AI Agent Skills

Build an outdoor learning presentation around photography, blue skies and sage green accents. Suitable for introducing field programs, activities and educational projects.

Present workshops and team ideas with warm backgrounds, bold headings and colorful cut-paper portraits. Useful for sessions about collaboration, belonging and participation.

Show the same prompt across several interfaces, then assemble the results into a launch reel. Supply real examples that support the capability being shown.

Present a product interface on a device in a dark studio setting. Plan the scroll, key interaction and final brand frame around your actual interface.

Condense a lesson or process into an illustrated note with a clear reading order. Choose one central idea and a small set of supporting labels.

Reveal a brand mark through the refraction and rupture of a liquid bead. Useful for a compact visual opening or closing sequence.

Explore a browser character builder with editable shapes, materials and outfits. Use it as a starting point for a branded avatar tool.

Start a landing page with a restrained animated hero and editable visual tokens. Adapt the copy, color and interface state to the product being introduced.

Design a statistically rigorous A/B or multivariate test plan — If/Then/Because hypothesis, control and variant specs, required sample size per variant (absolute vs rela…

Design, plan, and analyze A/B tests with statistical rigor. Use when the user asks about A/B testing, split testing, experiment design, statistical significance, sample…

This skill should be used when the user types /collab-audit or requests AI collaboration diagnosis. Analyzes conversation history, artifacts, and work patterns to genera…

Use when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading significance/CI/power, CUPED, or rescuing tests that w…

Compare two versions of an LLM-directed document - an original (teacher) and a candidate (student) - across a transfer set and return a per-case behavioural-equivalence…

Compares A/B variants of a WebAsk survey and checks whether the difference is real or within noise. Use when someone asks which variant performs better or is about to ma…

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experimen…

Generate A/B test variants for affiliate content. Triggers on: "create A/B test", "test my headline", "optimize my CTA", "generate variants", "split test ideas", "improv…