Launch logo

Launch

Community
Houseofmvps
launch

Launch Day Autopilot — prepare everything for a product launch. Use when user wants to launch, go live, announce, or prepare for Product Hunt / Hacker News / social media launch.

Overview

PublisherHouseofmvps
Repositoryultraship
Skill namelaunch
Stars
122
Forks
14
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Launch 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.
  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/Houseofmvps/ultraship.git /tmp/ultraship
mkdir -p .claude/skills
cp -r /tmp/ultraship/skills/launch .claude/skills/launch
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Launch 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 Launch 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 Launch 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.

Launch Day Autopilot

A launch is not a deploy. A deploy puts code on a server. A launch puts a product in front of people who need it, at the right time, with the right message, on the right channels. This skill treats launch as a coordinated campaign, not a checkbox.

Process

Phase 1: Analyze Project

bash
node ${CLAUDE_PLUGIN_ROOT}/tools/launch-prep.mjs <project-directory> --url=<production-url>

Parse the JSON output for project info, launch copy, checklist, and press kit.

Phase 2: Audience & Positioning

Before writing a single word of copy, nail the positioning:

Who is this for?

  • Define the target user in one sentence (e.g., "Solo SaaS founders with $5K-50K MRR who are losing customers to churn")
  • What is their current pain? What do they do today without this product?
  • What is the single most compelling thing this product does for them?

Positioning statement:

For [target user] who [pain point], [product] is a [category] that [key benefit]. Unlike [alternatives], it [differentiator].

This positioning statement drives ALL copy below. Every piece of content should map back to it.

Competitive angle:

  • What exists today that partially solves this? Why is it insufficient?
  • What is the "wedge" — the one thing that makes someone try this instead? Lead with that.

Phase 3: Launch Checklist

Present the launch checklist with pass/fail/warn status:

Product Ready:

  • Landing page live and fast (Lighthouse 90+)
  • Signup/onboarding flow tested end-to-end
  • Pricing page clear with CTA
  • No console.logs, TODOs, or placeholder text visible
  • Error states handled (404, 500, empty states)

SEO + AI visibility Ready:

  • Meta description, OG tags, favicon, sitemap, robots.txt
  • llms.txt for AI discoverability
  • Structured data (JSON-LD) on key pages
  • AI-friendly robots.txt (GPTBot, PerplexityBot allowed)

Analytics Ready:

  • Event tracking on signup, activation, and payment
  • UTM parameters working for campaign attribution
  • Goal/conversion tracking configured

Legal Ready:

  • Privacy policy and terms of service linked in footer
  • Cookie consent if serving EU users
  • GDPR/data deletion path documented

Social Proof Ready:

  • At least one testimonial, beta user quote, or dogfood result
  • GitHub stars, npm downloads, or other traction signal visible
  • Author/founder bio with credibility signals

For any FAIL items, fix them immediately.

Phase 4: Launch Copy — Platform by Platform

Product Hunt:

  • Tagline (max 60 chars): Punchy, specific, no buzzwords. Lead with what it does, not what it is.
    • Bad: "AI-powered productivity platform"
    • Good: "Find which customers are about to churn before they cancel"
  • Description (2-3 sentences): Problem → solution → proof. Include a number (users, rules, time saved).
  • Maker's first comment: Personal, authentic. Why you built this. What surprised you. What's next. End with a question to drive comments.
  • Gallery images (5-6): Hero screenshot, key feature 1-3, before/after or comparison, social proof. Each image should stand alone and tell a story.

Twitter/X Thread (5-7 tweets):

  • Tweet 1: Hook — state the problem in a way your target user feels. No "I'm excited to announce." Start with the pain.
  • Tweet 2: The aha moment — what you realized that led to building this.
  • Tweet 3-4: Show, don't tell — screenshot, GIF, or concrete example of the product working.
  • Tweet 5: Social proof — beta results, dogfood data, a specific number.
  • Tweet 6: The ask — try it (link), star it, share it. One clear CTA.
  • Tweet 7: Bonus — what's coming next. Creates anticipation for followers.

LinkedIn Post:

  • Professional tone but not corporate. Focus on the journey and the problem space.
  • Lead with insight about the industry, not about your product.
  • Include 3-5 hashtags (industry-specific, not generic).
  • End with a question that invites comments.

Hacker News (Show HN):

  • Title: "Show HN: [Product] – [What it does in plain English]"
  • Body: Technical, honest, no marketing. Explain: What it does. Why you built it. How it works technically. What's interesting about the implementation. What you learned. Link to demo/repo.
  • HN values: technical depth, honesty about limitations, open source, responding to every comment.

Phase 5: Community Seeding Strategy

Launching on platforms is necessary but not sufficient. The products that break through have community presence before launch day:

Pre-launch (1-2 weeks before):

  • Post in 3-5 relevant communities about the problem you're solving (not your product)
  • Share a "building in public" update showing progress
  • DM 10-20 people in your target audience for early feedback
  • Ask 5 people to be ready to upvote/comment on launch day

Launch day amplification:

  • Ask every early user to share on their preferred platform
  • Cross-post between platforms (PH post links to Twitter thread, Twitter links to HN)
  • Respond to every comment within 1 hour — engagement velocity matters for algorithms
  • Share real-time metrics updates ("50 signups in the first 2 hours") — progress updates drive curiosity

Post-launch (3-7 days after):

  • Follow up with everyone who signed up but didn't activate
  • Publish a "launch retrospective" blog post with real numbers
  • Submit to newsletters and curated lists in your niche
  • Update the product based on launch day feedback and announce the updates

Phase 6: Press Kit

Present the press kit components:

  • One-liner description (from positioning statement)
  • Elevator pitch (3 sentences: problem, solution, proof)
  • Tech highlights (for technical publications)
  • Key features list (5-7 bullet points, benefit-led)
  • Founder bio with relevant credentials
  • High-res logo and screenshot assets

Phase 7: Pre-Launch Health Check

If a production URL was provided:

bash
node ${CLAUDE_PLUGIN_ROOT}/tools/health-check.mjs <production-url>

Verify the site is up, fast, and SSL is valid. Run /seo to ensure all SEO + AI visibility signals are in place. Nothing worse than going viral with a broken OG image or a 4-second LCP.

Phase 8: Launch Day Timeline

Generate a suggested launch day timeline (all times in user's timezone):

TimeActionWhy
6:00 AM PTSubmit to Product HuntOptimal for full-day upvote accumulation
6:15 AM PTPost maker's first comment on PHSets the tone, shows you're responsive
7:00 AM PTTweet the announcement threadCatches morning scrollers
7:30 AM PTPost in 2-3 Slack/Discord communitiesWarm audiences convert best
8:00 AM PTPost on LinkedInProfessional audience online
9:00 AM PTSubmit to Hacker News (Show HN)HN peaks mid-morning ET
12:00 PM PTEngage with all platform commentsEngagement velocity signals quality
3:00 PM PTShare progress update with real numbersSocial proof drives late-day interest
6:00 PM PTThank early users, share key metricsGratitude posts perform well
Next dayFollow up everywhere, respond to all commentsSustained engagement > launch-day spike

Key Principles

  • Launch is a performance, not a deploy. Every piece of copy, every checklist item, every timing decision matters.
  • Specificity beats superlatives. "63 SEO rules" beats "comprehensive SEO." "Catches N+1 queries" beats "improves performance."
  • Show, don't tell. Screenshots, GIFs, and real data outperform description text.
  • The launch week matters more than launch day. Sustained follow-up converts more than a single spike.

Frequently asked questions

What does the Launch AI skill do?

Launch Day Autopilot — prepare everything for a product launch. Use when user wants to launch, go live, announce, or prepare for Product Hunt / Hacker News / social media launch.

Why use Launch on TypingMind?

Because you install it once and use it with any model. Launch 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 Launch in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Houseofmvps/ultraship/tree/main/skills/launch. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Launch?

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 Launch?

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

Is the Launch AI skill free?

Yes. It is published on GitHub by Houseofmvps 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 👇