45 free prompts · no sign-up
Prompts that get your site ready to launch
Paste one into Claude Code, Cursor or Codex and your agent fixes SEO, AI visibility and launch-day problems in your own codebase. Each one adapts to your stack, plans before it edits, and never touches what it should not.
Plan first, then wait
Every prompt makes the agent read your code, show a plan with the files it will touch, and wait for your approval.
Hard limits
No secrets, no deploys, no deleted data, no scripts or links you did not ask for. Each page lists what its prompt will never do.
Fits your stack
Pick Next.js, Astro, Rails, Django and more, and your host. No-code builders get the same job as a checklist.
Every agent's format
Copy it, or save it as a Claude Code skill, a Cursor rule or an AGENTS.md section. Or give your agent one line to fetch it.
Pre-launch prompts for coding agents
Run these in the week before you launch. Each one finds what would break or leak on launch day and fixes it at the source.
- Pre-launchPre-launch audit with a prioritised fix listAudit the whole site before launch and get a ranked fix list, then fix the blockers.30 to 60 minutes
- Pre-launchGet ready for a launch day traffic spikeMake the app survive a sudden burst of visitors: caching, limits, errors and a rollback plan.1 to 2 hours
- Pre-launchAnalytics and UTM attribution for launch dayKnow which launch site, post and AI assistant sent each signup, not just how many visitors came.45 to 90 minutes
- Pre-launchSocial share cards for every platformMake every link to your site preview with the right title, description and image, on every network.30 to 60 minutes
- Pre-launchFrom waitlist to launch day emailEmail your waitlist on launch day without landing in spam: clean list, authenticated domain, batched sends.1 to 2 hours
- Pre-launchA waitlist page that collects early usersBuild a pre-launch page that says what is coming and collects real, confirmed sign-ups.1 to 2 hours
AI visibility prompts for coding agents
AI assistants answer from pages they can read and trust. These prompts make your site one of them.
- AI visibilityMake your site readable by AI assistants: llms.txt and Markdown versionsAdd llms.txt and a Markdown version of every public page, so AI assistants read your site cleanly.1 to 2 hours
- AI visibilitySet your AI crawler policy in robots.txtDecide which AI bots can read your site, write it in robots.txt, and make sure nothing else silently blocks them.20 to 40 minutes
- AI visibilityDefinition and FAQ blocks that answer engines can quoteGive each key page a one-sentence definition, a facts table and real FAQs that assistants can lift as answers.1 to 2 hours
- AI visibilityStructured data for every page typeAdd correct, honest JSON-LD for each page type from one helper, matching what the page shows.1 to 2 hours
- AI visibilityA citable stats page from your own dataPublish your real numbers on a page writers and AI assistants can cite, with dates, method and anchors.2 to 3 hours
- AI visibilityEntity links: Organization, founder and official profilesTie your site, company, founder and official profiles together so search and AI know they are one entity.30 to 60 minutes
SEO prompts for coding agents
The technical SEO an agent can fix in an afternoon, done once at the source so every new page gets it right.
- SEOTitles, descriptions and canonicals, fixed at the sourceGive every page a unique title, a real description and the right canonical, from one helper.45 to 90 minutes
- SEOA sitemap that stays correct, plus IndexNowGenerate the sitemap from your real pages with true dates, and ping IndexNow when content changes.45 to 90 minutes
- SEORedirect, canonical and 404 hygieneOne canonical host, no redirect chains, real 404s and 410s, and every old URL sent somewhere useful.45 to 90 minutes
- SEOInternal linking audit and fixFind orphan pages and broken links, and add related links from your data so every page is reachable.1 to 2 hours
- SEOImage SEO: alt text, formats, sizes and lazy loadingGive every image useful alt text, a modern format, the right size and correct lazy loading.1 to 2 hours
- SEOCore Web Vitals: LCP, INP and CLSFind what slows your main pages and fix LCP, INP and CLS at their causes.2 to 3 hours
- SEOProgrammatic pages with thin-content gatesMake generated pages worth indexing, and keep thin ones out of the index and the sitemap.1 to 2 hours
- SEOhreflang for translated pagesTell search engines which language version of each page to show, with correct, reciprocal hreflang.45 to 90 minutes
Conversion prompts for coding agents
Launch day sends people once. These prompts make sure more of them sign up and stay.
- ConversionA landing page that says what it is in five secondsMake the first screen say what the product is, who it is for and what to do next, and load fast.1 to 2 hours
- ConversionA pricing page people trustMake plans clear, prices match checkout, and the common pricing questions answered on the page.1 to 2 hours
- ConversionFirst-run onboarding that gets users to the first winShorten the path from sign-up to the first moment a new user gets value, and measure it.2 to 3 hours
- ConversionEmpty, loading and error states that helpGive every list and screen a helpful empty state, a calm loading state and an error with a way out.1 to 2 hours
- ConversionRemove friction from sign-upCut sign-up to the fewest fields, add a faster sign-in option, and stop it blocking the first visit.1 to 2 hours
- ConversionA testimonial wall from real reviewsShow real quotes from real users, with permission and attribution, from one data file.1 to 2 hours
Security and reliability prompts for coding agents
Attention brings attackers and load as well as users. These prompts close the obvious doors before launch day.
- Security and reliabilitySecurity headers and HTTPS, set once for every responseSet HSTS, CSP, framing, MIME and referrer headers on every response, with CSP rolled out without breaking the site.45 to 90 minutes
- Security and reliabilityHarden sign-up, login and password resetCheck how passwords, sessions and resets work, and fix the gaps attackers try first.1 to 2 hours
- Security and reliabilityScan for leaked secrets and lock them downFind API keys and passwords in the code, the history and the browser bundle, and stop new ones getting in.30 to 60 minutes
- Security and reliabilityRate limits on public endpointsLimit how often anyone can hit the endpoints that cost money or invite abuse, with clear 429 answers.45 to 90 minutes
- Security and reliabilityError tracking, health checks and uptime alertsKnow about errors and outages before your users tell you: error tracking, a health endpoint and alerts.45 to 90 minutes
- Security and reliabilityDatabase backups you have actually restoredMake sure your data is backed up on a schedule, kept long enough, and that a restore actually works.45 to 90 minutes
Email prompts for coding agents
Sign-up confirmations and launch emails only work if they land in the inbox. These prompts make sure they do.
- EmailSPF, DKIM and DMARC so your email reaches the inboxFind every service that sends as your domain and get the exact SPF, DKIM and DMARC records to add.30 to 60 minutes
- EmailTransactional emails that look right and landMake every email your app sends consistent, readable in any client, and easy to reply to.1 to 2 hours
- EmailUnsubscribe links and consent that follow the rulesRecord consent, add one-click unsubscribe, and make sure nobody who opted out is emailed again.45 to 90 minutes
Trust and compliance prompts for coding agents
Founders who launch publicly get asked hard questions. These prompts make the honest answer easy.
- Trust and complianceA privacy policy and cookie banner that match the codeList what the code really collects and shares, then make the policy and the cookie banner match it.1 to 2 hours
- Trust and complianceData export and account deletion that really workLet users download their data and delete their account themselves, covering every table and service.2 to 3 hours
- Trust and complianceAccessibility pass to WCAG 2.2 AAMake your main pages and flows usable by keyboard and screen reader, with readable contrast.2 to 3 hours
Launch asset prompts for coding agents
The pages writers, launch sites and returning visitors look for. Build them once and they keep working.
- Launch assetsA changelog page with dated entries and a feedBuild a changelog from structured entries, with permalinks, a feed and a link from inside the app.1 to 2 hours
- Launch assetsA press kit page writers can use in two minutesBuild a press kit page with a boilerplate, facts, founders, downloadable logos and screenshots, and a contact.1 to 2 hours
- Launch assetsA featured-on section for the badges you earnedShow the launch badges and mentions you earned in one tidy, fast section, from one data file.30 to 60 minutes
After-launch prompts for coding agents
A launch leaves a pile of feedback. These prompts turn it into a better product and the next launch.
- After launchTurn launch comments into an FAQGroup the questions people asked on launch day and turn them into an FAQ on the pages where they come up.1 to 2 hours
- After launchTriage launch feedback into issuesTurn launch feedback into reproduced bugs, grouped requests and a ranked list of quick wins.1 to 2 hours
- After launchA relaunch changelog and announcementWork out what changed since the first launch and turn it into a changelog entry and a relaunch post draft.1 to 2 hours
- After launchAn exit survey for users who cancelAsk people who cancel one optional question about why, store the answers, and never make cancelling harder.1 to 2 hours
Use them from your agent
One line. Every prompt page gives you a line like Read https://abacklaunch.com/prompts/pre-launch-audit.md and follow it, with your stack in the URL.
MCP. Connect https://abacklaunch.com/mcp and call list_prompts and get_prompt. No key needed.
Agent skills. Every prompt is also published as a skill at /.well-known/agent-skills. See developers.
Questions
What is a prompt for a coding agent?
A written brief you paste into an AI coding tool such as Claude Code, Cursor or Codex. It tells the agent the job, the steps, what done looks like and what it must not do, so it works on your codebase like a careful contractor instead of guessing.
Are the prompts free?
Yes. Every prompt is free with no sign-up. Copy it, download it or fetch it from your agent.
Do the prompts put links to Aback Launch in my code?
No. Nothing in a prompt mentions Aback Launch. Each prompt page has an optional badge step that stays off unless you tick it.
How are the prompts kept up to date?
Each prompt has a version, a date and a changelog on its page. When search engines or AI assistants change how something works, the prompt is updated and the change is noted.
Can my agent fetch a prompt by itself?
Yes. Each prompt has a one-line version that tells an agent to read the prompt from its .md URL with your settings applied, and agents that speak MCP can call get_prompt on our MCP server.