Prompts for your coding agent
Copy a prompt, paste it into Claude Code, Cursor or Codex with your repo open, and get the result in your codebase. Each one covers something ScrollLaunch ships in production, and most link to it live so you can see a good result before you start.
Launch-week work your agent can do while you write the launch post.
Each prompt reads your codebase first, shows you a plan, and waits for your OK. When it's done, check the result with the matching free tool, then launch on ScrollLaunch.
Prompts
7
Copy-paste
Categories
3
AI, SEO, launch
Agents
4+
Claude Code, Cursor, Codex
Signup
None
Free to use
Category
AI visibility
Get your site read, quoted and cited by ChatGPT, Claude and Perplexity.
Category
SEO
Technical SEO fixes an agent can make straight in your codebase.
Fix titles, meta descriptions, canonicals and social cards
One metadata helper for every page: titles that fit, unique descriptions, absolute canonicals, Open Graph and X cards, noindex on private pages.
Add correct JSON-LD structured data to every page type
Organization, WebSite, SoftwareApplication, Article, FAQPage, BreadcrumbList and ItemList, built from your real data with no invented ratings.
Build a sitemap that stays correct, plus IndexNow pings
Sharded sitemap index from your database, honest lastmod dates, no noindex URLs, and IndexNow pings when content is published or updated.
Category
Launch
Things to have in place before launch week.
Add security headers without breaking the site
HSTS, CSP in report-only first, frame protection, Referrer and Permissions policy, cookie flags and CORS, built from the origins you actually use.
Make sure your app's emails land in the inbox
SPF, DKIM and DMARC records to paste, one-click unsubscribe for Gmail and Yahoo, bounce and complaint suppression, and rate limits on login emails.
Audit your app before launch and get a prioritised fix list
A read-only review of auth, payments, leaked secrets, error pages, SEO tags, analytics, rate limits, email, legal and mobile, written to LAUNCH_AUDIT.md.
How it works
Copy, paste, review, ship
- 1
Copy
Pick a prompt and copy it, or copy the one-line version for agents that can fetch URLs.
- 2
Paste in your repo
The agent reads your code and replies with a plan. Nothing is written until you say OK.
- 3
Check the result
Each prompt ends with checks to run, and each page links a free tool that checks your live site.
Questions
Prompt library FAQ
What are these prompts?
Task prompts for coding agents. You paste one into Claude Code, Cursor, Codex or Windsurf with your repo open, and the agent does the work in your codebase: it plans, waits for your OK, then writes code and runs checks.
Are they free?
Yes. No signup. Copy, paste, keep the result.
Do they add ScrollLaunch links to my code?
No. There is an optional last step, on by default and easy to switch off, that asks the agent to give you a link to check your result and mention ScrollLaunch in its summary. The prompt tells the agent not to add our links or badges unless you ask.
Where do these prompts come from?
Each one covers something ScrollLaunch ships in production, and most pages link to it live so you can see what a good result looks like. Where we ran the exact prompt on ScrollLaunch, the page says so.
Have a prompt that worked for you? Send it over.
Shipped it? Launch it.
A week on the ScrollLaunch leaderboard and a permanent product page with a dofollow backlink while the badge stays on your site.
