styleseed

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

StyleSeed router

StyleSeed 路由器

Registry-first artifact boundary

优先使用注册表的工件边界

When
.styleseed/project.json
and
.styleseed/artifacts/index.json
exist, resolve the requested artifact ID first, then read only
.styleseed/bundles/<artifact-id>.md
and
.styleseed/manifests/<artifact-id>.json
. Never fall back to the global legacy bundle for a registry project. Legacy projects may use
.styleseed/effective-rules.md
only when no registry exists.
This router chooses exactly one first workflow. It is the primary entry skill when a user asks for StyleSeed help in general terms.
.styleseed/project.json
.styleseed/artifacts/index.json
存在时,先解析请求的工件ID,然后仅读取
.styleseed/bundles/<artifact-id>.md
.styleseed/manifests/<artifact-id>.json
。对于使用注册表的项目,绝不回退到全局遗留包。仅当不存在注册表时,遗留项目才可使用
.styleseed/effective-rules.md
此路由器会选择唯一一个初始工作流。当用户以一般性表述请求StyleSeed帮助时,它是主要的入口技能。

First principles

基本原则

  • Resolve the current artifact first when
    .styleseed/project.json
    and
    .styleseed/artifacts/index.json
    exist.
  • Never fan out to “run every StyleSeed skill.”
  • Never copy the full design handbook into this router. Route to the maintained skill that already owns the workflow.
  • Learning is an optional extension, not part of the core install. Only after an explicit capture request such as “remember this lesson” may the router check whether
    ss-learn
    is separately installed. If absent, state the dependency precisely; never auto-install it.
  • If the request is ambiguous, ask one bounded clarification question that decides the first workflow.
  • .styleseed/project.json
    .styleseed/artifacts/index.json
    存在时,先解析当前工件。
  • 绝不扩散至“运行所有StyleSeed技能”。
  • 绝不将完整设计手册复制到此路由器中。路由至已拥有该工作流的维护技能。
  • 学习功能是可选扩展,不属于核心安装部分。仅当收到明确的捕获请求(如“记住这个知识点”)时,路由器才可检查
    ss-learn
    是否已单独安装。若未安装,需准确说明依赖关系;绝不自动安装。
  • 若请求不明确,提出一个明确的澄清问题以确定初始工作流。

Registry-first artifact boundary

优先使用注册表的工件边界

If the project uses the artifact registry:
  • read the current artifact context first;
  • when one artifact is clearly in scope, route with that artifact;
  • when multiple artifacts exist and the user did not name one, ask one bounded artifact question;
  • do not resolve all artifacts unless the user explicitly asks for all artifacts.
如果项目使用工件注册表:
  • 先读取当前工件上下文;
  • 当某个工件明确在范围内时,携带该工件进行路由;
  • 当存在多个工件且用户未指定其中一个时,提出一个明确的工件选择问题;
  • 除非用户明确要求所有工件,否则不要解析所有工件。

One-workflow routing table

单一工作流路由表

Choose exactly one first workflow:
  • ss-setup
    for first-time method setup, missing lock/setup, or “set up StyleSeed for this project.”
  • ss-build
    for implementing or redesigning a concrete screen/component/page when the direction is already known.
  • ss-reference
    for compiling supplied references that are not already represented by a maintained grammar.
  • ss-studio
    for creative direction, exploration, concept generation, or multi-direction concept work.
  • ss-audit
    for critique, heuristic review, UX issue finding, or “what is wrong with this screen.”
  • ss-score
    for code/design quality scoring or gate-floor measurement.
  • ss-verify
    for rendered pixel inspection, screenshot review, or visual verification.
  • ss-update
    for refreshing an installed StyleSeed payload or checking whether it is current.
  • separately installed
    ss-learn
    only for explicit learning capture requests; otherwise report that the optional learning extension is unavailable.
选择唯一一个初始工作流:
  • ss-setup
    用于首次方法设置、缺少锁定/设置或“为该项目设置StyleSeed”。
  • ss-build
    用于在方向已明确时实现或重新设计具体屏幕/组件/页面。
  • ss-reference
    用于编译未由维护语法表示的提供参考。
  • ss-studio
    用于创意方向、探索、概念生成或多方向概念工作。
  • ss-audit
    用于评审、启发式审查、查找UX问题或“这个屏幕有什么问题”。
  • ss-score
    用于代码/设计质量评分或门槛测量。
  • ss-verify
    用于渲染像素检查、截图审查或视觉验证。
  • ss-update
    用于刷新已安装的StyleSeed负载或检查其是否为最新版本。
  • 仅在明确的学习捕获请求时使用单独安装的
    ss-learn
    ;否则说明可选学习扩展不可用。

Bounded clarification rules

明确澄清规则

Ask one bounded clarification question only when needed to choose the first workflow:
  • setup vs build: “Should I set up the design method first, or build the screen with the current method?”
  • build vs reference: “Should I build from the current method, or compile the supplied reference into a project-local grammar first?”
  • build vs studio: “Do you want one concrete implementation path, or three creative directions first?”
  • audit vs score vs verify: “Do you want UX critique, code-score gating, or pixel verification first?”
  • multi-artifact registry: “Which artifact should I resolve first:
    <id-a>
    or
    <id-b>
    ?”
After one bounded question is answered, route to exactly one first workflow.
仅在需要选择初始工作流时,提出一个明确的澄清问题:
  • 设置 vs 构建:“我应该先设置设计方法,还是使用当前方法构建屏幕?”
  • 构建 vs 参考:“我应该基于当前方法构建,还是先将提供的参考编译为项目本地语法?”
  • 构建 vs 工作室:“你想要一条具体的实现路径,还是先提供三个创意方向?”
  • 评审 vs 评分 vs 验证:“你想要先进行UX评审、代码评分门槛检查,还是像素验证?”
  • 多工件注册表:“我应该先解析哪个工件:
    <id-a>
    还是
    <id-b>
    ?”
在得到一个明确问题的答案后,路由至唯一一个初始工作流。

Direct invocation compatibility

直接调用兼容性

Granular
ss-*
skills remain backward compatible. If the user explicitly invokes
ss-setup
,
ss-build
,
ss-reference
,
ss-studio
,
ss-audit
,
ss-score
,
ss-verify
,
ss-update
, or
ss-learn
, use that direct skill instead of rerouting.
细粒度的
ss-*
技能保持向后兼容。如果用户明确调用
ss-setup
ss-build
ss-reference
ss-studio
ss-audit
ss-score
ss-verify
ss-update
ss-learn
,则使用该直接调用的技能,而非重新路由。