AGENT SKILL

open-design-explore

Explore 2–4 deliberately different design directions for one brief, compare them side by side, then build out the one you pick — use whenever the user explicitly asks for several options, directions, alternatives or versions of a design to compare ("show me three directions for…", "a few different takes on…"), even if they don't mention Open Design; not for a single, ordinary design request

License 许可
MIT
最近更新
2026-11-14
Stars
★ 1.1k
Forks
104

01 前言 Front Matter

name
open-design-explore
description
Explore 2–4 deliberately different design directions for one brief, compare them side by side, then build out the one you pick — use whenever the user explicitly asks for several options, directions, alternatives or versions of a design to compare ("show me three directions for…", "a few different takes on…"), even if they don't mention Open Design; not for a single, ordinary design request
argument-hint
what to design, and optionally how many directions or what should vary (e.g. "pricing page, 3 directions")

03 SKILL.md 正文

<!-- generated:curated-entry -->

Explore several deliberately different design directions with Open Design, compare them side by side, and take the chosen one forward.

Brief: "$ARGUMENTS" — or, if that is empty, the user's request in this conversation (if it isn't clear, ask the user: "What should we explore directions for?")

How to talk to the user. Many people using Open Design don't write code, so:

  • Use the user's own words. If they say "artifact", "design tokens" or give a file path, use those terms back; otherwise use the plain words below.
  • Keep the machinery out of replies: no tool names, no ids like od:prototype:poster-hero, no internal files (.artifact.json, .comments.json, config.json), and not the words "register", "manifest", "sidecar", "entry" or "surface", unless the user used them first.
  • Explain a print term the first time it comes up, in one short clause, and not again.
  • Say where a file is the way the user would find it ("in your Open Design folder, under seed-swap-flyer"). Give a raw path only where the user can click it (Claude Code, Claude Desktop's Code tab, VS Code) or asks for it.
  • End each reply that finishes a step with one line on what they can do next, with at most two options ("Want it in Instagram sizes too, or is it ready to print?").
Instead of Say
artifact, entry, registered your design, saved
design system, active design system your style (the first time: "a saved style: colours, fonts and spacing")
surface, skill, template, recipe kind of design, starting layout, or nothing
workspace, output directory your folder, your Open Design folder
bleed print edge ("a few millimetres extra that the printer trims off")
trim size final size
preflight findings, errors "I checked it and fixed…", "one thing to look at:"
export save as PDF, save as an image
inline preview, MCP App the preview above

1. Plan the directions

If the brief is empty, ask the user what to design before doing anything else.

Call list_open_design_skills to find the skill that fits what's being designed (a landing page, a deck, a dashboard…). Then call prepare_open_design_exploration with that skillId and the brief:

  • count: the number of directions the user asked for (2–4). Default 3.
  • If the user named what should vary ("three hero concepts", "different pricing layouts"), pass axis: "custom" and customDirections, one { label, brief } per direction.
  • Otherwise leave axis out. The tool picks visual styles when no design system is active, and layout or narrative structures when one is, so the brand is kept.
  • Pass directionIds only when the brief's tone clearly calls for specific directions, e.g. editorial-monocle for a magazine or brutalist-experimental for an art or agency site.

If the result says the active design system was set aside, tell the user.

2. Generate each direction

For each direction in the result, follow sharedInstructions followed by that direction's own instructions. Write its file at exactly its suggestedEntryPath, then call register_open_design_artifact with the explorationId, the direction's directionId, kind, title and sourceSkillId.

These are sketches: one screen, or a cover plus two slides for a deck. Divergence matters more than polish. If you can delegate to sub-agents, generate the directions in parallel and give each one sharedInstructions plus its own instructions.

3. Compare

Call compare_open_design_exploration with contactSheet: true. If you can view images, open the contact sheet and check that the directions look clearly different (layout and hero pattern, not just colour). Regenerate any direction that resembles another, then compare again.

4. Present

Give the user the comparison page path (it opens in any browser straight from the file system and shows every direction side by side), and the contact sheet path if one was made. In one line each, say how the directions differ. Ask which one to take forward, and whether to:

  • build it out at full fidelity,
  • merge in parts of another direction ("B, with A's hero"), or
  • save it as a design system for later work.

<!-- claude-only --> In Claude Desktop Chat, call show_open_design_artifact with the explorationId to show the directions side by side, and where show_open_design_questions is in your tool list, ask the choice through it instead of a chat message: a direction question with one option per direction (imageRef: "artifact:<its entryPath>"), a next question (Build it out, Merge in parts of another, Save as a design system) and a short text question for anything to change or take from another direction. Read the <!-- od-answers {...} --> line of the reply (you-pick means choose for them), then go on to step 5. If the user types their answer or taps "Take this one" instead, use that. <!-- /claude-only -->

5. Take the choice forward

Call choose_open_design_direction with the explorationId, the chosen directionId, next (build-out, merge with mergeFrom, or save-design-system) and the user's own adjustments as notes. Follow the returned instructions and register the result as they say.

<!-- claude-only --> Artifact preview. If you have an Artifact tool, publish the result as its private artifact preview (the built-out design, not the sketches) once it's registered: call publish_open_design_artifact with provider: "claude-artifact" and follow what it returns. Publish again after each round of feedback you apply; it goes to the same artifact. Give the link once, then just say the preview was updated. <!-- /claude-only -->

04 同仓库更多 Skills

feimacode
feimacode/open-design-agent-kit

youtube-clipper

YouTube clip generation and editing with automated workflows — pull source video, slice highlights, add captions, and export.

★ 1.1k
feimacode
feimacode/open-design-agent-kit

writing-guidelines

Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".

★ 1.1k
feimacode
feimacode/open-design-agent-kit

wpds

WordPress Design System. Apply WordPress's official design tokens, typography, and component patterns to themes and sites.

★ 1.1k
feimacode
feimacode/open-design-agent-kit

weread-year-in-review-video-template

WeRead-inspired HyperFrames video template for vertical annual reading reports, personal reading dashboards, book-note recaps, and shareable year-in-review stories. Use when users want a 9:16 HTML-to-MP4 reading report with warm paper texture, editorial Chinese typography, book-page metaphors, data highlights, and deterministic motion.

★ 1.1k
feimacode
feimacode/open-design-agent-kit

web-design-guidelines

Review UI code for Web Interface Guidelines compliance by the Vercel engineering team. Covers layout, typography, color, motion, and accessibility for product UI.

★ 1.1k
feimacode
feimacode/open-design-agent-kit

web-clone

网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树,覆盖静态站 / React-Vue-Next 内容站 / WebGL-Canvas 重前端站三大分支,并强制核对任何 AI 二手分析里的可执行代码。

★ 1.1k