AI skill directory

Writes and rewrites marketing copy for homepages, landing pages, pricing, and ads.

Audits and improves Core Web Vitals (LCP, INP, CLS) with evidence-led guidance.

This skill designs and builds a voice assistant on Vapi for phone or web calls. It covers the system prompt and first message, choosing a model, voice, and transcriber, multilingual setup, call-control tools, and hooks. It also explains errors from the create call. A Vapi API key is needed to save the assistant.

Drafts clear product requirements documents with problem, outcomes, scope, and acceptance criteria.

Audits marketing pages and recommends conversion-rate fixes for goals, forms, and CTAs.

Maps customer journeys across stages, emotions, and opportunities for product improvement.

Runs customer research workflows—questions, synthesis, and insight capture for marketing/product.

Clarifies goals and success criteria before agent work so tasks stay outcome-focused.

Deploys applications and sites to Vercel with the correct project and CLI workflows.

This skill helps plan or improve a referral, affiliate, or word-of-mouth program. It covers when each type fits, the share loop and its trigger moments, incentives, payouts, and ways to collect more reviews.

Designs mobile app screens and UI flows, including Sleek design-project workflows.

Designer-eye QA for visual inconsistency, spacing, hierarchy, AI-slop patterns, and sluggish interactions.

Raises frontend visual taste—layout, hierarchy, and polish—beyond generic AI UI defaults.

Removes AI slop from code and UI—generic patterns, noisy comments, and low-signal churn.

Runs a structured diagnosis loop for hard bugs and performance regressions before proposing fixes.

Security-focused differential review of code changes using git history and depth adapted to repo size.

Nudges careful discernment after substantive advice so users pause before acting on drafts.

Prepares structured product discovery interview plans—goals, prompts, and note capture.

Runs an end-to-end product discovery process from questions through synthesis and bets.

Dispatches independent tasks to parallel agents when work has no shared-state dependencies.