Outreach Sequence Builder logo

Outreach Sequence Builder

Organization
Amazon-Quick
outreach-sequence-builder

Creates multi-touch sales outreach sequences (email, LinkedIn, phone scripts) personalized to each prospect. Generates complete cadences with timing, subject lines, body copy, and follow-up logic. Use when user says 'write outreach emails', 'create a sales sequence', 'help me follow up with prospects', 'draft cold emails', 'build a cadence', 'write LinkedIn messages', 'create touchpoints', or 'cold outreach for [product/audience]'.

Overview

PublisherAmazon-Quick
RepositoryAmazon-Quick-official-catalog
Skill nameoutreach-sequence-builder
Stars
50
Forks
4
Bundled files
1
LicenseMIT-0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Amazon-Quick on GitHub. Read the source before you install it.

Installation

Install the Outreach Sequence Builder AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/sales/outreach-sequence-builder
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Amazon-Quick/Amazon-Quick-official-catalog.git /tmp/Amazon-Quick-official-catalog
mkdir -p .claude/skills
cp -r /tmp/Amazon-Quick-official-catalog/skills/sales/outreach-sequence-builder .claude/skills/outreach-sequence-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Outreach Sequence Builder in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Outreach Sequence Builder on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Outreach Sequence Builder is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Overview

Creates multi-touch outreach sequences for small businesses. Each sequence combines email, LinkedIn, and phone scripts with personalization, timing logic, and conditional branching. Pulls context from lead-prospector when available and stages drafts for sending.

Workflow

<Definition - Standard Cadence Template>

DayChannelPurposeAngle
1EmailOpen cold, value hookLead with insight about their industry/company
3LinkedInConnection requestShort personalized note referencing email
5EmailFollow-up, social proofShare relevant case study or result
8LinkedInEngage with their contentComment/like their posts genuinely
10EmailBreakup attempt, new angleProvide resource regardless of response
14PhoneDirect callReference previous touches
21EmailFinal value dropLeave door open, no pressure
</Definition - Standard Cadence Template>

<Definition - C-Suite Adjustments> If prospect is C-suite or very senior at a large enterprise:

  • Reduce total touches (5 max instead of 7)
  • Wider spacing between touches (3-5 days instead of 2-3)
  • Suggest alternative entry points: executive assistant, VP-level champion, mutual connection, warm introduction
  • Set expectations: lower response rates, longer cycles
  • Lead with board-level insights, not product features </Definition - C-Suite Adjustments>

<Definition - Conditional Branching>

TriggerAction
Positive replyExit sequence, send meeting confirmation
"Not now" replyPause, set 60-day reminder
Negative replyExit, log reason, thank gracefully
No reply after all touchesMove to quarterly nurture list
Out of officePause sequence, resume when they're back
Booking link clickedExit, send calendar confirmation
</Definition - Conditional Branching>

<Definition - Delivery Modes>

ModeWhenWhat Happens
Stage drafts (default)Email connectedTouch 1 sent now; Touch 2+ saved as drafts with scheduled dates
Send Touch 1 onlyUser wants to test firstSends first email, presents rest for approval
Copy to clipboardNo email connectorFull sequence formatted in chat
</Definition - Delivery Modes>

<Definition - Skill-Ready Outputs> Two formatted blocks always included:

  1. Active Sequence Tracking table (for follow-up-cadence): Contact, Company, Current Touch, Next Send Date, Status
  2. Outreach Activity table (for deal-pipeline-manager): Prospect, Touches Sent, Last Response, Next Action, Status </Definition - Skill-Ready Outputs>

<Workflow - Build Sequence description="Create a complete multi-touch outreach sequence for one or more prospects." tools=[web_search, url_fetch, run_python, file_write, open_in_session_tab] triggers=["write outreach emails", "create a sales sequence", "draft cold emails", "build a cadence", "write LinkedIn messages", "cold outreach for"]

  1. [Agent] Check for lead-prospector context in current session. If available, auto-load: prospect company, contact name + title, personalization hooks, warm/cold status. Validate: If data exists, at least company + contact + 1 hook loaded. If fails: Skip. Proceed to step 2 to gather context manually.

  2. [Decide] Is context sufficient (prospect name/company, user's product/service, at least 1 differentiator)?

    • Yes (from lead-prospector or user): Confirm briefly. "Proceeding with [contact] at [company]. Top hook: [hook]. Correct?"
    • Partially: Ask only what is missing (tone preference, specific offer for this prospect).
    • No: Ask "What do you sell, who is the prospect (name + company), and what makes you different from alternatives?" Validate: Have prospect details, product/service, and at least one differentiator. If fails: Cannot write effective copy without differentiator. Re-ask.
  3. [Agent] Research the prospect if personalization hooks are thin (fewer than 2). Search for recent LinkedIn posts, company news, job postings, tech stack. If hooks already loaded from lead-prospector and recent (< 90 days), skip. Validate: At least 2 specific, verifiable personalization hooks available. If fails: Ask user for any known details. Note limited personalization.

  4. [Agent] Design sequence architecture. Apply <Definition - Standard Cadence Template> adjusted for: prospect seniority (apply <Definition - C-Suite Adjustments> if applicable), industry response patterns, number of touches requested. Output cadence map: Day, Channel, Purpose, Angle per touch. Validate: Timing is appropriate for seniority. Channels are diverse. Total touches match request or adjusted default. If fails: Fall back to standard 7-touch template unchanged.

  5. [Agent] Write complete copy for every touch. For Touch 1: write 2 variants (A: insight-led hook, B: direct value prop). For all others: one version each. Apply copy rules: under 125 words per email, subject lines under 6 words, each touch adds new value, personalization references real details. Validate: Every email under 125 words. Every subject under 6 words. No touch says "just following up." Each touch adds distinct new value. If fails: Rewrite offending touches. If copy is too generic, ask user for more prospect context.

  6. [Agent] Add conditional branching per <Definition - Conditional Branching>. Write specific response emails for: positive reply (meeting confirmation), "not now" (acknowledge + set reminder), negative (graceful exit). Validate: All 6 trigger scenarios covered with specific copy or action. If fails: Include basic branch logic (reply = exit, no reply = continue).

  7. [Ask user] Present complete sequence: cadence map, A/B variants for Touch 1, full copy for all touches, conditional logic. Ask which variant to use and confirm ready to deliver. Validate: User approves sequence or requests edits. If fails: Revise per feedback.

  8. [Agent] Deliver per <Definition - Delivery Modes>. If email tools are available, stage Touch 1 as ready-to-send and remaining touches as scheduled drafts. If unavailable, format full sequence in chat. Validate: Delivery completed in user's preferred mode. If fails: Display full sequence as formatted text.

  9. [Agent] Produce skill-ready outputs per <Definition - Skill-Ready Outputs>. Offer to save as reusable template: "Save this as a template? (e.g., 'SEO Agency to Dentist Owner')" Validate: Both skill-ready output blocks present. If fails: Add missing outputs.

</Workflow - Build Sequence>

<Template - Sequence Output>

Outreach Sequence: [Contact] at [Company]

Cadence Map:

DayChannelPurposeAngle

Touch 1 - Variant A (Insight-led): Subject: [under 6 words] [Body under 125 words]

Touch 1 - Variant B (Direct value prop): Subject: [under 6 words] [Body under 125 words]

Touch 2-N: [Full copy per touch]

Conditional Branching: [Response handling per scenario]

Active Sequence Tracking (for follow-up-cadence)

| Contact | Company | Current Touch | Next Send Date | Status |

Outreach Activity (for deal-pipeline-manager)

| Prospect | Touches Sent | Last Response | Next Action | Status | </Template - Sequence Output>

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Outreach Sequence Builder AI skill do?

Creates multi-touch sales outreach sequences (email, LinkedIn, phone scripts) personalized to each prospect. Generates complete cadences with timing, subject lines, body copy, and follow-up logic. Use when user says 'write outreach emails', 'create a sales sequence', 'help me follow up with prospects', 'draft cold emails', 'build a cadence', 'write LinkedIn messages', 'create touchpoints', or 'cold outreach for [product/audience]'.

Why use Outreach Sequence Builder on TypingMind?

Because you install it once and use it with any model. Outreach Sequence Builder is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Outreach Sequence Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/sales/outreach-sequence-builder. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Outreach Sequence Builder?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Outreach Sequence Builder?

As many as you like. As long as a model supports skills, you can use Outreach Sequence Builder with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Outreach Sequence Builder AI skill free?

Yes. It is published on GitHub by Amazon-Quick under the MIT-0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇