Agent skill

Craft

by educlopez in educlopez/ui-craft

One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar.

MITAuto-check passedDevOps & Cloud

Install Craft

skills CLI
$ npx skills add educlopez/ui-craft --skill craft -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install educlopez/ui-craft craft --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/educlopez/ui-craft.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/craft .claude/skills/craft && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
craft
GitHub stars
371
Token cost
~1.6k tokens
SKILL.md length
888 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar.

  • Works in 5 steps: Load spec (if present) → Inputs → Craft Read + lock the plan → …
  • The user asks for a whole surface (build me a dashboard
  • SKILL.md covers Step 0 — Load spec (if present), Step 1 — Inputs, Step 2 — Craft Read + lock the… and Step 3 — Build, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Craft is an agent skill from educlopez/ui-craft. 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.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering CI/CD. The repository describes itself as: Design engineering system for AI coding agents — ship UI with craft-level quality. Install as an agent skill. The licence is MIT.

When your agent uses it

  • The user asks for a whole surface (build me a dashboard
  • Hazme un dashboard) and expects a shippable result
  • Not component-level help
  • Asks for craft on their UI

Example prompts

  • “build me a dashboard”
  • “hazme un dashboard”
  • “/craft”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Load spec (if present)
  2. Inputs
  3. Craft Read + lock the plan
  4. Build
  5. Acceptance bar

What it can do on your machine

Read from SKILL.md and the folder at commit ceecc8e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Craft loads about 1.6k tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 888 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from educlopez/ui-craft at commit ceecc8e, republished under its MIT licence (© educlopez). 888 words, ~1,613 tokens.

Download SKILL.mdSave it as .claude/skills/craft/SKILL.md (or your agent's skills folder).
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.

Show full SKILL.md (379 more words)Show less

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. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .codex/skills/craft of educlopez/ui-craft.

Open the folder on GitHubat commit ceecc8e

Compare with similar skills

Craft next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Craft compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Craft this skilleduclopez/ui-craft371—~1.6kAutomated safety check: PassMIT
Winui AppLanceMcCarthy/DevOpsExamples1721 repos~2.8kAutomated safety check: PassApache-2.0
Modern Web GuidanceJetBrains/skills3643 repos~1.4kAutomated safety check: PassApache-2.0
Auto Page Synckennyzir/7deer_skills322—~1.7kAutomated safety check: PassMIT
Cicd Integrationmurphytrueman/design-system-ops203—~5.4kAutomated safety check: PassMIT
Anima CI Integrationjeremylongshore/tons-of-skills-marketplace2.8k—~1.6kAutomated safety check: PassMIT

Similar skills

  • Winui App

    LanceMcCarthy/DevOpsExamples

    Bootstrap, develop, and design modern WinUI 3 desktop applications with C and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns, Windows App SDK samples, and…

    172 GitHub starsUsed in 1 repo~2.8k tokens
    DevOps & CloudAuto-check passed
  • Modern Web Guidance

    JetBrains/skills

    Official

    Search tool for modern web development best practices. An agent skill from JetBrains/skills.

    364 GitHub starsUsed in 3 repos~1.4k tokens
    DevOps & CloudAuto-check passed
  • Auto Page Sync

    kennyzir/7deer_skills

    仓库 Markdown/JSON 内容自动同步到前端页面,配置 GitHub Actions 定时拉取 + 部署,保持 Google SEO 内容新鲜度。支持日报、博客、Changelog、Landing Page 等多种页面模式。

    322 GitHub stars~1.7k tokensUpdated 9 days ago
    DevOps & CloudAuto-check passed
  • Cicd Integration

    murphytrueman/design-system-ops

    Generate CI pipeline files and check scripts (GitHub Actions, GitLab, CircleCI, Bitbucket) that automate design system checks: token validation, hardcoded values, a11y scans, visual regression…

    203 GitHub stars~5.4k tokensUpdated 14 days ago
    DevOps & CloudAuto-check passed
  • Anima CI Integration

    jeremylongshore/tons-of-skills-marketplace

    Configure CI/CD pipeline for automated Figma-to-code generation with Anima.

    2.8k GitHub stars~1.6k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Figma CI Integration

    jeremylongshore/tons-of-skills-marketplace

    Automate Figma design token sync and asset export in CI/CD pipelines.

    2.8k GitHub stars~1.5k tokensUpdated today
    DevOps & CloudAuto-check passed

More from educlopez/ui-craft

All 13 skills in this repo
  • Finalize

    educlopez/ui-craft

    Pre-ship gate — runs detector, verifies brief and tokens, applies the 10-pass finish bar, ranks findings by feedback hierarchy.

    371 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Friction Log

    educlopez/ui-craft

    File contributor or agent papercuts as GitHub issues labeled friction, or investigate those issues as the daily friction-log Cloud Agent.

    371 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Remember

    educlopez/ui-craft

    Record a learned design constraint from a correction into the project brief.

    371 GitHub stars~585 tokensUpdated 1 mo ago
    Auto-check passed
  • Sddesign

    educlopez/ui-craft

    Full spec-driven pipeline — walks brief → tokens → shape (spec) → craft (build) → converge → ship in one guided run.

    371 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Start

    educlopez/ui-craft

    Front door. An agent skill from educlopez/ui-craft.

    371 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Tokens

    educlopez/ui-craft

    Audit or establish the project's 3-layer token spine. An agent skill from educlopez/ui-craft.

    371 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Craft

What does Craft do?

One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Craft is an agent skill from educlopez/ui-craft. One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar.

When should I use Craft?

Craft fits situations like: the user asks for a whole surface (build me a dashboard; hazme un dashboard) and expects a shippable result; not component-level help; asks for craft on their UI.

How do I install Craft in Claude Code?

Run `npx skills add educlopez/ui-craft --skill craft -a claude-code`. Or copy the skill folder (.codex/skills/craft in educlopez/ui-craft) into .claude/skills/craft in your project. Claude Code loads it when a task matches its description.

How do I install Craft in Codex?

Run `npx skills add educlopez/ui-craft --skill craft -a codex`. Or copy the skill folder (.codex/skills/craft in educlopez/ui-craft) into .agents/skills/craft in your project. Codex loads it when a task matches its description.

Can I use Craft in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add educlopez/ui-craft --skill craft -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/craft, .gemini/skills/craft, .github/skills/craft and .opencode/skills/craft in your project.

What does Craft need to run?

SKILL.md names no scripts, command-line tools or credentials: Craft is instructions for the agent only.

Does Craft access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Craft safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Craft use?

Craft is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Craft use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Craft?

Skills that share tags, products or a category with Craft: Winui App (LanceMcCarthy/DevOpsExamples, 172 stars), Modern Web Guidance (JetBrains/skills, 364 stars), Auto Page Sync (kennyzir/7deer_skills, 322 stars) and Cicd Integration (murphytrueman/design-system-ops, 203 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Craft?

educlopez (a GitHub user) maintains it in educlopez/ui-craft, which has 371 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 3, 2026.

Source: educlopez/ui-craft on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.