Back to Details

start

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
<!-- 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.
Orient the user. Load the 
ui-craft
skill, read the current project, and report what ui-craft can do right now for it. This is the front door — most people run it first.
<!-- HARNESS MIRROR — do not edit here. Canonical source: skills/ or commands/. After editing source, copy into cli/assets/<harness>/ and repo-root harness mirrors. -->
背景说明： 此子技能是更广泛的
ui-craft
技能的一个组成部分。如果已安装
ui-craft
技能，请先阅读其SKILL.md了解Discovery + Anti-Slop + Craft Test，再应用以下特定规则。
为用户指引方向。加载
ui-craft
技能，读取当前项目，报告ui-craft当前可为其执行的操作。这是入口命令——大多数人会首先运行它。

ORCHESTRATE-ONLY RULE

仅调度规则

This command detects state and routes. It MUST NOT build, edit, audit, or re-implement any phase logic. It contributes only:
  1. Project detection (read-only).
  2. A "what's available now" map across the three usage layers.
  3. One recommended next step + the command to run for it.
When the user wants to act, hand off to the real command (
/brief
, 
/tokens
, 
/sddesign
, 
/craft
, 
/finalize
, the review agents, etc.). Do not inline their steps.
此命令仅用于状态检测与路由。绝对不能执行构建、编辑、审计或重新实现任何阶段的逻辑。它仅负责：
  1. 项目检测（只读）。
  2. 生成跨三个使用层级的“当前可用功能”映射。
  3. 推荐一个下一步操作及对应的运行命令。
当用户想要执行操作时，将任务移交至实际命令（
/brief
、
/tokens
、
/sddesign
、
/craft
、
/finalize
、审核agent等）。不要将这些步骤内联执行。

Step 1 — Detect (read-only)

步骤1 — 检测（只读）

Scan the project. Do not write anything. Gather:
SignalHow to detectUsed for
Framework / stylingpackage.json deps, config files, file extensions — Tailwind, CSS Modules, styled-components/Emotion, vanilla CSS, Vue/Svelte/Astro SFCConfirm ui-craft adapts to this stack
Token spineCSS vars (
--color-*
, 
--accent-*
, 
--font-*
), Tailwind 
theme.extend
, a token file		Gate: is 
/tokens
needed?
Brief
.ui-craft/brief.md
exists?		Gate: is 
/brief
needed?
External design contract
DESIGN.md
or 
design-tokens.json
at repo root (ecosystem convention some teams use)		Treat as brief + token input — read it, honor it, don't duplicate it
Spec
.ui-craft/spec.md
exists? which surfaces?		Is there work in flight?
HarnessClaude Code (plugin/skill) vs 
.codex
/
.cursor
/
.gemini
/
.opencode
/
.agents
mirror		Which layers are reachable (agents/MCP are Claude Code / MCP-client only)
Existing UIare there components/pages already, or is this greenfield?Build-new vs review/polish framing
Keep detection fast and quiet — a few reads, no deep traversal. Report findings as a short table.
扫描项目。不要写入任何内容。收集以下信息：
信号检测方式用途
框架/样式package.json依赖、配置文件、文件扩展名 — Tailwind、CSS Modules、styled-components/Emotion、原生CSS、Vue/Svelte/Astro单文件组件确认ui-craft是否适配此技术栈
令牌核心CSS变量（
--color-*
、
--accent-*
、
--font-*
）、Tailwind 
theme.extend
、令牌文件		判断是否需要运行
/tokens
Brief是否存在
.ui-craft/brief.md
？		判断是否需要运行
/brief
外部设计约定仓库根目录下是否有
DESIGN.md
或
design-tokens.json
（部分团队使用的生态系统约定）		将其视为brief和令牌输入——读取并遵循，不要重复创建
Spec是否存在
.ui-craft/spec.md
？涵盖哪些界面？		是否有正在进行的工作？
HarnessClaude Code（插件/技能）vs 
.codex
/
.cursor
/
.gemini
/
.opencode
/
.agents
镜像		哪些层级可访问（agent/MCP仅支持Claude Code / MCP-client）
现有UI是否已有组件/页面，还是全新项目？区分是新建UI还是审核/优化场景
保持检测快速且无干扰——仅读取少量内容，不进行深度遍历。将检测结果整理为简短表格呈现。

Step 2 — Report the three layers

步骤2 — 报告三个层级

Print what's available now, mapped to how people actually use ui-craft. Mark each layer ● active / ○ available / – not reachable in this harness.
ui-craft is a design engineering SYSTEM. You're set up for:

● Layer 1 — Just ask
    Describe any UI and the agent designs with taste (anti-slop, system tokens,
    real hierarchy). No command needed. This is the default and the point.

○ Layer 2 — Drive it
    Slash commands for focused passes. Given THIS project:
      <tailored list — see Step 3>

○ Layer 3 — Verify it
    design-reviewer + a11y-auditor agents · ui-craft-mcp gates · UICraftScore · ui-craft-detect CLI.
    <mark – if the harness can't reach agents/MCP, and say so>
Tailor the bullets to the detected state — don't print the generic catalog.
打印当前可用的功能，匹配用户实际使用ui-craft的方式。用●表示已激活 / ○表示可用 / –表示当前harness无法访问，标记每个层级。
ui-craft is a design engineering SYSTEM. You're set up for:

● Layer 1 — Just ask
    Describe any UI and the agent designs with taste (anti-slop, system tokens,
    real hierarchy). No command needed. This is the default and the point.

○ Layer 2 — Drive it
    Slash commands for focused passes. Given THIS project:
      <tailored list — see Step 3>

○ Layer 3 — Verify it
    design-reviewer + a11y-auditor agents · ui-craft-mcp gates · UICraftScore · ui-craft-detect CLI.
    <mark – if the harness can't reach agents/MCP, and say so>
根据检测到的状态调整项目符号内容——不要打印通用目录。

Step 3 — Recommend ONE next step

步骤3 — 推荐一个下一步操作

Pick the single highest-value next action from detected state. Use this decision order:
  1. No brief, non-trivial project → recommend 
    /brief
    ("anchor every later decision to your product's principles — 5 min, writes 
    .ui-craft/brief.md
    ").
  2. Brief exists, no token spine → recommend 
    /tokens
    ("establish the 3-layer token spine so builds match a system, not inline guesses").
  3. Brief + tokens exist, building something net-new → recommend 
    /sddesign <surface>
    (full pipeline) or 
    /craft <surface>
    (one-shot) — ask which.
  4. Existing UI to improve → route by intent: review → 
    ui-craft:design-reviewer
    + 
    ui-craft:a11y-auditor
    (Claude Code) or 
    /critique
    + 
    /audit
    ; polish → 
    /polish
    ; simplify → 
    /distill
    ; flat/generic → 
    /bolder
    ; loud/busy → 
    /quieter
    ; dated site to modernize → 
    /redesign
    .
  5. About to ship / merge → recommend 
    /finalize
    (10-pass gate) and, for CI, 
    npx ui-craft-detect
    or the 
    score_ui
    MCP tool.
Print it as one clear line:
Recommended next: 
…
— <one-sentence why>.
Then offer the full menu only if asked: "Want the full command list, or shall I run that now?"
根据检测到的状态选择单个最高价值的下一步操作。遵循以下决策顺序：
  1. 无brief，非小型项目 → 推荐
    /brief
    （“将后续所有决策锚定到产品原则——耗时5分钟，生成
    .ui-craft/brief.md
    ”）。
  2. 存在brief，无令牌核心 → 推荐
    /tokens
    （“建立三层令牌核心，使构建符合系统规范，而非随机内联样式”）。
  3. 存在brief和令牌，正在构建全新内容 → 推荐
    /sddesign <surface>
    （完整流程）或
    /craft <surface>
    （单次构建）——询问用户选择哪一个。
  4. 现有UI需要优化 → 根据意图路由：审核 → 
    ui-craft:design-reviewer
    + 
    ui-craft:a11y-auditor
    （Claude Code）或
    /critique
    + 
    /audit
    ；优化 → 
    /polish
    ；简化 → 
    /distill
    ；平淡/通用 → 
    /bolder
    ；嘈杂/繁琐 → 
    /quieter
    ；老旧站点现代化 → 
    /redesign
    。
  5. 即将发布/合并 → 推荐
    /finalize
    （10轮检查），对于CI环境，推荐
    npx ui-craft-detect
    或
    score_ui
    MCP工具。
将其打印为清晰的一行：
Recommended next: 
…
— <one-sentence why>.
仅在用户要求时提供完整命令列表：“需要查看完整命令列表，还是现在就运行该命令？”

Step 4 — Hand off

步骤4 — 移交任务

If the user confirms, run the recommended command. Otherwise stop — 
/start
never acts on its own. Its job is done once the user knows where they are and where to go.
如果用户确认，运行推荐的命令。否则停止——
/start
绝不会自行执行操作。一旦用户了解当前状态和下一步方向，它的任务就完成了。

Notes

注意事项

  • Read-only. 
    /start
    writes nothing and changes no code. The artifacts (
    brief.md
    , 
    spec.md
    , tokens) are written by their own commands.
  • Harness honesty. If the project is in a non-Claude-Code harness (
    .codex
    , 
    .cursor
    , etc.), Layer 3 agents and the MCP server may not be reachable from that agent — say so plainly and point to the CLI (
    ui-craft-detect
    ) as the portable verify path.
  • Craft-intent routing. Full-surface builds (
    /craft
    , 
    /sddesign
    ) declare a Craft Read before code. If the user describes a built UI as "generic", "template-y", or "too safe", route to 
    /bolder
    ; if "too loud" or "too busy", route to 
    /quieter
    .
  • Don't re-run Discovery. If a brief or spec already exists, don't interrogate the user for preferences — read the artifacts and report.
Next step: Follow the rung this run named. 
/start
is read-only — the value is in doing the one command it picked.
  • 只读模式：
    /start
    不写入任何内容，也不修改代码。相关产物（
    brief.md
    、
    spec.md
    、tokens）由各自的命令生成。
  • Harness如实告知：如果项目处于非Claude-Code的harness（
    .codex
    、
    .cursor
    等）中，第三层级的agent和MCP服务器可能无法从该agent访问——请明确告知用户，并将CLI工具
    ui-craft-detect
    作为可移植的验证途径。
  • 按设计意图路由：全界面构建命令（
    /craft
    、
    /sddesign
    ）在编写代码前会声明Craft Read。如果用户描述已构建的UI为“通用”、“模板化”或“过于保守”，则路由至
    /bolder
    ；如果描述为“过于嘈杂”或“过于繁琐”，则路由至
    /quieter
    。
  • 不要重复执行Discovery：如果已存在brief或spec，不要询问用户偏好——读取现有产物并报告即可。
下一步： 执行本次推荐的命令。
/start
是只读命令——其价值在于引导您执行它所选择的那一个命令。