An open-source set of go-to-market skills for solo technical founders — positioning, first users, launch and pricing, sequenced into a roadmap your agent works with you.
UX WritingSkill
Summary
Write and audit interface microcopy, from buttons to error messages, against four checkable quality standards.
Features
- Four quality standards with concrete, checkable benchmarks
- Pattern library for buttons, errors, empty states, and onboarding
- Reading-level and comprehension benchmarks baked into guidance
- Voice and tone adaptation framework for different product contexts
Install This Skill
Add this skill to your favorite AI agent in a few steps.
Skill Content
Description
UX Writing is a standalone skill focused entirely on interface copy, meaning the buttons, labels, error messages, notifications, form hints, empty states, and onboarding text that make up a product's voice but rarely get the same editorial attention as marketing copy. It is built around four quality standards, purposeful, concise, conversational, and clear, and backs each with concrete, checkable guidance rather than vague advice, including a 40-60 character line-length target, a seventh-grade reading level for general audiences, roughly 85 percent active voice, and second-person address.
It provides pattern libraries for common UI text types, such as titles, error messages, empty states, confirmations, and tooltips, each with purpose, format conventions, and examples, plus frameworks for establishing and adapting a product's voice and tone across different contexts. Accessibility is core to the skill rather than an afterthought, with comprehension research and plain-language guidance baked into the same recommendations used for clarity and concision. Use it any time text is being written or edited for an app, website, or software interface, whether drafting new copy, auditing an existing product for consistency, or reviewing UI strings before ship. It is explicitly compatible with any agent supporting the Agent Skills spec, not just Claude.
Related Skills
Multi-source academic literature search as an agent skill — OpenAlex, Semantic Scholar, CrossRef, PubMed and arXiv at four depths, from a 5-minute scan to a PRISMA-S logged systematic review.
Claude Code skill that audits a site for visibility in AI answers — citability scoring, AI-crawler access, llms.txt, schema markup and brand-mention scanning — plus classic technical SEO.
A four-skill bundle that runs the academic pipeline end to end — deep research, paper writing, peer review and revision — as multi-agent workflows inside Claude Code.