Write Outreach Draft Sequence logo

Write Outreach Draft Sequence

OrganizationPopular
gooseworks-ai
write-outreach-draft-sequence

Step of the write-outreach playbook: the brief a helper follows to write one segment's email and LinkedIn sequence, first lines and replies from rows and an angle prepared earlier. Run write-outreach instead; not for direct use.

Overview

Publishergooseworks-ai
Repositorygoose-skills
Skill namewrite-outreach-draft-sequence
Stars
1.3K
Forks
219
Bundled files
1
LicenseMIT
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 gooseworks-ai on GitHub. Read the source before you install it.

Installation

Install the Write Outreach Draft Sequence 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/gooseworks-ai/goose-skills/tree/main/skills/marketing/write-outreach-draft-sequence
  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/gooseworks-ai/goose-skills.git /tmp/goose-skills
mkdir -p .claude/skills
cp -r /tmp/goose-skills/skills/marketing/write-outreach-draft-sequence .claude/skills/write-outreach-draft-sequence
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Write Outreach Draft Sequence 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 Write Outreach Draft Sequence 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 Write Outreach Draft Sequence 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.

draft-sequence

You are writing cold outreach for one segment of one brand. This brief is complete: don't load any skill, don't read playbook files, don't start other agents, make no GooseWorks calls. At most 3 web reads, only to re-check that a row's signal link still says what the row claims. Return in the shape at the end; no preamble.

Inputs (in the prompt): the brand, what it sells and its price; the sender (name, role); the segment and its angle — pain in the buyers' words (with the quote and link — or, with no quote bank, in our words labelled "not yet from buyers"), proof (a signed-off claim verbatim, or "proof needed: "), the ask; the sequence shape (touches, channels, days); the rows (name, title, company, signal + URL + date, hook + URL, region flag, email status); the brand's [outreach …] rules and voice notes; today's date.

Rules

  • Touch 1: first line = the row's signal or hook and why it matters to the pain; then one or two lines on the pain and what we do (plain product fact, or the signed-off proof verbatim); one ask; sign-off with the sender's first name. 50–90 words. Subject under 50 characters, lower-case, plain.
  • Follow-ups: each adds something new (a second pain, a short resource, signed-off proof, or a general practice framed as such — never an invented peer story) — never "bumping", "checking in", "circling back". 30–50 words, then 20–30 for the last, which leaves the door open without guilt. Same thread.
  • At most 6 touches in all per person (e.g. 4 emails, the connection request, one LinkedIn message).
  • LinkedIn: connection note ≤200 characters with no pitch, no ask, no link (free accounts get only a few notes a month — at volume, the invite goes without a note and the line moves to message 1); messages after accept are short, value first, one question; never the email's text.
  • First line per row: built only on that row's facts. Nothing invented — no compliments, mutual connections, numbers, customers or results. No hook → write "no personal hook" and use the segment opener.
  • Never: hype words (revolutionary, game-changing, cutting-edge, best-in-class), jargon (synergy, leverage, touch base), "hope this finds you well", fake "Re:", lying about how you found them, school, family, health, politics, location, "#OpenToWork", the funding amount as the opener, the predecessor of a new leader.
  • Proof: only the signed-off line you were given, verbatim. Anything else that sounds like a result → cut it and list it under "proof needed".
  • Region rules: UK-soletrader → a short letter instead of email and no DM; CASL / AU-NZ with a non-published address → no email, LinkedIn only; every email ends with the opt-out line you were given; EU-UK, UK-ltd and unknown-country rows' first email carries the source-and-object line.
  • Count words and characters; rewrite to fit, never cut a sentence off.

Return this shape

## <Segment>
Angle: pain "<their words>" (<link>) · proof: <verbatim or "proof needed: …"> · ask: <…>
Sequence: | day | channel | touch | subject | text | words/chars |
First lines: | row | first line | rests on (signal/hook URL, date) |
Letters (UK sole traders, if any): …
Replies: | category | answer |
Proof needed: …
Re-checked links: <n> held, <n> changed (which)

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 Write Outreach Draft Sequence AI skill do?

Step of the write-outreach playbook: the brief a helper follows to write one segment's email and LinkedIn sequence, first lines and replies from rows and an angle prepared earlier. Run write-outreach instead; not for direct use.

Why use Write Outreach Draft Sequence on TypingMind?

Because you install it once and use it with any model. Write Outreach Draft Sequence 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 Write Outreach Draft Sequence in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gooseworks-ai/goose-skills/tree/main/skills/marketing/write-outreach-draft-sequence. 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 Write Outreach Draft Sequence?

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 Write Outreach Draft Sequence?

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

Is the Write Outreach Draft Sequence AI skill free?

Yes. It is published on GitHub by gooseworks-ai under the MIT 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 👇