toolkit/packages/skills/frontend-design/SKILL.md
Frontend design skill for UI/UX implementation - generates distinctive, production-grade interfaces
npx skillsauth add stevengonsalvez/agents-in-a-box frontend-designInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill helps create distinctive, production-grade frontend interfaces that avoid generic AI aesthetics.
When building any frontend interface, follow these principles to create visually striking, memorable designs:
Before writing any code, define a clear aesthetic vision:
Every interface you create should be:
Choose fonts that are beautiful, unique, and interesting.
Commit to cohesive aesthetics with CSS variables.
Use high-impact animations that enhance the experience.
Embrace unexpected layouts.
Create atmosphere through thoughtful details.
Generic AI Design Patterns:
Show restraint or elaboration as the vision demands—execution quality matters most.
When creating a frontend interface:
For deeper guidance on prompting for high-quality frontend design, see the Frontend Aesthetics Cookbook.
Remember: The goal is to create interfaces that are both functionally excellent and visually unforgettable. Avoid generic AI aesthetics by committing to a clear, bold direction and executing it with meticulous attention to detail.
documentation
Report reflect drain spend over a time window — tokens split by cached (cache_read), uncached writes (cache_creation), and io (input+output), with a $ estimate, grouped by day / outcome / model / transcript. Reads the drainer's cost log and surfaces outlier runs and cache-reuse health (the 41.5M-token failure mode = low cache reuse + high cache writes). Use to answer "what is reflection costing me" for the last day / week.
development
Show fleet status — every claude session running on the host, merged across ainb + claude-peers broker + background jobs. Use when you need to enumerate sessions before composing an action, see which sessions have a peer registered (broker-routable) vs tmux-only, check the `summary` of each session, or pipe the list into jq for filtering. Default output: text table. Pass --format json for LLM consumption.
testing
Ordered multi-step prompts to fleet targets, ack-gated between steps via JSONL assistant-turn-end detection. Use for cycles like disconnect→reconnect→verify, or any flow where step N+1 requires step N to have completed first. The skill BLOCKS until each target's transcript shows the next assistant turn finishing OR per-step timeout fires (default 300s).
development
Center control panel — enumerate every claude session that is blocked waiting on something: a user answer (AskUserQuestion fired), an API error retry, an idle assistant turn-end with no follow-up, or an explicit WAITING: marker. Returns rich JSON with signal kind + context per session. Use this when you've stepped away from the fleet and want one place to see everything that wants your attention and answer it.