Claude Skills by IleanaMarcut

Run one of Ileana Marcut's 101 UX and AI methods on the user's own work, or list and install the UX+AI skills. Use when the user asks for a method by name or id, asks what UX+AI methods or skills exist, asks to install a UX+AI skill, or describes a UX, research, ideation, critique, writing, design-system, or AI-design task that one of the methods below covers. Needs the uxai MCP server.

Design an AI agent or bot before it meets users. Use it at design time, when the agent's behaviour is still on paper. It runs three methods from the UX + AI connector: one defines what the agent may do, must ask about first, and never does; one decides when it hands off to a human and what context travels with the handoff; one delivers its personality, voice, and behaviour as a usable system prompt. Outcome: an enforceable scope, a handoff plan, and a system prompt that holds the voice. Trigg...

Review a design and come back with the issues worth fixing, ranked, each with a fix. Use it when a screen, a flow, or a set of screens is ready for a hard look. It runs the right critique method from the UX + AI connector for what you have in front of you: a 30-second first-impression read, the full usability critique, a friction audit on a flow, a consistency check across screens, a structured accessibility pass, or the three objections most likely to block a design review. Outcome: issues r...

Build the portfolio case a hiring team will judge you by. Use it when applying for a role or updating your portfolio. It runs three methods from the UX + AI connector: one finds what repeats across your work and turns it into positioning you can say out loud, one structures a case study from a real project with gaps marked instead of invented, and one delivers a tough critique aimed at the role before you send anything. Outcome: positioning, a case study, and a fix list, all built from work y...

Check the health of a project you built. Use it any time you want to know where the build stands: before it goes live, after a stretch of fast building, before handing it over, or when a fix lands in working code. It runs three checks from the UX + AI connector: a QA pass that ranks what breaks with real users by what bites first, a security pass that catches the basics non-engineers miss on everything public, and a regression check that lists what a change could break and what to re-test. Ou...