svg-logo-designer
Generate SVG logos with multiple concepts, layouts, and color variations.
- License 许可
- Apache-2.0
- 最近更新
- 2026-10-19
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- svg-logo-designer
- description
- Generate SVG logos with multiple concepts, layouts, and color variations.
- allowed-tools
- Read, Write, Glob
02 资源文件 1
- 参考文档agents/openai.yaml156 B
03 SKILL.md 正文
SVG Logo Designer
Design a logo as scalable vector graphics: several concepts first, then the chosen ones in every layout and color treatment. When the user wants a single design rather than a family of variations, skip steps 3 and 4.
1. Gather the brief
Ask about the brand name, industry, target audience, color preferences, style (modern, classic, playful), and logo type (wordmark, icon, or combination). Done when each is answered or the user has left it to you.
2. Sketch concepts
Create 3 to 5 distinct directions that explore different visual metaphors and compositions. The full set is 20 files per concept (five layouts times four color treatments), so confirm the scope with the user: which concepts, and which layouts and treatments each needs. Done when the user has picked the concepts and agreed the set of files to produce.
3. Lay out each concept
For each chosen concept: horizontal, vertical (stacked), square, icon-only, and text-only. Done when every chosen concept has each agreed layout.
4. Color each layout
Each layout in full color, monochrome dark, monochrome light, and reversed. Done when every layout has each agreed treatment.
5. Build the SVG
Every file follows this structure:
<svg viewBox="0 0 [width] [height]" xmlns="http://www.w3.org/2000/svg">
<title>Logo Name</title>
<desc>Brief description for accessibility</desc>
<defs><!-- Gradients, patterns, masks --></defs>
<!-- Logo elements -->
</svg>
- Size the root
<svg>withviewBoxalone, without fixedwidthorheight, so the logo scales to any container. - Give it a
<title>and<desc>, which screen readers use to describe the logo. - Define gradients, patterns, and masks once in
<defs>and reference them, rather than repeating them inline.
Done when every file meets all three.
6. Deliver
Hand over one SVG file per variation, the color specs (HEX and RGB), and usage guidelines. Done when the user has all three.
04 同仓库更多 Skills
teach
Teach yourself a topic over several sessions, with lessons, references, and a record of what you've learned.
documentation-writer
Writes and revises human-facing documentation — READMEs, contributor and setup guides, reference pages, architecture notes, CLAUDE.md, and changelog entries. Covers picking the right document type for the question being asked, structuring for skimming, writing examples that actually run, and keeping docs from going stale. Use when creating or rewriting docs, when a README has drifted from the code, or when deciding where a piece of information belongs. For SKILL.md and agent files, use /skill-writer instead.
adhd-mode
Shapes every response for a reader with ADHD: the next action first, numbered steps, progress restated each turn, tangents held back, concrete time estimates, wins made visible. Stays on for the rest of the session until the reader says "stop adhd mode". On Claude Code, the harness-kit:adhd output style does the same without invoking this skill.
wait-what
That last message didn't land: re-explain it with the missing context.
to-questionnaire
Turn a decision you can't make alone into a questionnaire for the one person who can answer it, filled in async or together in a meeting.
research
Investigates a question against primary sources (official docs, source code, specs, first-party APIs) and writes the findings, with a citation for every claim, to a Markdown file. Use when the user wants a topic researched or facts gathered from documentation, when a decision waits on facts from outside the repo, and when reading legwork should run while other work continues.