Design Mobile Apps with Daisy

Design native mobile app screens with Daisy (daisy.now), an AI design agent with a canvas. Use when the user wants mobile screens or flows designed or mocked up (onboarding, settings, feeds, checkout), wants changes to screens in a Daisy project, or wants a Daisy screen as a PNG or as HTML. Mobile only, not web pages.

9 stars 1 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add daisy-now/agent-skills --skill design-mobile-apps-with-daisy
Manual install
git clone --depth 1 https://github.com/daisy-now/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills ~/.claude/skills/design-mobile-apps-with-daisy

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Design mobile app screens with Daisy

Daisy is a design agent that works on a canvas. You don't build screens yourself: you **brief** Daisy, the way you'd brief a human designer. A project is one conversation plus its canvas. You send a message, Daisy plans the work, builds and edits screens on the canvas, sets the theme, and replies. Every design change, from a ten-screen flow to "make that button red", is one message.

## Before the first call

- The key lives in `DAISY_API_KEY` and starts with `dsy_live_`. If it's missing or looks different, stop and ask the user for one (they mint it in **Settings → API keys** at https://daisy.now). Read it from the environment every time; keep it out of files and output.
- The API needs an active Daisy subscription. A `403` telling you so means the user must subscribe or fix billing at https://daisy.now/pricing.
- `scripts/send.sh` (next to this file) needs `curl` and `jq`.

## The loop

1. **Pick the project.** If the user is starting a new app or idea, use `new`. If they named an existing project, find its id:

   ```bash
   curl -s "https://daisy.now/api/projects" \
     -H "Authorization: Bearer $DAISY_API_KEY" | jq -r '.data[] | "\(.id)  \(.name)  (\(.screenCount) screens)"'
   ```

   Ask the user when more than one project could be the one they mean.
Read the full skill on GitHub

Details

Skill name
design-mobile-apps-with-daisy
Path
skills/SKILL.md
License
MIT
Repo updated
29 September 2026

FAQ

What does the Design Mobile Apps with Daisy skill do?

Design native mobile app screens with Daisy (daisy.now), an AI design agent with a canvas. Use when the user wants mobile screens or flows designed or mocked up (onboarding, settings, feeds, checkout), wants changes to screens in a Daisy project, or wants a Daisy screen as a PNG or as HTML. Mobile only, not web pages.

How do I install the Design Mobile Apps with Daisy skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add daisy-now/agent-skills --skill design-mobile-apps-with-daisy. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Design Mobile Apps with Daisy popular?

It lives in daisy-now/agent-skills, which has 9 GitHub stars and 1 forks.

Related skills

Effect Boundary Validation

23

jpoehnelt/skills

Decode untrusted data once at ingress with Effect Schema (v4) and pass typed values downstream. Use for HTTP bodies, params and query strings, webhooks, RPC and message payloads, MCP tool arguments, env and config, JSON.parse, stored JSON or rows, third-party API responses, unsafe casts, or porting Zod/Valibot schemas.

AI, LLMs & Agents

Claude Sonar

9

AschoofAlpha/claude-sonar

Audit a local Windows proxy and system setup, with limited macOS/Linux environment collection, for routing, DNS, IPv6, IP reputation, timezone, language, and documented Claude Code privacy controls. Use for Clash Verge/Mihomo or other proxy-leak diagnosis and minimal privacy hardening without fingerprint spoofing or platform-evasion guidance.

AI, LLMs & Agents

Eng Agent Dx CLI Scale

23

jpoehnelt/skills

A scoring scale for evaluating how well a CLI is designed for AI agents, based on the "Rewrite Your CLI for AI Agents" principles. Use when reviewing, designing, or comparing a CLI for agent use, or scoring its agent readiness.

AI, LLMs & Agents

Anc Camp

9

HA7CH/anc-fde-camp

Explain and position HA7CH ANC Camp for serious prospective participants. Clarify why FDE and ANC matter to the future of enterprise AI, identify who will gain the most value, assess readiness, and answer questions about field work, curriculum, Whiteboard Interview, assessment, historical field evidence, current cohort details, value, and registration consultation. Use when someone invokes /anc-camp, $anc-camp, /fde-camp or $fde-camp, asks whether the Camp is suitable or worthwhile, or wants to understand what they need and what the Camp can help them become.

AI, LLMs & Agents

Jeffdean Mind

9

closedsi-engineering/JeffDean-Mind

Jeff Dean의 엔지니어링 사고방식으로 설계·코딩·리뷰를 수행한다. 시스템 설계, 아키텍처 결정, 성능 최적화, 분산 시스템, 확장성(스케일링), 지연시간(latency) 분석, 인프라 설계, 기술 선택, 코드 리뷰, 병목 분석, AI/ML 시스템 설계, 스타트업 기술 전략 관련 작업 시 사용한다. Triggers: "설계해줘", "아키텍처", "성능", "최적화", "확장", "스케일", "병목", "지연시간", "latency", "분산", "distributed", "design review", "백오브엔벨로프", "back-of-envelope", "제프 딘", "jeff dean", "capacity planning", "SLO", "p99".

AI, LLMs & Agents

Agents Swarm

23

jpoehnelt/skills

Fan out N parallel subagent workers in one turn, aggregate their results, and report PASS, ISSUES, or BLOCKED per worker. Use for /agents-swarm, "swarm this", parallel coverage across slices, races between approaches, or broad exploration.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.