Agent skill

Launch Checklist

by BuildGreatProducts in BuildGreatProducts/builder-os

A skill your agent uses when the user's product is built (or nearly built) and they want to get it live and accessible to customers.

MITAuto-check passedMarketing & SEO

Install Launch Checklist

skills CLI
$ npx skills add BuildGreatProducts/builder-os --skill launch-checklist -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install BuildGreatProducts/builder-os launch-checklist --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/BuildGreatProducts/builder-os.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/launch-checklist .claude/skills/launch-checklist && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
launch-checklist
GitHub stars
228
Token cost
~1.5k tokens
SKILL.md length
795 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user's product is built (or nearly built) and they want to get it live and accessible to customers.

  • Works in 3 steps: Audit the codebase → Write docs/launch-checklist.md → Walk the user in
  • The users product is built (or nearly built) and they want to get it live and accessible to customers
  • SKILL.md covers Step 1: Audit the codebase, Step 2: Write…, Step 3: Walk the user in and Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Launch Checklist is an agent skill from BuildGreatProducts/builder-os. Use when the user's product is built (or nearly built) and they want to get it live and accessible to customers. Triggers on phrases like "create my launch checklist", "how do I deploy this", "help me launch", "get this live", "put this in production", "ship it to customers", "what do I need to do to go live", or any request for a step-by-step path from working code to a product customers can use. Audits the current codebase — stack, services, environment variables, payments, deploy config — then writes a…

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO, covering Product launch strategy and Plain language and style rules. The repository describes itself as: BuilderOS is your operating system for building with AI. The licence is MIT.

When your agent uses it

  • The users product is built (or nearly built) and they want to get it live and accessible to customers
  • Phrases like create my launch checklist
  • How do I deploy this
  • Put this in production

Example prompts

  • “create my launch checklist”
  • “how do I deploy this”
  • “help me launch”
  • “/launch-checklist”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Audit the codebase
  2. Write docs/launch-checklist.md
  3. Walk the user in

What it can do on your machine

Read from SKILL.md and the folder at commit fb74cac. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Launch Checklist loads about 1.5k tokens when it runs. Until then it costs about 196 tokens; SKILL.md has 795 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~196
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from BuildGreatProducts/builder-os at commit fb74cac, republished under its MIT licence (© BuildGreatProducts). 795 words, ~1,536 tokens.

Download SKILL.mdSave it as .claude/skills/launch-checklist/SKILL.md (or your agent's skills folder).
name
launch-checklist
description
Use when the user's product is built (or nearly built) and they want to get it live and accessible to customers. Triggers on phrases like "create my launch checklist", "how do I deploy this", "help me launch", "get this live", "put this in production", "ship it to customers", "what do I need to do to go live", or any request for a step-by-step path from working code to a product customers can use. Audits the current codebase — stack, services, environment variables, payments, deploy config — then writes a plain-English, step-by-step launch guide to `docs/launch-checklist.md`. Every step is marked as something the user must do themselves, something their coding agent can do, or both together, and all technical terms are explained for non-technical founders.
license
MIT
metadata.author
BuilderOS
metadata.version
1.0

Launch Checklist

This skill turns "the app works on my machine" into "customers can use it." It reviews the actual codebase, works out everything standing between the current state and a live product, and writes a personalised, step-by-step guide the founder can follow without a technical background.

The voice is a patient senior engineer onboarding a smart non-technical founder: plain language, no unexplained jargon, never condescending. The founder is capable — they just haven't done this before.

Step 1: Audit the codebase

Read the repository thoroughly before writing anything. Establish:

  • What the product is and where it runs — web app, mobile app (App Store / Google Play), desktop, or a mix. Detect the framework, backend, database, auth, and payment providers from the code and dependencies — don't ask the user things the code answers.
  • Configuration state — environment variables used in code vs. what's documented (.env.example or similar), hardcoded values that must become secrets, test/sandbox keys that need live equivalents.
  • Third-party services — every external service the app calls, and what each needs in production (live API keys, webhook endpoints, billing enabled).
  • Deploy readiness — existing deploy config (e.g. vercel.json, Dockerfile, eas.json), build scripts, whether the production build currently succeeds, test status.
  • Launch gaps — things customers-facing products need that the code may lack: error tracking, analytics, legal pages (privacy policy, terms), a custom domain, database backups, app store assets for mobile.

Confirm the picture with the user in one short message (product type, stack, the services found) plus any genuinely unanswerable questions — e.g. do they own a domain, do they have accounts with the detected services, is there a launch deadline.

Step 2: Write docs/launch-checklist.md

Write the guide to docs/launch-checklist.md (create the folder if needed). Structure:

Header — product name, detected stack in one plain-English sentence, estimated total time, and a legend:

  • 🧑 You — needs your identity, accounts, payment details, or a decision. An agent can't (or shouldn't) do this for you.
  • 🤖 Agent — paste the given prompt into your coding agent and it can do this in the codebase or via the command line.
  • 🤝 Together — the agent prepares it, you click the final button or paste in a value.

Phases, each with checkbox steps. Adapt to what the audit found — typical shape:

  1. Accounts and prerequisites — sign up for the hosting platform and each production service; choose the cheapest tier that works, with monthly cost noted.
  2. Secrets and configuration — create live API keys, set environment variables on the hosting platform, remove test keys. Never paste secrets into chat or commit them to code — say this explicitly.
  3. Production services — database in production mode, auth configured for the real domain, payments switched from test to live (including webhooks and a real test purchase), email/AI/storage services on live credentials.
  4. Deploy the app — the path of least resistance for the detected stack. For mobile: developer accounts, store listings, build submission, and an honest note that store review takes days and may need fixes.
  5. Domain — buy/connect the domain, DNS setup, confirm HTTPS.
  6. Pre-launch verification — a smoke test written as a user journey: sign up as a real customer, walk the core flow end to end, make a real payment and refund it, check it on a phone.
  7. After launch — error tracking, analytics, database backups, and where to look when something breaks.
Show full SKILL.md (251 more words)Show less

Every step must have:

  • A checkbox, a 🧑/🤖/🤝 marker, and a time estimate.
  • Plain-language instructions. Explain every technical term inline on first use — e.g. "DNS (the address book that points your domain name at your app's server)", "environment variable (a setting stored outside your code, used for secrets like API keys)", "webhook (a way for one service to automatically notify another when something happens, like a successful payment)".
  • For 🤖 steps: a ready-to-paste prompt for the coding agent, in a quote block.
  • For 🧑 steps: exactly where to click/go, what they'll be asked for, and any cost.
  • A "You'll know it worked when..." line so the founder can verify each step without guessing.

Step 3: Walk the user in

Don't just drop the file. Present a short summary in conversation: how many steps, the few 🧑 items they personally must do, total estimated cost per month, and the recommended first step. Offer to execute the first 🤖 step now.

Rules

  • Be honest about cost, time, and risk — store review delays, DNS propagation ("can take up to a day"), payment provider verification.
  • Recommend one path, not a menu. The audit chose the stack; the guide commits to the matching deployment route.
  • Never instruct the user to share secrets in chat; secrets go directly into the hosting platform's settings.
  • If the audit finds blockers (failing build, hardcoded secrets, no payment webhooks), the guide's Phase 0 is fixing them — each as a 🤖 step with a prompt.
  • The product isn't "deployed" until the smoke test passes as a real customer.

© BuildGreatProducts, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/launch-checklist of BuildGreatProducts/builder-os.

Open the folder on GitHubat commit fb74cac

Compare with similar skills

Launch Checklist next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Launch Checklist compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Launch Checklist this skillBuildGreatProducts/builder-os228—~1.5kAutomated safety check: PassMIT
Micro SaaS Launchernicepkg/auto-company1958 repos~1.3kAutomated safety check: PassNone
LaunchAuditbuildfastwithai/gen-ai-experiments785—~1.8kAutomated safety check: PassMIT
Go To Marketemotixco/claude-skills-founder540—~884Automated safety check: PassMIT
Product Hunt Search and Monitoringdylanfeltus/skills179—~1.7kAutomated safety check: PassMIT
Multi-Platform Launch Plannertech-leads-club/agent-skills7k—~3.9kAutomated safety check: PassCustom licence

Similar skills

  • Micro SaaS Launcher

    nicepkg/auto-company

    Expert in launching small, focused SaaS products fast - the indie hacker approach to building profitable software.

    195 GitHub starsUsed in 8 repos~1.3k tokens
    Marketing & SEOAuto-check passed
  • LaunchAudit

    buildfastwithai/gen-ai-experiments

    Audits a startup, app or landing page from a URL, localhost, repository, screenshots or copy, then gives a launch-readiness verdict, prioritized fixes and an HTML report.

    785 GitHub stars~1.8k tokensUpdated 18 days ago
    Marketing & SEOAuto-check passed
  • Go To Market

    emotixco/claude-skills-founder

    Plan a product launch from pre-launch audience building to a 90-day growth plan, with named communities, platform-specific launch tactics, channel rankings, and a budget for $0-$500 a month.

    540 GitHub stars~884 tokensUpdated 3 days ago
    Marketing & SEOAuto-check passed
  • Looks up Product Hunt launches, products and makers through its GraphQL API: daily top posts, topic browsing and per-post details, using a free developer token.

    179 GitHub stars~1.7k tokensUpdated 23 days ago
    Marketing & SEOAuto-check passed
  • Multi-Platform Launch Planner

    tech-leads-club/agent-skills

    Plans a product launch across Product Hunt, Hacker News, BetaList and other directories, with timing from the pre-launch waitlist through post-launch follow-up.

    7k GitHub stars~3.9k tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Producthunt Launches

    browser-act/skills

    Scrape Product Hunt daily/weekly/monthly/yearly leaderboard launches with full product details, maker profiles, and website contact info.

    6.1k GitHub stars~2.6k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed

More from BuildGreatProducts/builder-os

All 8 skills in this repo
  • Design System

    BuildGreatProducts/builder-os

    Translates an image (or a set of image references — screenshots, mockups, Figma URLs, live websites) into two mirrored design-system artifacts: docs/design.md (YAML tokens + prose, following…

    228 GitHub stars~4.8k tokensUpdated 3 mo ago
    Auto-check passed
  • Idea Generator

    BuildGreatProducts/builder-os

    Guided discovery of a product idea by mining what the founder already knows or already does — covers source selection (business vs.

    228 GitHub stars~3.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Idea Validator

    BuildGreatProducts/builder-os

    Pressure-tests a product idea before the founder invests in planning, building, or launching.

    228 GitHub stars~3.8k tokensUpdated 3 mo ago
    Auto-check passed
  • Product Planner

    BuildGreatProducts/builder-os

    Vision intake conversation followed by generation of three product documents — docs/product-vision.md (strategy and brand), docs/prd.md (technical spec for coding agents), and…

    228 GitHub stars~4.6k tokensUpdated 3 mo ago
    Auto-check passed
  • Build Loop Codex

    BuildGreatProducts/builder-os

    A skill your agent uses when building features with Codex (OpenAI Codex CLI) in any codebase and the work should go through a disciplined build → review → test → fix loop.

    228 GitHub stars~888 tokensUpdated 3 mo ago
    Auto-check passed
  • Build Loop Cursor

    BuildGreatProducts/builder-os

    A skill your agent uses when building features with Cursor in any codebase and the work should go through a disciplined build → review → test → fix loop.

    228 GitHub stars~827 tokensUpdated 3 mo ago
    Auto-check passed

Questions about Launch Checklist

What does Launch Checklist do?

A skill your agent uses when the user's product is built (or nearly built) and they want to get it live and accessible to customers. Launch Checklist is an agent skill from BuildGreatProducts/builder-os. Use when the user's product is built (or nearly built) and they want to get it live and accessible to customers.

When should I use Launch Checklist?

Launch Checklist fits situations like: the users product is built (or nearly built) and they want to get it live and accessible to customers; phrases like create my launch checklist; how do I deploy this; put this in production.

How do I install Launch Checklist in Claude Code?

Run `npx skills add BuildGreatProducts/builder-os --skill launch-checklist -a claude-code`. Or copy the skill folder (skills/launch-checklist in BuildGreatProducts/builder-os) into .claude/skills/launch-checklist in your project. Claude Code loads it when a task matches its description.

How do I install Launch Checklist in Codex?

Run `npx skills add BuildGreatProducts/builder-os --skill launch-checklist -a codex`. Or copy the skill folder (skills/launch-checklist in BuildGreatProducts/builder-os) into .agents/skills/launch-checklist in your project. Codex loads it when a task matches its description.

Can I use Launch Checklist in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add BuildGreatProducts/builder-os --skill launch-checklist -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/launch-checklist, .gemini/skills/launch-checklist, .github/skills/launch-checklist and .opencode/skills/launch-checklist in your project.

What does Launch Checklist need to run?

SKILL.md names no scripts, command-line tools or credentials: Launch Checklist is instructions for the agent only.

Does Launch Checklist access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Launch Checklist safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Launch Checklist use?

Launch Checklist is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Launch Checklist use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Launch Checklist?

Skills that share tags, products or a category with Launch Checklist: Micro SaaS Launcher (nicepkg/auto-company, 195 stars), LaunchAudit (buildfastwithai/gen-ai-experiments, 785 stars), Go To Market (emotixco/claude-skills-founder, 540 stars) and Product Hunt Search and Monitoring (dylanfeltus/skills, 179 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Launch Checklist?

BuildGreatProducts (a GitHub user) maintains it in BuildGreatProducts/builder-os, which has 228 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on July 7, 2026.

Source: BuildGreatProducts/builder-os on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.