with a resurface date.


Phase 3: Self-Critique Pass (REQUIRED)

After generating the full sequence, evaluate:

  • Does every message reference the specific signal from research, or are they generic?
  • Is the connection request under 300 characters?
  • Does the first message ask a question (invite dialogue) rather than pitch?
  • Does follow-up #1 add something genuinely new, or is it just "following up"?
  • Does the break-up message reference something specific about their situation?
  • Did I correctly assign the personalization tier, or am I over-personalizing a Tier 3 prospect?

Flag any issue: "The first message doesn't include a soft question — it reads as a pitch. Revised to invite dialogue."


Pipeline Tracking Table

Always output a tracking table for the batch:

| Prospect | Company | Platform | Tier | Sent Date | Response | Stage | Next Action | Resurface Date |
|---|---|---|---|---|---|---|---|---|
| [Name] | [Co] | LinkedIn | 1 | [date] | — | Connection sent | Wait 24-48h | — |
| [Name] | [Co] | Email | 2 | [date] | — | First email sent | Follow-up Day 7 | — |

Iteration Protocol

After each response (or non-response), ask:

  • Did the connection request get accepted? If low acceptance rate → revise the observation line
  • Did the first message get a reply? If no → was the question soft enough, or did it feel like a pitch?
  • Did follow-ups get ignored? If yes → try a different angle or acknowledge the silence directly

Output Structure

## Outreach Sequence: [Prospect Name] — [Date]

### Research Summary
- Signal type: [news / post / company info / none]
- Signal found: "[Specific detail]"
- Personalization tier: [1/2/3]
- Source: [URL or platform]

### Sequence

**Connection Request (LinkedIn):**
[Text — max 300 chars]

**First Message (Day 1-2 after accept):**
[Text]

**Follow-Up #1 (Day 7):**
[Text]

**Follow-Up #2 (Day 14):**
Platform: [LinkedIn / Email]
Subject: [if email]
[Text]

**Break-Up (Day 21):**
[Text]

### Pipeline Entry
| Prospect | Company | Platform | Tier | Stage | Next Action | Resurface Date |
|---|---|---|---|---|---|---|
| [Name] | [Co] | [Platform] | [Tier] | Connection sent | Wait 24-48h | — |

### Self-Critique Notes
[Any issues flagged + revisions made]

*Skill by Brian Wagner | AI Marketing Architect | brianrwagner.com*

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.57%
按下载量换算232

Claude

30.38%
按下载量换算188

Cursor

19.53%
按下载量换算121

Gemini CLI

10.39%
按下载量换算64

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 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills