New: Earn 20% as an AgentAlley affiliate. Share your link and earn on every sale you refer. Join now New: Earn 20% as an affiliate. Join now

Ever creating outreach

Reach out

by swan-gtm · MIT license · ★ 159 on GitHub · updated Sep 23

Reach out cover

Use this skill whenever creating outreach — a cold email, a LinkedIn message, a follow-up, or a multi-step sequence — for a company, a contact, a list, or a signal. Use it even when the user doesn't say "outreach": any request to write…

---
name: "reach-out"
title: Reach out
description: |
  Use this skill whenever creating outreach — a cold email, a LinkedIn message, a follow-up, or a multi-step sequence — for a company, a contact, a list, or a signal. Use it even when the user doesn't say "outreach": any request to write to, contact, message, or get in front of a prospect or account goes through here. Covers picking the hook, matching the org's voice, choosing the sequence shape, and staging everything for approval. Trigger phrasings: "reach out to", "draft outreach", "email this company", "message this prospect", "follow up with", "build a sequence", "contact these visitors".

  Also use it for strategic outreach questions ("how should our cold emails sound", "what cadence should we run") — the output is then a point of view grounded in the org's saved voice, not a sequence.
category: Outreach
---

Produces a staged outreach sequence awaiting the user's approval, with the reasoning attached: who, why now, what hook.

### The motion table — this org's, not the skill's

This table is the org's motion library. It starts seeded and is meant to be edited — rows get added, renamed, and replaced as the org's motions take shape. Open the matching reference before drafting; follow its don'ts over generic instinct.

| Situation | Reference |
|---|---|

Overview

Produces a staged outreach sequence awaiting the user's approval, with the reasoning attached: who, why now, what hook.

Manual install (npx, ZIP)
Claude Codenpx skills add swan-gtm/gtm-skills --skill reach-out -g -a claude-code
Claude Code (manual)mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/swan-gtm/gtm-skills/tar.gz/e65d97205fd2 \ | tar -xz -C ~/.claude/skills --strip-components=3 gtm-skills-e65d97205fd2/skills/ido-goldberg/reach-out
Windows (PowerShell)New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/8c0f1cf5da562dff5f2c/reach-out.zip" -OutFile "$env:TEMP\reach-out.zip"; Expand-Archive "$env:TEMP\reach-out.zip" -DestinationPath "$HOME\.claude\skills" -Force
Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md7.7 KB
  • references/9 files · 29.6 KB
Read the files here
swan-gtm/e65d97210 files
SKILL.md
Show the full text80 lines

Produces a staged outreach sequence awaiting the user's approval, with the reasoning attached: who, why now, what hook.

The motion table — this org's, not the skill's

This table is the org's motion library. It starts seeded and is meant to be edited — rows get added, renamed, and replaced as the org's motions take shape. Open the matching reference before drafting; follow its don'ts over generic instinct.

Situation Reference
Named company, named contact, or a small account set references/targeted.md
An identified website visitor references/website-visitor.md
A recurring or scheduled list run, cold volume references/cold-list.md
Someone engaged with a post or profile on LinkedIn references/linkedin-engagement.md
Funding, hiring spree, leadership change, product launch references/company-signals.md
Form fill, content download, demo request, MQL, signup references/inbound-hand-raiser.md
Webinar or conference registrants, attendees, no-shows references/event-follow-up.md
Third-party intent data — category research, review-site activity references/intent-signals.md
The user gives feedback, wants outreach to sound or perform better, announces a strategy shift, or asks to set up the voice references/improve-outreach.md

No row matches (win-back, referral, reply handling) → run the procedure below and say so in the reasoning. A recurring motion with no row → propose creating its reference page and adding the row.

references/improve-outreach.md is how this skill becomes the org's: it says where every kind of feedback gets recorded. Open it whenever the user reacts to a draft — feedback that isn't written down is retraining that never happened.

This org's voice and rules

Nothing recorded yet. Org-wide rules from user feedback live here, one do/don't per line with its condition when it has one. These outrank everything below except the user's live instruction.

Anchor on the hook

Every message needs a reason it goes to this person now. Hook ladder: trigger event > relationship > their own content > company initiative > persona pain (usable, but say so in the reasoning). No hook → push back before drafting. NEVER invent a signal.

The hook informs the angle; it rarely appears in the copy. Tracking-type signals — website visits, intent data, profile views — NEVER appear in the message. A public event may be referenced once, later in the message, as an observation with its implication — NEVER as the opening sentence, never as a congratulation. Leading with someone's funding round or new hire is the clearest tell that a machine wrote the message.

Voice

Approved sends accumulate automatically as style examples. Examples carry the voice; this skill carries the strategy — when they contradict, the skill is right, because examples can't be unsaved and lag every course change. Imitate an example's tone and rhythm, never a choice that breaks a rule. NEVER imitate copy from skill text or another org. No examples yet? Draft anyway from what's loaded — ICP pains, value prop, personas — plainly and shortly, tell the user the voice is provisional, and offer the voice setup flow in references/improve-outreach.md. If a contradiction keeps recurring, run that page's course-correction flow.

Draft
  • Opener, email: the hook's implication, in the contact's frame. One sentence. The event or signal itself never opens the message.
  • Opener, LinkedIn: say who you are and what you want in the first line. A DM has no room for a warm-up observation — it reads as preamble and gets skipped.
  • Body: one researched detail max, reacted to rather than exhibited. One proof point max — attributed, sized to the company. Never a feature list, never an invented customer or stat. On LinkedIn, drop the proof point and the hard numbers entirely; the register is a message between two people, not a pitch.
  • CTA: one ask, and make it the smallest real thing that could land this week — a short list to run, one account to check, a sample to review. Offering to do concrete work, or asking for the raw material to do it, beats asking for time.
  • Pitch at the reader's altitude: C-level hears risk and strategy, VP hears performance, director hears operational pain.
  • Shape per email: signal → proof → ask (fresh trigger); problem → cost → fix (only when the pain is documented in the ICP); before → after → bridge (easy-to-picture change).
  • Draft in the language the org sells in — a wrong-language sequence is an error, not a style choice.
Cadence

The org's recorded cadence always wins; default: 3–5 steps, days ~0/3/7/14, single channel unless the motion says otherwise, never referencing one channel from the other. Every follow-up is shorter than the last, stands alone, and brings a genuinely new angle — new proof, sharper insight, useful asset, peer story — or gets skipped. Last touch: a 25–50 word breakup, door open, no new pitch — and once sent, honored. Multi-thread only for large accounts (~200+ employees), committee signals, or on request — different angle per contact, never the same email twice into one company.

The final gate

Run on every message before staging; a failed check means rewrite, not tweak:

  1. Delete the opener — still makes sense? The personalization is decoration; rebuild around the hook.
  2. Does the close contain the word "worth"? Rewrite it. "worth 15 minutes", "worth a quick look", "worth a conversation" — anyone who receives outbound has read them a hundred times, and they cost replies. Ask for the thing itself instead.
  3. Does sentence one name a funding round, a launch, a hire, or any other event? Rewrite — open with what it means for them, not with the news.
  4. Could this go to anyone else this week? Then it's a blast in costume.
  5. One CTA. 60–110 words, follow-ups shorter. Subject 2–5 words, lowercase, internal-looking. More "you" than "I/we".
  6. Email: is the proof a number or a name? "Helps teams like yours" is not proof.
  7. Read as the recipient with a full inbox: any reason to reply beyond politeness?
Stage

Check for an existing unsent sequence to the contact — edit, don't duplicate. Stage for manual approval with the reasoning: who, why now, what hook, which reference. NEVER auto-send unless the user says so in this conversation. NEVER attach files; link instead. A channel missing its contact data gets fixed or dropped.

What good looks like

A first-run draft — new org, zero examples — approved with a tweak, not a rewrite: a hook that fits nobody else this week, substance traceable to the org's ICP and value prop, nothing that smells like a template. Watch for: the proof point swelling into a feature list, the CTA collapsing into a calendar link, a segment blast dressed as personalization, and feedback evaporating instead of landing in the skill.

1---
2name: "reach-out"
3title: Reach out
4description: |
5 Use this skill whenever creating outreach — a cold email, a LinkedIn message, a follow-up, or a multi-step sequence — for a company, a contact, a list, or a signal. Use it even when the user doesn't say "outreach": any request to write to, contact, message, or get in front of a prospect or account goes through here. Covers picking the hook, matching the org's voice, choosing the sequence shape, and staging everything for approval. Trigger phrasings: "reach out to", "draft outreach", "email this company", "message this prospect", "follow up with", "build a sequence", "contact these visitors".
6 
7 Also use it for strategic outreach questions ("how should our cold emails sound", "what cadence should we run") — the output is then a point of view grounded in the org's saved voice, not a sequence.
8category: Outreach
9---
10 
11Produces a staged outreach sequence awaiting the user's approval, with the reasoning attached: who, why now, what hook.
12 
13### The motion table — this org's, not the skill's
14 
15This table is the org's motion library. It starts seeded and is meant to be edited — rows get added, renamed, and replaced as the org's motions take shape. Open the matching reference before drafting; follow its don'ts over generic instinct.
16 
17| Situation | Reference |
18|---|---|
19| Named company, named contact, or a small account set | `references/targeted.md` |
20| An identified website visitor | `references/website-visitor.md` |
21| A recurring or scheduled list run, cold volume | `references/cold-list.md` |
22| Someone engaged with a post or profile on LinkedIn | `references/linkedin-engagement.md` |
23| Funding, hiring spree, leadership change, product launch | `references/company-signals.md` |
24| Form fill, content download, demo request, MQL, signup | `references/inbound-hand-raiser.md` |
25| Webinar or conference registrants, attendees, no-shows | `references/event-follow-up.md` |
26| Third-party intent data — category research, review-site activity | `references/intent-signals.md` |
27| The user gives feedback, wants outreach to sound or perform better, announces a strategy shift, or asks to set up the voice | `references/improve-outreach.md` |
28 
29No row matches (win-back, referral, reply handling) → run the procedure below and say so in the reasoning. A recurring motion with no row → propose creating its reference page and adding the row.
30 
31`references/improve-outreach.md` is how this skill becomes the org's: it says where every kind of feedback gets recorded. Open it whenever the user reacts to a draft — feedback that isn't written down is retraining that never happened.
32 
33### This org's voice and rules
34 
35Nothing recorded yet. Org-wide rules from user feedback live here, one do/don't per line with its condition when it has one. These outrank everything below except the user's live instruction.
36 
37### Anchor on the hook
38 
39Every message needs a reason it goes to this person now. Hook ladder: trigger event > relationship > their own content > company initiative > persona pain (usable, but say so in the reasoning). No hook → push back before drafting. NEVER invent a signal.
40 
41The hook informs the angle; it rarely appears in the copy. Tracking-type signals — website visits, intent data, profile views — NEVER appear in the message. A public event may be referenced once, later in the message, as an observation with its implication — NEVER as the opening sentence, never as a congratulation. Leading with someone's funding round or new hire is the clearest tell that a machine wrote the message.
42 
43### Voice
44 
45Approved sends accumulate automatically as style examples. Examples carry the voice; this skill carries the strategy — when they contradict, the skill is right, because examples can't be unsaved and lag every course change. Imitate an example's tone and rhythm, never a choice that breaks a rule. NEVER imitate copy from skill text or another org. No examples yet? Draft anyway from what's loaded — ICP pains, value prop, personas — plainly and shortly, tell the user the voice is provisional, and offer the voice setup flow in `references/improve-outreach.md`. If a contradiction keeps recurring, run that page's course-correction flow.
46 
47### Draft
48 
49- Opener, email: the hook's implication, in the contact's frame. One sentence. The event or signal itself never opens the message.
50- Opener, LinkedIn: say who you are and what you want in the first line. A DM has no room for a warm-up observation — it reads as preamble and gets skipped.
51- Body: one researched detail max, reacted to rather than exhibited. One proof point max — attributed, sized to the company. Never a feature list, never an invented customer or stat. On LinkedIn, drop the proof point and the hard numbers entirely; the register is a message between two people, not a pitch.
52- CTA: one ask, and make it the smallest real thing that could land this week — a short list to run, one account to check, a sample to review. Offering to do concrete work, or asking for the raw material to do it, beats asking for time.
53- Pitch at the reader's altitude: C-level hears risk and strategy, VP hears performance, director hears operational pain.
54- Shape per email: signal → proof → ask (fresh trigger); problem → cost → fix (only when the pain is documented in the ICP); before → after → bridge (easy-to-picture change).
55- Draft in the language the org sells in — a wrong-language sequence is an error, not a style choice.
56 
57### Cadence
58 
59The org's recorded cadence always wins; default: 3–5 steps, days ~0/3/7/14, single channel unless the motion says otherwise, never referencing one channel from the other. Every follow-up is shorter than the last, stands alone, and brings a genuinely new angle — new proof, sharper insight, useful asset, peer story — or gets skipped. Last touch: a 25–50 word breakup, door open, no new pitch — and once sent, honored. Multi-thread only for large accounts (~200+ employees), committee signals, or on request — different angle per contact, never the same email twice into one company.
60 
61### The final gate
62 
63Run on every message before staging; a failed check means rewrite, not tweak:
64 
651. Delete the opener — still makes sense? The personalization is decoration; rebuild around the hook.
662. Does the close contain the word "worth"? Rewrite it. "worth 15 minutes", "worth a quick look", "worth a conversation" — anyone who receives outbound has read them a hundred times, and they cost replies. Ask for the thing itself instead.
673. Does sentence one name a funding round, a launch, a hire, or any other event? Rewrite — open with what it means for them, not with the news.
684. Could this go to anyone else this week? Then it's a blast in costume.
695. One CTA. 60–110 words, follow-ups shorter. Subject 2–5 words, lowercase, internal-looking. More "you" than "I/we".
706. Email: is the proof a number or a name? "Helps teams like yours" is not proof.
717. Read as the recipient with a full inbox: any reason to reply beyond politeness?
72 
73### Stage
74 
75Check for an existing unsent sequence to the contact — edit, don't duplicate. Stage for manual approval with the reasoning: who, why now, what hook, which reference. NEVER auto-send unless the user says so in this conversation. NEVER attach files; link instead. A channel missing its contact data gets fixed or dropped.
76 
77## What good looks like
78 
79A first-run draft — new org, zero examples — approved with a tweak, not a rewrite: a hook that fits nobody else this week, substance traceable to the org's ICP and value prop, nothing that smells like a template. Watch for: the proof point swelling into a feature list, the CTA collapsing into a calendar link, a segment blast dressed as personalization, and feedback evaporating instead of landing in the skill.
80 
View all files on GitHub →

Details

Updated
Sep 23, 2026
License
MIT
Stars on the repo
★ 159
Checked
Source
swan-gtm/gtm-skills ↗
Creator
swan-gtm · 51 listings
View creator

Similar skills

See all →
SkillAct as a comprehensive AI sales intelligenceAI Sales Team — Main Orchestratorzubair-trabzada/ai-sales-team-claude · by zubair-trabzadaYou are a comprehensive AI sales intelligence and outreach system for Claude Code. You help founders, sales teams, agency owners, and…★ 1.4k GitHub starsSkillAutonomous cold email campaign launcherAuto research publicgrowthenginenowoslawski/coldoutboundskills · by growthenginenowoslawskiAutonomous cold email campaign launcher. Takes one target company domain, scrapes their website, generates an ICP with Claude, pulls matching leads via Prospeo, enriches emails + company descriptions, personalizes each lead with parallel Claude Code Task sub-agents (A/B/C variants), and uploads as a live Smartlead campaign. Uses local JSON files for state (no database required). Use for automated daily campaign launches after you have an initial `client-profile.yaml` from /icp-onboarding. Triggers on "auto-research", "launch an automated campaign", "daily campaign", "run the research loop".★ 736 GitHub starsSkillRun a full Account-Based Marketing campaign end-to-endABM Campaign — DIY Playbookexplorium-ai/gtm-skills · by explorium-aiABM campaign skill for Claude Code: run a full Account-Based Marketing campaign end-to-end — from ICP definition to live LinkedIn Ads. Builds targeted account lists with Vibe Prospecting, enriches and scores companies with real-time B2B data, generates personalized ad creatives with Claude Code and Figma, pushes matched audiences to LinkedIn Ads, and monitors campaigns daily at scale. The complete GTM skill for AI-driven account-based marketing in Claude Code, Codex, Hermes-Agent, and OpenClaw. No agency needed.★ 197 GitHub starsSkillContact data skill for Claude Code and Codex: build a rankedAccount contact shortlistexplorium-ai/gtm-skills · by explorium-aiContact data skill for Claude Code and Codex: build a ranked shortlist of decision-makers and contacts at a target company for outbound prospecting, deal acceleration, or renewal/expansion plays. Returns verified contact data including email, phone, LinkedIn profile, title, seniority, and department. Provide a company name or domain plus optional seniority focus or use case. Use for contact data enrichment, LinkedIn profile lookup, and building outbound contact lists. Works in Claude Code, Codex, Hermes-Agent, and OpenClaw.★ 197 GitHub starsSkillLead scoring and buying signals skill for Claude CodeAccount fit rankexplorium-ai/gtm-skills · by explorium-aiLead scoring and buying signals skill for Claude Code and Codex: rank a list of accounts by ICP fit, buying intent, real-time trigger events, and workforce momentum. Returns composite score (0-100), tier (A/B/C), and a 'why now' signal per account. Use for account-based selling, ABM list prioritization, territory planning, signal-based selling, and buyer-intent ranking. Triggers on 'score these accounts', 'rank by ICP fit and intent', 'prioritize this account list', 'which accounts have the strongest buying signals', 'ICP scoring', 'account prioritization'. Works in Claude Code, Codex, Hermes-Agent, OpenClaw, and Claude Cowork.★ 197 GitHub starsSkillRun end-to-end B2B cold-email outreach through the Hyper MCPhyperfx-ai/marketing-skills · by hyperfx-aiRun end-to-end B2B cold-email outreach through the Hyper MCP — enrich prospects with Apollo, scrape per-prospect signals from company sites and LinkedIn, draft personalized emails using proven hook frameworks, send via Gmail with safe defaults, and route replies into labeled folders. Use when the user wants to write cold emails, run an outbound sequence, prospect a list, build a follow-up cadence, "reach out to leads," or asks why nobody is replying to their cold emails.★ 90 GitHub stars

More from swan-gtm

SkillAn ABM program cannot prove engagement mattersAccount-Based Engagement Scoring and Buying Group Measurementswan-gtm/gtm-skills · by swan-gtmUse this skill when an ABM program cannot prove engagement matters, accounts get handed to sales on gut feel, or nobody knows which activity moves buying groups forward. Builds an account engagement score (weighted signals plus decay), maps buying group coverage across the decision-making unit, and defines explicit handover gates so marketing and sales agree on readiness. Produces a scoring model, a buying group tracker template, and a handover decision rule. Rule: without buying group visibility a high engagement score is a false positive; handover requires both the score and the coverage threshold met. Trigger phrases: ABM measurement, which accounts are hot, buying committee coverage, when do we hand this to sales, account engagement score, ABM ROI.★ 159 GitHub starsSkillWriting ad copy — headline formulas, visual directionAd Copywriting - Headline Formulas, Visual Design & Voice of Customerswan-gtm/gtm-skills · by swan-gtmUse this skill when writing ad copy — headline formulas, visual direction, and voice-of-customer sourcing that makes ads specific instead of generic.★ 159 GitHub starsSkillDefining ad personasAd Persona Frameworkswan-gtm/gtm-skills · by swan-gtmUse this skill when defining ad personas — translating ICP segments into the persona lens every ad, angle, and offer gets built against.★ 159 GitHub starsSkillA percentage in a commercial term is being set, questionedAudit the base not the rateswan-gtm/gtm-skills · by swan-gtmUse this skill when a percentage in a commercial term is being set, questioned, or is producing a number nobody expected — sales commission, revenue share, affiliate and creator payouts, channel margin, agency fees, referral fees, rebates. Triggers: "reps are hitting quota but margin isn't moving", "what does this promo actually cost us", "our partner payouts are higher than the model", "is 15% a fair rate", "we're renegotiating the split", "the comp plan is paying out on deals we lost money on". It finds what the percentage multiplies, identifies the condition under which that choice starts to matter, quantifies the gap at that condition, and identifies the clause to revisit.★ 159 GitHub starsSkillInbound leads arrive incomplete B2B Data Enrichment for Revenue Operationsswan-gtm/gtm-skills · by swan-gtmUse this skill when inbound leads arrive incomplete (missing company size, industry, revenue), the TAM list lacks data for scoring, or the CRM cannot route and segment without enrichment. Maps coverage gaps, compares single-source and waterfall provider strategies, and builds an integration roadmap with cost guardrails and quality gates. Produces a provider recommendation matrix, a waterfall architecture, and a go or no-go checklist. Rule: no single provider has full coverage; a waterfall across two or more providers in sequence beats any one source on match rate. Trigger phrases: data enrichment, leads come in with no company info, enrichment coverage, firmographic data, which enrichment tool, data freshness.★ 159 GitHub starsSkillYou need to know what people are saying about a brandBrand mention monitorswan-gtm/gtm-skills · by swan-gtmUse this skill when you need to know what people are saying about a brand across the web and social — "monitor brand mentions", "what are people saying about [brand] this week", "run a brand sweep", "social listening", "find high-risk mentions", or "how does [brand] compare to [competitor] in the conversation". Sweeps social platforms, news, forums, and review sites; scores every mention on reach, velocity, sentiment, and risk-topic match; and produces a triage report bucketed into Crisis / Watch / Engage / Log with a suggested owner and response window for each mention, so the team responds before one spirals.★ 159 GitHub stars