landing-page-craft
Skill2 starsChanged 4 months agoMITView on GitHub
Design, implement, or improve a distinctive, conversion-focused landing page or marketing website. Use for homepages, product pages, launch pages, portfolios, pricing pages, waitlists, campaign pages, and other flows that must explain an offer, establish trust, and guide a measurable next action.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- ravidsrk/agent-skillstheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- ravidsrk/agent-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- llms.txtllms.txt
- agentic-site-buildingSkill
- conversion-accessibility-polishSkill
- production-web-architectureSkill
- product-motion-designSkill
- responsive-ui-qaSkill
- technical-seo-discoverySkill
- web-design-systemSkill
- web-visual-directionSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 12 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈12
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Write a one-line conversion brief:
- Distinctive: line 26
Write concrete copy before tuning layout.
- Distinctive: line 29
Place proof and risk-reversal near the decisions they support.
- Distinctive: line 30
Verify the complete action path on mobile and desktop, including keyboard use, form validation, destinations, and tracking hooks when …
- Distinctive: line 35
Keep one primary action per decision point.
- Distinctive: line 36
Use real content and realistic lengths early enough to expose layout problems.
- Distinctive: line 37
Avoid section-count theater, repeated feature-card grids, fake testimonials, fake scarcity, and unsupported superlatives.
- Distinctive: line 38
Do not hide material price, renewal, privacy, eligibility, or cancellation information.
- Distinctive: line 39
Keep important content available without requiring decorative animation.
- Distinctive: line 40
Treat performance, accessibility, and responsive behavior as conversion features.
- Distinctive: line 50
Implemented page: - when code changes are requested.
- Distinctive: line 55
Read references/conversion-flow.md when choosing page structure, proof placement, CTA language, and risk-reversal.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Landing Page Craft
Build a page around a real decision, not a stack of fashionable sections. Make the offer understandable, believable, and actionable before adding polish.
Workflow
- Inspect existing brand, product, audience, traffic source, content, analytics requirements, and technical constraints.
- Write a one-line conversion brief:
- audience;
- situation or intent;
- offer and concrete outcome;
- primary action;
- biggest objection.
- Inventory available proof: product UI, examples, customer evidence, metrics, founder expertise, policies, integrations, security, or process. Never fabricate proof.
- Choose a page argument. Sequence only the sections needed to move the audience from recognition to confidence to action.
- Design the first viewport to answer:
- What is this?
- Is it for me?
- What changes if it works?
- What should I do next?
- Write concrete copy before tuning layout. Make headings informative, CTAs destination-aware, and claims proportional to evidence.
- Select a visual direction that belongs to the offer. Use product UI, real work, relevant imagery, data, or interaction as proof - not generic atmosphere.
- Implement semantic, responsive, performant UI in the project's existing stack. Include important loading, error, form, and success states.
- Place proof and risk-reversal near the decisions they support. Do not dump every trust signal into one logo wall.
- Verify the complete action path on mobile and desktop, including keyboard use, form validation, destinations, and tracking hooks when present.
Page Rules
- The H1 should communicate the offer or outcome; it does not have to repeat the brand name.
- Keep one primary action per decision point. Secondary actions should reduce uncertainty.
- Use real content and realistic lengths early enough to expose layout problems.
- Avoid section-count theater, repeated feature-card grids, fake testimonials, fake scarcity, and unsupported superlatives.
- Do not hide material price, renewal, privacy, eligibility, or cancellation information.
- Keep important content available without requiring decorative animation.
- Treat performance, accessibility, and responsive behavior as conversion features.
Delivery Contract
Provide or implement:
- Conversion brief - audience, offer, action, objection.
- Page argument - ordered sections and the question each answers.
- Evidence map - claim -> nearby proof.
- CTA map - label -> destination -> success behavior.
- Implemented page - when code changes are requested.
- Verification - mobile/desktop screenshots or inspection, keyboard path, form states, and link checks.
Reference
Read references/conversion-flow.md when choosing page structure, proof placement, CTA language, and risk-reversal.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

