jev-design

# Jev design Each part of the work goes to whoever does it best: | Phase | Who | Output | |---|---|---| | 1. Brief | the agent running the skill | `brief.json` | | 2. Pick | Jev, through `scripts/plan.py` | a component per requirement, a style recipe, install commands, and CSS | | 3. Compose and build | the agent, with the `frontend` skill | layout, hierarchy, copy, custom parts, and working code | | 4. Review | the agent, with any screenshot tool | concrete findings, then fixes or a revised brief | Jev only picks from lists: a component from the catalog's candidates and a recipe from its styles. It does not write layout, copy, or code. The agent does all open-ended work. Everything below is a default. Override any step when you have a stated reason, and write the reason in your summary. ## 1. Brief Turn the user's request into `brief.json`. Read [references/brief-writing.md](references/brief-writing.md) for the procedure and a worked example. ```json {"brief":"Support agents triage 200+ cases a day on desktop; calm, dense, keyboard-first.", "style_traits":["dense","calm","professional"], "requirements":[ {"id":"results","role":"Compare, filter, and act on open cases","capabilities":["tabular-data","filter","row-actions"]}, {"id":"details","role":"Inspect one case without leaving the list","capabilities":["overlay","details"]} ]} ``` - List capabilities, style traits, recipes, and limits with `--list-capabilities`. Use only listed names. - Keep the brief to audie...