TypingMindTypingMindThe best frontend for AI
Cold Outreach Stinger logo

Cold Outreach Stinger

Organization
legioncodeinc
cold-outreach-stinger

Build founder cold-email programs. Use for deliverability, list hygiene, outreach tools, personalization, or sequences. Read README.md for the guide map.

Overview

Publisherlegioncodeinc
Repositoryvibe-coding-tools
Skill namecold-outreach-stinger
Stars
94
Forks
44
Bundled files
17
LicenseAGPL-3.0-or-later
Links
Skill sourceRepository
  • 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.

  • 17 bundled files

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

  • Open source

    Published by legioncodeinc on GitHub. Read the source before you install it.

Installation

Install the Cold Outreach Stinger 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/legioncodeinc/vibe-coding-tools/tree/main/plugins/growth-and-customer-tools/skills/cold-outreach-stinger
  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/legioncodeinc/vibe-coding-tools.git /tmp/vibe-coding-tools
mkdir -p .claude/skills
cp -r /tmp/vibe-coding-tools/plugins/growth-and-customer-tools/skills/cold-outreach-stinger .claude/skills/cold-outreach-stinger
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cold Outreach Stinger 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 Cold Outreach Stinger 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 Cold Outreach Stinger 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.

cold-outreach-stinger

Start with README.md for the workflow map and detailed references.

Opinionated cold outreach playbook for founder-led B2B sales. Encodes the decisions, diagnostics, and templates that separate 3%+ reply rates from landing in spam.

Read first: guides/00-principles.md -- the six non-negotiables that govern every engagement. If you violate these, no amount of copy optimization will help.

Then orient by task:

TaskStart here
"Which tools should I use?"guides/01-tool-decision-matrix.md
"My emails land in spam" / deliverability fixguides/02-infrastructure-and-deliverability.md
"Write me a cold sequence" / sequence auditguides/03-sequence-design.md
"Set up Clay personalization"guides/04-clay-personalization.md
"Clean my list" / ICP definitionguides/05-list-hygiene.md
"Handle replies" / disqualificationguides/06-reply-handling.md
"Something broke" / reply rate droppedguides/07-diagnostics.md

Critical directives (non-negotiables)

These are the guardrails that govern every cold-outreach-wasp-drone engagement. They are explained fully in guides/00-principles.md.

  1. Deliverability before copy. Infrastructure problems make perfect copy irrelevant. Assess SPF/DKIM/DMARC, warmup status, and sending reputation before touching email text.

  2. Separate sending domains are non-negotiable. The main company domain is never used for cold outreach. If the user is sending from acme.com, stop and fix this before anything else. Deliverability damage to the primary domain is irreversible without full domain rotation.

  3. AI personalization must pass the 1-in-1000 test. Any AI-generated opener that would be true for the majority of the list is slop. The Clay Claygent SKIP rule is the operational implementation: if no specific data is found, return "SKIP" rather than generate a generic line. (See research/external/2026-05-20-clay-claygent-personalization-anti-slop.md [source-repository research, not shipped with the plugin])

  4. Never recommend more than 5 steps for cold SMB sequences. Data shows 3-step sequences generate the highest per-sequence reply rate (9.2%). Steps 6+ produce near-zero positive replies and burn sender reputation. (See research/external/2026-05-20-cold-email-sequence-length-benchmarks.md [source-repository research, not shipped with the plugin])

  5. Reply rate is the canonical metric. Open rates are manipulated by Apple MPP and are not a reliable KPI since 2021. The canonical measure is reply rate: positive replies / emails sent. Benchmark: >2% = functional, 3.43% = industry average, 10%+ = elite. (See research/external/2026-05-20-cold-email-reply-rate-benchmarks-2026.md [source-repository research, not shipped with the plugin])

  6. Flag EU/GDPR cold outreach risks explicitly. Cold email to EU prospects without legitimate interest documentation is non-compliant. Surface this explicitly and route to security-wasp-drone for audit. Never provide legal advice; flag and hand off.

The five primary workflows

1. Infrastructure and deliverability setup

Entry point: guides/02-infrastructure-and-deliverability.md

Key facts from research:

  • Google permanent 550 rejections went live November 2025 (not temporary deferrals anymore). (See research/external/2026-05-20-cold-email-deliverability-2026-rules.md [source-repository research, not shipped with the plugin])
  • Google Postmaster Tools v2 (October 2025): binary Pass/Fail reputation scoring, replacing gradient.
  • Required: SPF + DKIM (2048-bit key) + DMARC (minimum p=none, recommended p=quarantine).
  • Safe volume: 50-100 emails/mailbox/day. Scale horizontally (more mailboxes) not vertically (more sends per mailbox).
  • Warmup: 4 weeks minimum. Key warmup metric is reply rate during warmup, not volume.

Use templates/deliverability-audit-checklist.md to run the audit before touching sequence or copy.

2. Sequence design

Entry point: guides/03-sequence-design.md

Key facts from research:

  • Optimal sequence: 3-5 steps (SMB = 3-4, mid-market = 5-7). (See research/external/2026-05-20-cold-email-sequence-length-benchmarks.md [source-repository research, not shipped with the plugin])
  • Under 80 words per email. (See research/external/2026-05-20-cold-email-reply-rate-benchmarks-2026.md [source-repository research, not shipped with the plugin])
  • Peak timing: Wednesday, 7-11 AM recipient local time; Tuesday-Thursday window. (See research/external/2026-05-20-b2b-cold-email-sequence-build.md [source-repository research, not shipped with the plugin])
  • Step 2 should read like a reply, not a reminder.
  • One CTA per email. No two asks in one message.
  • Multi-channel rule: email accounts for 50% or less of total touchpoints in a full sequence.

Use templates/sequence-5-step.md as the scaffold.

3. Clay AI personalization

Entry point: guides/04-clay-personalization.md

Key facts from research:

  • Clay Claygent throughput: 500+ contacts/hour at $0.02-0.05 per personalized line. (See research/external/2026-05-20-clay-claygent-personalization-anti-slop.md [source-repository research, not shipped with the plugin])
  • SKIP rule: prompt Claygent to return "SKIP" if it cannot find a specific, genuine insight. Never generate a generic line.
  • Opener constraints: 25 words max, no forbidden phrases ("I noticed", "impressive", "exciting").
  • Personalization lift: 1.5-2x reply rate vs template personalization with Claygent.
  • Signal triggers worth building campaigns around: job change (VP roles = 3x higher buy probability in 90 days), funding events, tech stack change, open job postings. (See research/external/2026-05-20-clay-signal-based-prospecting.md [source-repository research, not shipped with the plugin])
  • Recommended email waterfall: Prospeo → Hunter → Apollo (3 providers + MX validation = 70-85% coverage). (See research/external/2026-05-20-clay-ai-personalization-workflow.md [source-repository research, not shipped with the plugin])

Use templates/clay-waterfall-formula.md as the starting formula.

4. List hygiene

Entry point: guides/05-list-hygiene.md

Key facts from research:

  • ZeroBounce: best accuracy (1.8% actual bounce after verification), $0.80/1K contacts. (See research/external/2026-05-20-email-verification-zerobounce-neverbounce.md [source-repository research, not shipped with the plugin])
  • NeverBounce: best balance of accuracy + price, $1.00/1K.
  • Catch-all domains: remove entirely from cold email lists. Risk outweighs coverage.
  • List decay: 25% per year. Re-verify every 6 months minimum.
  • EU/GDPR: flag explicitly; route to security-wasp-drone for compliance audit.

Use templates/icp-definition-worksheet.md before building the list.

5. Tool selection

Entry point: guides/01-tool-decision-matrix.md

Recommended 2026 founder stacks:

  • Apollo + Instantly: email-only, volume-first, budget-conscious. (See research/external/2026-05-20-apollo-vs-lemlist-tool-decision.md [source-repository research, not shipped with the plugin])
  • Apollo + Lemlist: high-personalization craft, LinkedIn steps, image personalization.
  • Apollo + Smartlead: agency or multi-channel (email + LinkedIn + SMS).
  • Smartlead standalone: agency managing multiple clients with full multi-channel.

Critical rule: Apollo does NOT run email warmup. Always pair with a sending platform that does.

Open questions (flagged from research)

TODO: Clay's current AI model backend is abstracted through Claygent. Verify current model options at docs.clay.com before advising on model selection. See research/research-summary.md open question 1.

TODO: Instantly pricing discrepancy ($30 vs $37.6 vs $47/mo for Growth plan across sources). Always verify current pricing at instantly.ai before recommending. Do not hard-code pricing figures. See research/research-summary.md open question 2.

TODO: Microsoft Outlook bulk sender rules (May 2025) were referenced in multiple sources but not scraped directly. The deliverability guide covers Google; Microsoft rules require a targeted follow-up search before the guide can claim comprehensive coverage. See research/research-summary.md open question 3.

Cross-Angel handoffs

DomainRoute to
CRM schema (lead status, sequence tracking fields)db-wasp-drone
GDPR / EU compliance, lawful basis for cold contactsecurity-wasp-drone
GTM strategy, ICP definition, target marketlibrary-wasp-drone (PRD)
Evidence-backed ICP research from a company's public footprinticp-research-wasp-drone
AE discovery call scripts, demo processout of scope (no peer Angel)

Forged from ai-tools/command-briefs/cold-outreach-wasp-drone-command-brief.md and research/. Part of the Legion AI Tools Factory by Mario Aldayuz a.k.a @thenotoriousllama.

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 Cold Outreach Stinger AI skill do?

Build founder cold-email programs. Use for deliverability, list hygiene, outreach tools, personalization, or sequences. Read README.md for the guide map.

Why use Cold Outreach Stinger on TypingMind?

Because you install it once and use it with any model. Cold Outreach Stinger 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 Cold Outreach Stinger in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/legioncodeinc/vibe-coding-tools/tree/main/plugins/growth-and-customer-tools/skills/cold-outreach-stinger. 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 Cold Outreach Stinger?

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 Cold Outreach Stinger?

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

Is the Cold Outreach Stinger AI skill free?

Yes. It is published on GitHub by legioncodeinc under the AGPL-3.0-or-later 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.

Related AI Skills

View all
obra logo

Using Superpowers

obra
CommunityPopular

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

25.8K
288.1K
5 files
View
affaan-m logo

Context And Decisions

affaan-m
CommunityPopular

Govern stable domain context with a narrowly scoped CONTEXT.md when needed, and route hard-to-reverse decisions to ECC's existing architecture-decision-records skill. Use when domain terms require…

41.4K
277.3K
2 files
View
affaan-m logo

Docs Governance

affaan-m
CommunityPopular

Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks…

41.4K
277.3K
4 files
View
affaan-m logo

Ecc Conventions

affaan-m
CommunityPopular

Development conventions and patterns for ECC. JavaScript project with conventional commits.

41.4K
277.3K
1 files
View

Set up your own AI workspace now

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