craft · educlopez — Claude Code skill: what it does, how to install
The craft Claude Code skill builds a complete interface from a surface recipe and checks it against an acceptance bar. It handles requests such as creating a dashboard or landing page.
MIT 594 installs ★ 469 updated 2026-11-06
npx skills add educlopez/ui-craft --skill craft -a claude-codeWhat craft does
The skill also runs in Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. It assembles a full UI surface by choosing a composition and theme, following a build sequence, adding interface states, and checking the result against acceptance criteria. Recipes cover dashboards, landing pages, and authentication.
Before writing code, craft prints a compact plan. A matching section in .ui-craft/spec.md takes priority over recipe defaults. For a surface without a recipe, it switches to standard build mode and uses the closest references.
Landing pages use the MCP tool fold_candidates to select a composition, then check_fold to inspect the built page. If MCP is not connected, craft picks a class from scripts/fold/classes.mjs. Without .ui-craft/brief.md, the project has no saved record of previously used composition classes, so the next selection cannot draw on that history.
What it helps with
- build a dashboard against a defined acceptance bar
- choose a composition and theme for a landing page
- add loading, error, and empty states to a surface
- check a completed interface against its recipe
Example prompts for the agent
- Build a dashboard for this project with the
craftskill. - Create a landing page with
craftand inspect its chosen composition. - Build an authentication screen using
craft.
How to install craft
1Skills CLI (Vercel)
npx skills add educlopez/ui-craft --skill craft -a claude-code2Manually: put the files in place
~/.claude/skills/craft/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/craft/
1Skills CLI (Vercel)
npx skills add educlopez/ui-craft --skill craft -a codex2Manually: put the files in place
.agents/skills/craft/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add educlopez/ui-craft --skill craft -a cursor2Manually: put the files in place
.cursor/skills/craft/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install educlopez/ui-craft cli/assets/codex/skills/craft2Manually: put the files in place
.github/skills/craft/SKILL.md1Skills CLI (Vercel)
npx skills add educlopez/ui-craft --skill craft -a gemini-cli2Platform CLI
gemini skills install https://github.com/educlopez/ui-craft --path cli/assets/codex/skills/craftManually: put the files in place
.devin/skills/craft/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add educlopez/ui-craft --skill craft -a opencodeClaude.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
How do I install craft in Claude Code?
Run npx skills add educlopez/ui-craft --skill craft -a claude-code. The skill file is at ~/.claude/skills/craft/SKILL.md.
What does craft do?
It builds a complete interface surface from a recipe, including its composition, theme, implementation steps, and acceptance checks. Recipes are included for dashboards, landing pages, and authentication.
Which surfaces have craft recipes?
There are recipes for dashboards, landing pages, and authentication. For other surfaces, craft switches to standard build mode and uses the closest references.
Source text
SKILL.md · MIT
--- name: craft description: "One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Use when the user asks for a whole surface (\"build me a dashboard\", \"hazme un dashboard\") and expects a shippable result, not component-level help. Invoke when the user asks for craft on their UI, or mentions 'craft' alongside design / UI / frontend work." --- <!-- HARNESS MIRROR — do not edit here. Canonical source: skills/ or commands/. After editing source, copy into cli/assets/<harness>/ and repo-root harness mirrors. --> **Context:** this sub-skill is one lens of the broader `ui-craft` skill. If the `ui-craft` skill is also installed, read its SKILL.md first for Discovery + Anti-Slop + Craft Test, then apply the specific lens below. Load the `ui-craft` skill. This command BUILDS — it ends with working code that passes the recipe's acceptance bar. Recipes available: `dashboard` → `references/recipe-dashboard.md` · `landing` → `references/recipe-landing.md` · `auth` (sign-in/sign-up) → `references/recipe-auth.md`. If `$ARGUMENTS` names a surface with no recipe yet (settings, docs, e-commerce), say so and fall back to standard Build mode with the closest references — do not improvise a fake recipe. --- ## Step 0 — Load spec (if present) Before anything else: if `.ui-craft/spec.md` exists and contains a `## Surface: <name>` section whose name matches `$ARGUMENTS`, load that section now. Its chosen composition, component inventory, state lattice, and **acceptance bar take precedence over the recipe defaults** for all downstream steps. Note which acceptance bar items came from the spec vs. recipe defaults. ## Step 1 — Inputs Run Stack Detection + Discovery Step 1 (existing tokens, `.ui-craft/brief.md`). Load `references/craft-intent.md`. Ask the recipe's Step 0 questions in ONE compact prompt, pre-filling anything `$ARGUMENTS` or the brief already answers. If the user declines, says "you decide", or has answered before in this session: apply the recipe defaults silently and say which were applied. Never ask twice; never block. Set **DESIGN_VARIANCE** from craft-intent defaults for this surface type unless the user or brief specifies otherwise. ## Step 2 — Craft Read + lock the plan **Output the Craft Read** (one line, craft-intent §1) before any code. Include: surface kind, audience, product vs marketing language, theme/accent, variance, **signature bet**. From the answers: composition + theme preset (or existing tokens) + density + variance + signature bet. If no brand direction, rotate one axis (craft-intent §6) and name it. **Landing surfaces — draw the fold, do not pick it.** Call the `fold_candidates` MCP tool, passing every composition class already listed under `## Fold classes used` in `.ui-craft/brief.md` as `used`. Commit to one of the three it returns, and state the sacrifice that class demands out loud, because that sacrifice is what will make this page look like itself. Do not average the candidates together, and do not fall back to a text-left/visual-right split because it fits everything. It fits everything because it commits to nothing: ten blind builds of this skill produced that fold ten times out of ten, across two unrelated products, while only 3 of 18 reference landing pages use it. If the MCP server is not wired, say so and pick a class from `scripts/fold/classes.mjs` that the brief has not spent yet — the point is the draw, not the tool. Print a short plan (5–7 lines): Craft Read, composition class **and its sacrifice**, theme, signature bet, what's above the fold, what's deferred — then proceed unless the user objects. ## Step 3 — Build Follow the recipe's Build order EXACTLY (tokens → shell → hero tier → primary region → remaining tiers → states → keyboard → finish). Load the references each step names plus `craft-intent.md` patterns for this surface type. **Build the signature bet in this pass** — not later. States and keyboard are build steps, not polish — a surface without empty/loading/error states is not done. ## Step 4 — Acceptance bar Run the recipe's acceptance checklist against the built surface. Fix every unchecked item before reporting — the bar is the definition of done, not a suggestion. **Visual self-check (when a screenshot tool is reachable):** if a Playwright/browser MCP or similar is available, capture the built surface at desktop width and look at it before reporting — a render exposes spacing collisions, hierarchy ties, and dead zones that code review can't. Run the similar-prompt self-test (craft-intent §1) against the screenshot: would this exact page pass for a different brand in the category? If yes, strengthen the signature before reporting. No tool available → skip silently, never block. **Landing surfaces — check the fold you actually built.** Serve the page and call `check_fold` with the URL, the class you drew as `expected_class`, and the costly detail you committed to. It renders in a browser you already have and returns the screenshot alongside its reading. Two things there are worth acting on: **drift**, which means you drew one class and built another — usually the split, since that is the fold the model returns to unprompted — and a **population reading that says the fold stands out nowhere**, which is a prompt to look at the screenshot rather than a fault, since it also flags 7 of 18 reference landing pages. Everything else it returns is measurement without a verdict, and should be read that way. Only two of its invariants are judged, and neither is geometric. **Record what was spent:** append the class you built to `## Fold classes used` in `.ui-craft/brief.md`, creating the section if it is missing. That list is what makes the next `/craft` in this project draw something else. Without it the draw has no memory and the project converges again. **Report to the user:** 1. The Craft Read (repeat) 2. The composition class drawn, and the sacrifice it demanded 3. Which signature bet was built 4. Checklist results 5. Any item the user explicitly waived Lead with intent, not a findings dump. Use the Review Format table only for fixes made in this pass. At CRAFT_LEVEL ≥ 8, finish with the full `/finalize` gate instead of the recipe's minimum passes. **Next step:** `/finalize` — run the pre-ship gate (rung 3). If this project has no brief yet, `/brief` first (rung 2).
© educlopez · MIT · educlopez/ui-craft
Similar skills
All skills for Frontend and UI →craft by other authors comes first.