一键导入
leonardo
Generate images with Leonardo AI (Lucid Origin model), remove backgrounds, and write SVG. For brand assets, UI illustrations, backgrounds, and icons.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Generate images with Leonardo AI (Lucid Origin model), remove backgrounds, and write SVG. For brand assets, UI illustrations, backgrounds, and icons.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Session-after-session product perfection loop for Vibeman. The strongest available model (Fable) directs — it walks the repo's context map context-by-context, proposes 5 challenged, high-value directions per context (features, design elevations, significant optimizations), gates them with the user until 10 are accepted, then orchestrates one Opus builder subagent per context in isolated worktrees while making every review/merge decision itself. All state lives in a linked Obsidian vault so any future session resumes the loop exactly where the last one stopped. Invoke with `/perfect [init|propose|build|status|reflect] [context-name]`.
Run a Vibeman pipeline on a project. Three modes — (A) goal-based development (PLAN > IMPLEMENT > VERIFY > REPORT), (B) audit-driven scan + triage + wave-based fix implementation, or (C) scan-and-decide (pick one context group; the skill auto-selects Idea scanners, generates a capped backlog, you accept/reject each, then it implements the approved scope). All run with quality gates, brain-signal recording, and structured per-wave/per-phase reporting.
Systematically triage, challenge, and process a backlog of auto-generated idea files. Groups by context area, validates against codebase, filters BS, presents one approval gate, then executes autonomously with code review.
Fetch npm package updates, analyze new features, and identify improvement opportunities for this app. Use when the user wants to explore what's new in dependencies or plan next development directions.
Review code for quality, security, and patterns. Scans changed files for bugs, OWASP vulnerabilities, SQLite injection, missing error handling, and anti-patterns specific to this Next.js + SQLite + Zustand stack.
Test-driven development workflow. Write failing tests first, then implement minimal code to pass, then refactor. Uses Vitest with better-sqlite3 test database. Enforces RED → GREEN → IMPROVE cycle.
| name | leonardo |
| description | Generate images with Leonardo AI (Lucid Origin model), remove backgrounds, and write SVG. For brand assets, UI illustrations, backgrounds, and icons. |
| allowed-tools | Read, Write, Edit, Glob, Grep, Bash(node *), Bash(npx *) |
| argument-hint | <description of visual asset to create> |
Generate production-quality images using Leonardo AI's Lucid Origin model.
When the user invokes /leonardo, start by asking:
What type of visual do you need?
- Icon — App icons, logos, brand marks (square, centered, clean edges)
- State illustration — Empty states, onboarding, success/error states (needs transparent bg)
- Background — Ambient textures, atmospheric scenes, decorative backdrops
- Other — Describe freely and I'll choose the best approach
Also tell me: where will this be used? (component/page name)
Then follow the matching procedure below.
--width 512 --height 512 --style dynamic --contrast 3.5currentColorLeonardo's Lucid Origin does not support --transparent. Use the remove-bg pipeline:
--style vibrant --contrast 3remove-bg --id <imageId> --output path.png (requires --no-cleanup on generate)--width 1536 --height 512 --style cinematic --contrast 2.5var(--background)currentColor and CSS custom propertiesnode .claude/skills/leonardo/tools/leonardo-image.mjs generate \
--prompt "description" \
--output path.png \
--width 512 --height 512 \
--style dynamic --contrast 3.5 \
[--no-cleanup]
Styles: bokeh, cinematic, dynamic, fashion, portrait, vibrant
Contrast: 1.0, 1.3, 1.8, 2.5, 3, 3.5, 4, 4.5
Auto-cleanup: Generations are deleted from Leonardo cloud after download. Use --no-cleanup when chaining with remove-bg.
node .claude/skills/leonardo/tools/leonardo-image.mjs remove-bg \
--id <imageId> --output path-nobg.png
currentColor / var(--primary) for theme adaptationRequires in .env:
LEONARDO_API_KEY — from app.leonardo.aiLoad env before running (bash): export $(grep -E '^LEONARDO_API_KEY=' .env | xargs)
Load env before running (PowerShell): Get-Content .env | ForEach-Object { if ($_ -match '^LEONARDO_API_KEY=(.*)') { [Environment]::SetEnvironmentVariable('LEONARDO_API_KEY', $matches[1]) } }
Personas brand identity: Neon android head — representing AI agents of the new generation. Futuristic, glowing, geometric, clean. Primary palette from src/styles/tokens.css and src/lib/colors.ts.