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.
Install / Use
npx skills add gooseworks-ai/goose-skills --skill write-outreach-draft-sequenceInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
CommunicationSupported Platforms
Tags
Our assessment of write-outreach-draft-sequence
write-outreach-draft-sequence scores 81/100 on our quality scale, 365th of 401 Communication skills we index.
Its SKILL.md is 3.6 KB long, split into 4 sections with 1 code example: a solid amount of guidance for an agent.
With 1,222 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated 33 days ago, so write-outreach-draft-sequence is actively maintained.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
write-outreach-draft-sequence compared with similar skills
All 4 of these similar skills score higher than write-outreach-draft-sequence; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| write-outreach-draft-sequence (this skill)by gooseworks-ai | 81 | 1.2k | 33d ago | SKILL.md |
| crawl4aiby unclecode | 100 | 86.3k | 3d ago | MCP Server |
| algorithmic-artby anthropics | 100 | 177.9k | 33d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 33d ago | SKILL.md |
| designby nextlevelbuilder | 100 | 137.2k | 11d ago | SKILL.md |
Frequently asked questions
- How do I install write-outreach-draft-sequence?
- Run
npx skills add gooseworks-ai/goose-skills --skill write-outreach-draft-sequence. The install tabs above show the steps for each supported agent. - Which AI agents does write-outreach-draft-sequence work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is write-outreach-draft-sequence safe to use?
- It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is write-outreach-draft-sequence still maintained?
- The repository was last updated 33 days ago, so write-outreach-draft-sequence is actively maintained.
Skill content
View source on GitHubname: write-outreach-draft-sequence description: >- 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. version: 0.1.1
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: <what>"), 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-NZwith a non-published address → no email, LinkedIn only; every email ends with the opt-out line you were given;EU-UK,UK-ltdand 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)
Related Skills
crawl4ai
86.3kOpen-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key. Join our Discord https://discord.gg/VuxzM8mtf
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
design
137.2kComprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG…
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
