
cold-email-outreach
End-to-end cold email outreach orchestration. Handles goal alignment, lead ingestion from any source (CSV, paste, CRM export, database), sequence design, email generation, campaign setup in the user's chosen outreach tool, and launch. Tool-agnostic — supports Smartlead (full MCP automation), Instantly, Lemlist, Apollo, or manual CSV export.
- Installs
- 58
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/gooseworks-ai/goose-skills --skill cold-email-outreach- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads cold-email-outreach automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Cold Email Outreach
The final mile of the outbound pipeline. Takes leads from wherever the user has them, builds email sequences, loads campaigns into the user's chosen outreach tool, and launches.
Tool-agnostic: Asks the user which outreach platform they use. Defaults to Smartlead if they have MCP tools configured. Falls back to CSV export for any other tool or manual workflow.
When to Use
Use this skill when:
- User says "launch a campaign", "send outreach", "email these leads", "set up cold email"
- User has a list of leads and wants to run an outbound email campaign
- User wants to create and configure a campaign in Smartlead or another outreach tool
Supported Outreach Tools
This skill does NOT assume a specific tool. It asks first, then adapts.
| Tool | Integration | How It Works |
|---|---|---|
| Smartlead (default) | MCP tools (mcp__smartlead__*) | Full automation: create campaign, add sequences, import leads, allocate mailboxes, configure schedule, launch |
| Instantly | CSV import | Generate CSV matching Instantly's import format, user uploads manually |
| Lemlist | CSV import | Generate CSV with Lemlist-compatible columns |
| Apollo | CSV import | Generate CSV matching Apollo sequence import format |
| Manual / Other | CSV + instructions | Export leads + emails as generic CSV, provide setup instructions |
Tool selection logic:
- Ask user in Phase 0: "Which outreach tool do you use?"
- If Smartlead → use MCP tools for full automation
- If Instantly / Lemlist / Apollo → generate tool-specific import CSV
- If Other or unknown → generate generic CSV (
email,first_name,last_name,company,title,subject,bodyper touch) and ask user for their tool's import requirements
Prerequisites
Environment Variables
For Smartlead (full automation):
SMARTLEAD_API_KEY=your_api_key_here
All Smartlead API calls go to https://server.smartlead.ai/api/v1 with ?api_key=$SMARTLEAD_API_KEY appended. Rate limit: 10 requests per 2 seconds.
For CSV-based tools: No env vars needed.
Phase 0: Intake
Ask all questions at once. Organize by category. Skip any already answered.
Campaign Goal
- What's the objective? (book meetings, drive demo requests, get replies, nurture)
- What's the outreach angle or hook? (hiring signal, competitor displacement, event-based, pain-based, cold database)
- What should we name this campaign?
Outreach Tool
- Which outreach tool do you use? (Smartlead / Instantly / Lemlist / Apollo / Other / Just give me a CSV)
Lead Source
- Where are your leads? Accept any of these:
- CSV file — read the file, map columns to required fields
- Pasted list — names, emails, companies pasted directly
- CRM export — Salesforce, HubSpot, or other CRM data
- Database query — if the user has a database, help them query it
- Upstream output — data from a prior task in this conversation
- Any exclusions? (specific companies, recently contacted leads, certain titles)
- Max campaign size? (default: 200)
Minimum required per lead: email address. Nice to have: first_name, last_name, company, title.
Sequence Design
- How many touches? (default: 3)
- Timing between touches? (default: Day 1 / Day 5 / Day 12)
- Personalization tier? (Tier 1: merge fields only / Tier 2: segment-specific / Tier 3: unique per lead)
Sending Config (skip if CSV export)
- Which email accounts should send? (list accounts or "use all available")
- Sending schedule? (default: Mon-Fri 8am-5pm in recipient's timezone)
- Daily send limit per account? (default: 30/day)
- Track opens and clicks? (default: opens yes, clicks no)
Phase 1: Lead Ingestion
Parse Leads
Accept leads from whatever source the user provides:
- CSV file: Read the file. Flexibly match columns:
email(required) — also matchesEmail,email_addressfirst_name— also matchesfirstname,first,First Namelast_name— also matcheslastname,last,Last Namecompany_name— also matchescompany,organization,Company- Any extra columns become custom fields
- Pasted data: Parse whatever format the user provides. Extract emails, names, companies.
- CRM/Database: Help the user query or export, then parse the result.
Validate & Deduplicate
- Remove rows without a valid email
- Deduplicate by email (keep first occurrence)
- Report: total rows, valid, invalid, duplicates removed
Present & Confirm
Show a sample table (10-15 leads) with:
- Name, Title, Company, Email
Tell user: total eligible leads, how many were invalid/removed.
Ask user to confirm or adjust before proceeding.
Phase 2: Sequence Design
Present the sequence plan as a table before writing any copy:
| Touch | Day | Email Type | Framework | CTA |
|---|---|---|---|---|
| 1 | 1 | Cold intro | Signal-Proof-Ask | 15-min call |
| 2 | 5 | New angle / asset | PAS | Resource offer |
| 3 | 12 | Social proof | BAB | Open to chat? |
Get user approval on the structure before generating copy in Phase 3.
Phase 3: Email Generation
Write the email copy directly using these guidelines.
Email Structure Formula
Every cold email follows this skeleton:
Hook (1 sentence) → Evidence (1-2 sentences) → Offer (1 sentence)
Word count targets:
- Cold intro (Touch 1): 50-90 words
- Follow-up (Touch 2-3): 30-50 words
- Breakup (final touch): 20-40 words
By Personalization Tier
Tier 1 (Generic): Generate one template per touch with merge fields ({first_name}, {company}, {title}). Same template for all leads.
Tier 2 (Segment): Generate one template per segment per touch. Segments are defined by role, industry, or signal type. Swap pain points and proof points between segments.
Tier 3 (Deep): Generate unique email per lead per touch. Cap at 50 leads — recommend Tier 2 above that volume.
Hard Rules
- No filler openers. Never "I hope this finds you well"
- No "just checking in" follow-ups. Every touch adds a new reason to reply
- Under 150 words per email. Most should be 80-120.
- One CTA per email. Always low-friction.
- No selling in the first sentence. Lead with them, not you.
- Subject lines under 50 chars. No caps, no exclamation marks, no emoji.
- Sign off with name only. No "Best regards."
Review Loop
- Generate sample emails for 3-5 leads first
- Present to user for review
- Iterate until approved (max 3 rounds)
- Generate remaining emails after approval
Phase 4: Campaign Setup
If Smartlead (MCP Automation)
Full automation via MCP tools. Execute in this order:
Step 1: Find and allocate mailboxes
mcp__smartlead__get_email_accounts
Returns all email accounts with id, from_email, from_name, daily_sent_count, is_smtp_success, is_imap_success.
To find free mailboxes (not already assigned to active campaigns):
- Fetch all campaigns:
mcp__smartlead__get_campaigns - For each campaign with status
ACTIVEorSTARTED, fetch its email accounts:mcp__smartlead__get_campaign_email_accounts - Build a set of all
email_account_idvalues currently assigned to active campaigns - A mailbox is "free" if its
idis NOT in the active set ANDis_smtp_success= true ANDis_imap_success= true - Sort free mailboxes by
daily_sent_countascending (prefer least-used) - Select the requested number of free mailboxes
If fewer free mailboxes than requested, tell the user and ask how to proceed.
Present available/selected accounts to user for confirmation.
Step 2: Create campaign
mcp__smartlead__create_campaign
name: {campaign_name}
Save the returned campaign_id.
Step 3: Add sequence steps
mcp__smartlead__save_campaign_sequences
campaign_id: {campaign_id}
sequences: [
{ seq_number: 1, subject: "...", email_body: "...", seq_delay_details: { delay_in_days: 0 } },
{ seq_number: 2, subject: "...", email_body: "...", seq_delay_details: { delay_in_days: 4 } },
{ seq_number: 3, subject: "...", email_body: "...", seq_delay_details: { delay_in_days: 7 } }
]
Merge variable mapping: Convert {first_name} → {{first_name}}, {company} → {{company}} (Smartlead uses double-brace syntax).
Note: Blank subject on emails 2+ makes them send as replies in the same thread.
Step 4: Import leads (batch 100)
mcp__smartlead__add_leads_to_campaign
campaign_id: {campaign_id}
lead_list: [{ email: "...", first_name: "...", last_name: "...", company_name: "...", ... }]
Smartlead accepts max 100 leads per call. Chunk the list and call for each batch. Extra columns become custom_fields.
Step 5: Assign sending accounts
mcp__smartlead__add_email_accounts_to_campaign
campaign_id: {campaign_id}
email_account_ids: [...]
Step 6: Set schedule
mcp__smartlead__update_campaign_schedule
campaign_id: {campaign_id}
schedule: {
timezone: "America/New_York",
days_of_the_week: [1, 2, 3, 4, 5],
start_hour: "08:00",
end_hour: "18:00",
min_time_btw_emails: 10,
max_new_leads_per_day: 20
}
days_of_the_week: 0=Sunday, 1=Monday, ..., 6=Saturday.
Step 7: Configure settings
mcp__smartlead__update_campaign_settings
campaign_id: {campaign_id}
settings: {
track_settings: [],
stop_lead_settings: "REPLY_TO_AN_EMAIL",
send_as_plain_text: false,
follow_up_percentage: 100
}
Allowed track_settings: DONT_TRACK_EMAIL_OPEN, DONT_TRACK_LINK_CLICK, DONT_TRACK_REPLY_TO_AN_EMAIL
Allowed stop_lead_settings: REPLY_TO_AN_EMAIL, CLICK_ON_A_LINK, OPEN_AN_EMAIL
If CSV-Based Tool (Instantly, Lemlist, Apollo, Other)
Step 1: Generate CSV
Columns depend on personalization tier:
Tier 1 (same template for all):
- CSV columns:
email,first_name,last_name,company,title,custom_field_1(signal/hook) - Separate file with sequence templates (subjects + bodies with merge fields)
Tier 2/3 (per-segment or per-lead emails):
- CSV columns:
email,first_name,last_name,company,title,touch_1_subject,touch_1_body,touch_2_subject,touch_2_body,touch_3_subject,touch_3_body
Step 2: Save file
Save to the current working directory:
{campaign-name}-{YYYY-MM-DD}.csv
Step 3: Provide tool-specific import instructions
Instantly:
- Upload CSV → Sequences → Create new sequence
- Map columns: Email → email, First Name → first_name, etc.
- Paste sequence templates into each step
- Set delays between steps
Lemlist:
- People → Import → Upload CSV
- Map custom variables to columns
- Create campaign → add email steps → insert variables
Apollo:
- Sequences → Create Sequence → add email steps
- Contacts → Import → Upload CSV
- Add imported contacts to sequence
Other / Manual:
- Provide the CSV path and explain the column structure
- Ask user what format their tool expects, adjust if needed
Phase 5: Review & Launch
Present campaign summary:
Campaign: {name}
Leads: {count}
Sequence: {touches} touches over {days} days
Sending: {accounts} accounts × {daily_limit}/day = {daily_volume} emails/day
Estimated completion: {date}
Tool: {smartlead/instantly/etc.}
Hard Approval Gate
Do NOT activate the campaign without explicit user confirmation. Present the summary, then ask: "Ready to launch? Type 'yes' to activate."
- Smartlead:
mcp__smartlead__update_campaign_status→ set status toSTART - CSV tools: Tell user the file is ready for import, provide the file path
Smartlead API Reference
All endpoints use base URL https://server.smartlead.ai/api/v1 with ?api_key= query param.
| Endpoint | Method | Purpose |
|---|---|---|
/campaigns/create | POST | Create a new campaign |
/campaigns | GET | List all campaigns |
/campaigns/{id} | GET | Get campaign by ID |
/campaigns/{id}/schedule | POST | Set campaign schedule |
/campaigns/{id}/settings | POST | Update tracking/stop settings |
/campaigns/{id}/sequences | POST | Save email sequences |
/campaigns/{id}/leads | POST | Add leads (max 100 per call) |
/campaigns/{id}/email-accounts | GET | List mailboxes on a campaign |
/campaigns/{id}/email-accounts | POST | Assign mailboxes to campaign |
/campaigns/{id}/status | POST | Change campaign status (START/PAUSED/STOPPED) |
/campaigns/{id}/analytics | GET | Top-level campaign analytics |
/email-accounts/ | GET | List all email accounts (offset/limit) |
Cost
| Component | Cost |
|---|---|
| Smartlead campaign setup | Free (API included with Smartlead plan) |
| CSV export | Free |
| Email copy generation | Free (LLM reasoning) |
Error Handling
| Error | Fix |
|---|---|
SMARTLEAD_API_KEY not set | Ask user to add it to .env or export it |
| Smartlead rate limit (429) | Wait 2 seconds and retry |
| Lead upload fails | Check email format, retry batch |
| No free mailboxes | Show all accounts, ask user which to use |
| Campaign creation fails | Check API key validity |
FAQ
What does the cold-email-outreach skill do?
End-to-end cold email outreach orchestration. Handles goal alignment, lead ingestion from any source (CSV, paste, CRM export, database), sequence design, email generation, campaign setup in the user's chosen outreach tool, and launch. Tool-agnostic — supports Smartlead (full MCP automation), Instantly, Lemlist, Apollo, or manual CSV export.
How do I install cold-email-outreach?
Run npx skills add https://github.com/gooseworks-ai/goose-skills --skill cold-email-outreach in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/cold-email-outreach/ (personal) or .claude/skills/cold-email-outreach/ (project).
Which AI agents can use cold-email-outreach?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is cold-email-outreach safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains cold-email-outreach?
It is published by gooseworks-ai in gooseworks-ai/goose-skills. It has 58 recorded installs.
More from gooseworks-ai/goose-skills
restaurant-booking
gooseworks-ai/goose-skills
Book restaurant reservations via browser automation. Use when asked to make dinner reservations, book a table, or find availability at restaurants. Supports OpenTable, Resy, and direct restaurant booking sites.
send-sms-textbelt
gooseworks-ai/goose-skills
Send SMS text messages to phone numbers. Use when the user asks to send a text, send an SMS, text someone, message a phone number, or send a notification via text message.
job-scraper
gooseworks-ai/goose-skills
Search for job postings across LinkedIn and Indeed. Use when users want to find open roles, monitor hiring signals, identify companies hiring for specific positions, or research competitor hiring activity. Returns job title, company, location, salary, description, seniority level, and direct apply URLs. No login or cookies required.
linkedin-outreach
gooseworks-ai/goose-skills
End-to-end LinkedIn outreach campaign builder. Takes leads from Supabase, upstream skills, or CSV. Aligns on campaign goal and tone, writes personalized LinkedIn message sequences (connection request + follow-ups + optional InMail), presents for review, and exports for the user's outreach tool (Dripify, Botdog, Expandi, or manual CSV). Logs to Supabase outreachlog.
find-skill
gooseworks-ai/goose-skills
Find and install skills from the Orthogonal skill library. Use when you need capabilities you don't have, want to discover available skills, or need to add new tools to your agent.
linkedin-job-scraper
gooseworks-ai/goose-skills
Scrapes LinkedIn job postings using the JobSpy library (python-jobspy). Use this skill whenever the user wants to find jobs on LinkedIn, search for open roles, pull job listings, build a job pipeline, source job targets for GTM research, or monitor hiring signals. Even if the user just says "find me some jobs" or "what roles is [company] hiring for", use this skill. It runs a local Python script that outputs a CSV of job postings with title, company, location, salary, job type, description, and direct URLs.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。