Copywriting
Write clearer website copy for homepages, landing pages, pricing pages, and product pages.
AI skills for your next project. Explore real workflows, with clear explainers and links to the people who built them.
skills to explore
PUBLIC SKILLS, ONE SEARCHABLE SHELFIndexed 25 Sep 2026 ↗
1–24 of 662 skills
Write clearer website copy for homepages, landing pages, pricing pages, and product pages.
Create distinctive web interfaces with deliberate typography, layout, colour, and interaction design.
Generate new images or edit existing images from a brief, with support for transparency and reference images.
Build MCP servers that give an AI agent access to external tools and services.
Read and extract PDF content, create documents, combine pages, and work with PDF forms.
Review React and Next.js code for performance issues using Vercel Engineering’s recommended patterns.
Diagnose technical and on-page SEO problems and turn findings into a prioritised improvement plan.
Turn a repeatable task into an agent skill, then evaluate and improve how reliably it works.
Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases.
Plan, design, or implement an A/B test or experiment.
Plan, design, or implement an A/B test or experiment, or build a growth experimentation program.
Find Claude Academy courses, tutorials, and examples that match a question about using Claude.
Generate, iterate, or scale ad creative for paid advertising.
Generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform.
How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval.
Help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms.
Adversarial code review that breaks the self-review monoculture.
Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources.
Time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search.
Mint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone.
Design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks.
Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived.
A user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker".
A project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from.
Source-linked, not execution-tested. Check the publisher’s setup instructions and permissions before use.