craft-explore — Claude Code skill for design options
The craft-explore Claude Code skill creates alternative designs for a screen, flow, or interface element. It activates when someone asks for options or rejects the current design.
MIT ★ 393 updated 2026-11-15
/plugin marketplace add diego3g/craft
/plugin install craft@craftWhat craft-explore does
The skill helps compare design directions before changing real screens. It clarifies the problem, creates options that differ in structure, interaction, or density, and places them beside the current design. The agent gives its recommendation first, then waits for a choice.
It builds a comparison board in a temporary area, with a legend, the current design, and options rendered at the same size and fidelity. If the project root contains DESIGN.md, the skill reads it; options use the project’s design-system components and tokens. Real screens remain untouched until a choice is made.
A specific edit, such as changing a title or color, does not call for this skill. If no adapter matches the design tool, the agent maps the same actions by hand. With no design tool, it builds the board in HTML. Values estimated from an image are treated as estimates.
What it helps with
- compare distinct directions for a screen
- show the current design beside alternatives
- rethink a rejected design using the stated reason
- apply a chosen direction to screens and the design system
Example prompts for the agent
- Show me several distinct directions for this screen so I can choose.
- I don’t like this flow; rethink it and present alternatives.
- Make two versions of this element for me to compare.
How to install craft-explore
1Plugin marketplace
/plugin marketplace add diego3g/craft/plugin install craft@craftThis installs the whole craft plugin with all its skills
2Skills CLI (Vercel)
npx skills add diego3g/craft --skill craft-explore -a claude-code3Manually: put the files in place
~/.claude/skills/craft-explore/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/craft-explore/
1Skills CLI (Vercel)
npx skills add diego3g/craft --skill craft-explore -a codex2Manually: put the files in place
.agents/skills/craft-explore/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add diego3g/craft --skill craft-explore -a cursor2Manually: put the files in place
.cursor/skills/craft-explore/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install diego3g/craft skills/craft-explore2Manually: put the files in place
.github/skills/craft-explore/SKILL.md1Skills CLI (Vercel)
npx skills add diego3g/craft --skill craft-explore -a gemini-cli2Platform CLI
gemini skills install https://github.com/diego3g/craft --path skills/craft-exploreManually: put the files in place
.devin/skills/craft-explore/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about craft-explore
How do I install craft-explore in Claude Code?
Add the marketplace with /plugin marketplace add diego3g/craft, then install the plugin with /plugin install craft@craft.
What does craft-explore do?
It creates a board that compares the current design with alternative directions and presents a recommendation first. Real screens are changed only after a selection.
When does craft-explore skip the design exploration?
It is not for a specific edit, such as renaming a title or changing a color. It also skips exploration when the request already describes one clear fix.
Source text
SKILL.md · MIT
---
name: craft-explore
description: Use when asked for options, alternatives, variations, directions or "a few ideas" for a screen, flow or element, when the person rejects a design or says they don't like it, or says "rethink this", "try something else" or "design both so I can pick".
---
# Three proposals
## Overview
When someone asks for options, they want to **choose**, not to be handed a winner. Give them three directions that solve the problem in genuinely different ways, side by side, at the same fidelity, next to what exists today, **with your recommendation first**. Then wait for the pick.
## When to use
- "Give me options", "3 variations", "other directions", "what else could this be?"
- "I don't like this", "rethink it", "try something different".
- "Design both so I can choose": that means two.
## When NOT to use
- A specific change ("change the title to Preferences", "make it blue"): make it.
- One clear fix the person already described.
## Before you start
0. Read `DESIGN.md` at the project root if it exists: it is the project's design brief.
1. Read the project's design system and the screen in question. All options use the system's pieces and tokens: options differ in **design**, not in brand.
2. Pick your tool's adapter in `references/adapters/` (`paper.md`, `figma.md`, `html.md`). If no adapter matches your tool, do the same verbs in your tool and say which you mapped by hand. With no design tool at all, build in HTML (`html.md`). If an image is all you have, say that values read from it are estimates.
## Steps
1. **Restate the problem** in one or two sentences: what's wrong today, and what a good result must do. If the request was only "make it better", name the problem you see. **Stop and confirm it with the person before designing.** If they already named the problem, go on.
2. **Choose the directions on different axes** ([divergence axes](references/divergence-axes.md)): structure or placement, interaction model, density, emphasis, or what gets removed. Write each direction as one line: the idea and its trade-off. Directions must differ: a different axis, or clearly different values on one axis when the person names the axis ("too dense" → three density answers). A change of colour, theme or font is never an axis.
3. **Build the comparison board in a temporary area** ([comparison board](references/comparison-board.md)):
- a legend card (each option's idea, what it's good at, what it costs, and the recommendation with its reason);
- **"Current"**, a copy of today's design, when one exists;
- options **A, B, C**, the same size and with the same realistic data.
**Never edit the real screens.**
4. **Draw every option with final-screen care**, including the states that its difference affects. If B moves an action into a menu, show the menu open.
5. **Present the recommendation first**, then one line per option. **Stop. The person picks, combines ("B with A's header"), or rejects all of them.**
6. **After the answer:**
- **Pick or combination:** apply it to the real screens and the design system (and its propagation to every screen that uses a changed piece), then clear the temporary area.
- **All rejected:** go back to step 1 with their reason as the new problem statement. Allow changes to the surrounding parts. Never answer a rejection with small tweaks of the same options.
## Rules
| Rule | Why |
|---|---|
| Three by default; two for "both" (when they named both options, skip the bolder-option rule); exactly the number they ask for otherwise | The count is theirs; three is enough to compare without fatigue |
| Different axes, not different paint | Three layouts in three colour schemes is one idea with three skins |
| Always recommend, and say why | They asked an expert; "tell me which you like" hands the work back |
| "Current" sits on the board | People judge change against what they know |
| Same data, same size, same fidelity | A polished option next to sketches is a vote, not a choice |
| No straw men: every option is one you'd defend | Fake options waste the person's attention and trust |
| One option is deliberately bolder | Otherwise the set only covers safe variations |
| Real screens stay untouched until the pick | Options that leak into the product are decisions nobody made |
## Done when
The board shows the legend, Current and every option at equal fidelity; the recommendation is stated first; you have stopped for the pick. After the pick: applied to the real screens and the system, and the temporary area cleared.
## Common mistakes
| Thought | Reality |
|---|---|
| "Option C: the same page in a dark theme" | Theme is paint, not a direction. Change structure, interaction, density, emphasis or what's removed. |
| "I'll let them choose without biasing them" | Not recommending isn't neutral, it's unhelpful. Recommend first, with the reason. |
| "The original file is unchanged, so they can compare" | Put Current *on the board*, next to the options. |
| "They rejected all three, I'll adjust the closest one" | A rejection is new information about the problem. Restate it and diverge again. |
| "They asked for 5, but 3 is the method" | Give 5. The divergence rule still applies to all of them. |
| "Options share the same fixes, so they look alike" | Shared fixes are fine. Say so once in the legend and make the main axis differ. |
© Diego Fernandes · MIT · diego3g/craft