project-tiny-context-harness 0.7.3 → 0.7.5

package/assets/skills/context_uiux_design/SKILL.md

@@ -1,101 +1,118 @@
----
-name: context_uiux_design
-description: Use when the user explicitly asks for 设计稿, 重做设计, UI/UX 设计方案, UI 设计师, UX 设计师, 视觉设计方案, 视觉专家, 交互设计方案, 界面设计方案, 页面设计方案, 原型设计, 线框图方案, 视觉规范, 设计系统方案, DESIGN.md, Impeccable review, UX designer, UI designer, frontend redesign, visual polish, or design system spec, or when material production UI lacks sufficient or consistent Design Authority in a Minimal Context Harness project. Do not trigger for routine implementation that already has sufficient design authority, local CSS tweaks, UI bug fixes, explicit throwaway prototypes, or generic mentions of 设计, design, or user experience.
----
+---
+name: context_uiux_design
+description: Use when the user explicitly asks to establish, adopt or repair durable UI/UX Design Authority, DESIGN.md, design-system governance, visual standards, stable interaction/surface Context, Impeccable review, visual polish, frontend redesign, or when material production UI lacks sufficient or consistent Design Authority in a Minimal Context Harness project. For standalone generation of low/high-fidelity wireframes, visual candidates, a design prototype or Figma handoff, use an available dedicated Product Design capability instead; do not trigger this Skill solely for resource generation, routine implementation with sufficient authority, local CSS fixes, UI bugs, explicit throwaway prototypes or generic mentions of design.
+---
+
+# Context UIUX Design
+
+## Package-Managed Boundary
+
+This Skill is generated by `ty-context sync` and owned by the Harness package. Do not edit the generated `context_uiux_design` Skill directly.
+
+Project-specific UI/UX and visual design rules belong in a separate project-local Skill under `<harnessRoot>/skills/uiux_design/SKILL.md`. When a project-local Skill and this package-managed Skill both apply, use the more specific project-local Skill as the primary instruction source while keeping durable conclusions in `project_context/**` and `DESIGN.md`. Keep the project-local Skill front matter `description` trigger keywords aligned with this package-managed Skill and the project `AGENTS.md` role-trigger rule; if the project adds or narrows trigger terms, update both places together so agent activation and Tiny Context guidance do not drift apart.
+
+## 目标
 
-# Context UIUX Design
+帮助 agent 在开发工作流中审查、采纳或修复设计权威，把已经选定的界面、交互和视觉结论沉淀成可恢复的 Minimal Context 和 `DESIGN.md`，并保持实现与验证对齐。
 
-## Package-Managed Boundary
+## Design Context Depth / 设计上下文深度
 
-This Skill is generated by `ty-context sync` and owned by the Harness package. Do not edit the generated `context_uiux_design` Skill directly.
+按需使用而不是默认加载全部层级：全局体验原则；跨 surface 的 Product Surface Contract；单屏 Screen Contract；可复用的 Control interaction Context；`DESIGN.md` 视觉系统/引用解释；项目原生 authored targets；verification Context。继续使用现有 `global`、`contract`、area/subdomain、`decision-rationale`、`verification` 和 `implementation-index` 角色，不新增笼统 `design` 或 `screen` 角色。
 
-Project-specific UI/UX and visual design rules belong in a separate project-local Skill under `<harnessRoot>/skills/uiux_design/SKILL.md`. When a project-local Skill and this package-managed Skill both apply, use the more specific project-local Skill as the primary instruction source while keeping durable conclusions in `project_context/**` and `DESIGN.md`. Keep the project-local Skill front matter `description` trigger keywords aligned with this package-managed Skill and the project `AGENTS.md` role-trigger rule; if the project adds or narrows trigger terms, update both places together so agent activation and Tiny Context guidance do not drift apart.
+一项事实只有一个主要 owner：跨页面职责属于 Surface Context，稳定的单屏层级/交互属于 Screen/interaction Context，视觉 token/rationale/reference interpretation 属于 `DESIGN.md`，具体构图属于 selected target，交付范围与证明属于现有 Delivery Contract/verification。使用稳定 surface/control/target key 连接，不复制成彼此竞争的说明。
 
-## 目标
+## External Design Resource Consumption / 外部设计资源消费
 
-帮助 agent 把界面、交互和视觉设计结论沉淀成可恢复的 Minimal Context 和 `DESIGN.md`。
+- Product Design、Figma、图像生成、原型工具或人工设计流程可以在上游产生 flow、低保真、候选方向、已选高保真、token/component/asset 与交互原型；Tiny Context 不复制这些工具的生成流程。
+- 本 Skill 不承担独立资源生产。只有进入默认开发流程或 Long-Task、需要采纳稳定结论时，本 Skill 才消费外部设计 Source。
+- 候选、灵感和未选定输出不是 Context readiness 或实现权威，不能写入 selected registry；选定目标仍必须完成 UI Authority Closure 和 `Context Delta`。
+- 消费时核对产品 Source、Screen/Control Context、`DESIGN.md`、token owner、资源稳定身份及 exact-target 覆盖条件；只把长期稳定且无冲突的事实写入其唯一 owner，不要求统一 pack、目录或工具格式。
+- 设计资源生成本身不改 `project_context/**`、`DESIGN.md` 或 production code。下游采纳、实现与验证仍由当前 Workflow Contract 或 `long-task-workflow` 负责。
 
 ## 工作方式
-
-1. 先读取 `project_context/global.md` 和 `project_context/context.toml`，按 default area、triggers、read_when 选择相关 context。
-2. 如果项目存在 `DESIGN.md`，先读取其 Design Authority 状态、唯一 token 源/生成方向和设计引用；如果用户要求视觉体系、设计稿或界面风格，按 Google `@google/design.md` 的 DESIGN.md 格式创建或更新根目录 `DESIGN.md`。
-3. 整理或生成：用户流程、页面/组件清单、关键状态、交互反馈、响应式边界、a11y 要求、视觉约束、设计 token，以及需要长期复用的 design reference registry。
-4. 涉及 Product Surface（Web 页面、移动/桌面屏幕、游戏 UI/HUD/菜单、CLI/TUI 输出、扩展或设备界面）、前端布局、UI/UX、产品模块边界或信息放置时，把产品/页面定位检查作为前置动作：用户在这个 surface 要完成的判断、产品必须提供的信息/动作/反馈、不应常驻的信息、主层/下钻/运维/诊断/详情归属、布局和信息密度是否匹配任务。多 surface、多平台或多模块归属不清时，先读取相关 Context、搜索入口并结合已有 UI 代码/截图做信息架构 sweep，必要时使用 `context_surface_contract` 做 Surface Contract Check，再收窄到具体视觉或交互实现。该检查是下一步变更分类的输入；只有形成长期 surface 职责、信息架构、交互契约或模块边界结论时才更新 Context 或 `DESIGN.md`。
-   - 若存在 Product Surface Contract，读取并对齐 primary user question、main allows/forbids、drilldown ownership、long-task state 和 verification。
-   - 若缺失且本任务改变 durable surface responsibility，输出 `Surface Contract Delta: required`，把界面职责写入 `project_context/**`；视觉 token、颜色、字体、间距、圆角和视觉 rationale 仍写入 `DESIGN.md`。
-5. 涉及输入、选择、搜索、筛选、表单/配置、调度/时间窗口、预算/配额/限流或加载/空态/错误态等 UI 控件时，用“控件交互框架”检查控件语义、反馈状态、校验、错误预防、可供性和信息密度；这只是通用判断框架，不是固定控件处方。
+
+1. 先读取 `project_context/global.md` 和 `project_context/context.toml`，按 default area、triggers、read_when 选择相关 context。
+2. 如果项目存在 `DESIGN.md`，先读取其 Design Authority 状态、唯一 token 源/生成方向和设计引用。仅当当前开发工作流经 UI Authority Closure 判断长期视觉体系需要采纳或修复时，按 Google `@google/design.md` 的格式创建或更新根目录 `DESIGN.md`；独立资源生成阶段不写入。
+3. 读取已有外部设计资源或其他 selected Source，整理需要采纳的用户流程、页面/组件清单、关键状态、交互反馈、响应式边界、a11y、视觉约束、token 和 design reference registry。若当前请求只是生成资源，转到可用的专用 Product Design 能力；不要在本 Skill 内复制其生成流程或建立强制交付格式。
+4. 涉及 Product Surface（Web 页面、移动/桌面屏幕、游戏 UI/HUD/菜单、CLI/TUI 输出、扩展或设备界面）、前端布局、UI/UX、产品模块边界或信息放置时，把产品/页面定位检查作为前置动作：用户在这个 surface 要完成的判断、产品必须提供的信息/动作/反馈、不应常驻的信息、主层/下钻/运维/诊断/详情归属、布局和信息密度是否匹配任务。多 surface、多平台或多模块归属不清时，先读取相关 Context、搜索入口并结合已有 UI 代码/截图做信息架构 sweep，必要时使用 `context_surface_contract` 做 Surface Contract Check，再收窄到具体视觉或交互实现。该检查是下一步变更分类的输入；只有形成长期 surface 职责、信息架构、交互契约或模块边界结论时才更新 Context 或 `DESIGN.md`。
+   - 若存在 Product Surface Contract，读取并对齐 primary user question、main allows/forbids、drilldown ownership、long-task state 和 verification。
+   - 若缺失且本任务改变 durable surface responsibility，将唯一 `Context Delta` 设为 `required`，把界面职责写入 `project_context/**`；视觉 token、颜色、字体、间距、圆角和视觉 rationale 仍写入 `DESIGN.md`。
+5. 涉及输入、选择、搜索、筛选、表单/配置、调度/时间窗口、预算/配额/限流或加载/空态/错误态等 UI 控件时，用“控件交互框架”检查控件语义、反馈状态、校验、错误预防、可供性和信息密度；这只是通用判断框架，不是固定控件处方。
 6. 界面职责、流程归属和长期交互契约以 `project_context/**` 为准；`DESIGN.md` 负责视觉 token、视觉 rationale、唯一 authored token source/generation direction 和设计引用解释；versioned authored targets 保留在项目原生路径，代码与生成截图只说明当前实现状态。Context 决定“应该是什么”，代码和实现截图揭示“现在是什么”，代码不能静默重定义 Context。
-7. 设计判断或第一处实现编辑前，先给出唯一长期事实判断 `Context Delta: none|required`。若输入包含产品、架构、技术、界面或验收来源，在 agent 内部逐项判断 durable surface / IA / interaction / verification constraint 已被 Context / `DESIGN.md` 覆盖、需要先更新、仅属 task-local、显式 out-of-scope 或需要真实用户决策；不要创建 `plan.md`、Task Contract 文件或 Markdown 映射表。
-8. 普通 UI bug、局部样式或 CSS 修复、测试修复或探索性 spike 不更新 Context，可先改代码；一旦形成长期交互或视觉结论，继续对齐或交付前必须回写 Context 或 `DESIGN.md`。不要把 Context 机械补成代码改动摘要。
-9. 如果二者冲突，显式标记为实现漂移、缺失工作或 Context 过期。
-10. 如果涉及已有 UI，优先结合代码入口、运行截图或用户提供的参考图来描述差异。
-11. 当任务涉及设计稿、重做设计、视觉方案、设计系统、visual polish、frontend redesign 或 frontend styling，且存在可扫描的 UI 代码、页面文件、构建产物目录或本地/远程 URL 时，默认运行 `npx impeccable detect <target>`；实现前可用于识别既有视觉问题，实现后或交付前用于审查结果。没有可扫描目标、命令不可用或扫描失败时，说明原因并继续。
-12. 需要长期沉淀时：
-   - 项目级体验原则和屏幕清单写入 `global.md`。
-   - 模块级 screen contract、state、interaction 和视觉约束写入对应 area / subdomain Context。
-   - 颜色、字体、间距、圆角、组件视觉 token 和视觉 rationale 写入 `DESIGN.md`。
-   - 新 UI context unit 可新增 `project_context/areas/<unit>.md`，并更新 `global.md#Context Index`；复杂项目同时更新 `project_context/context.toml`。
-   - 如果 `upgrade` 自动把深层 `.md` 注册成 area，但语义上更像 foundation / contract / archive，后续应显式调整 manifest role；不要依赖自动迁移判断语义。
-13. Context 只能声明设计验收入口或 smoke 入口，不能伪造“已验证通过”。
-14. Verification / Deployment Role Context 只记录长期可复用的设计验证、smoke、部署或运行初始化路径事实：特殊准备、最短命令或路径、预期阶段 / 信号、可接受 warning、已排除的重复探索点。不要记录一次性测试日志、完整输出、临时 JSON、CI artifact、测试报告、release ledger、secret、token、cookie、device id、raw payload 或完整截图报告。
-15. 收尾时做 `Contract Conformance` 和 Context drift check，只报告轻量状态：`Context: 已更新 ...` 或 `Context: 本次无长期事实变化`。Conformance 说明本次契约满足情况、未满足或延期项和截图 / 手动检查入口；一次性证据、截图结果、测试日志、任务契约和实现摘要不写入 Context。
-
+7. 设计判断或第一处实现编辑前，执行 UI Authority Closure，并给出唯一长期事实判断 `Context Delta: none|required`。对 affected stable surface/control/target keys，在 agent 内部逐项判断 durable surface / IA / interaction / verification constraint 已被 Context / `DESIGN.md` 覆盖、需要先更新、仅属 task-local、显式 out-of-scope 或需要真实用户决策；不要创建 `plan.md`、Task Contract 文件或 Markdown 映射表。冲突的 controlling owners 必须修正 Source/Context/target 或保留 decision required，不能让当前实现或 YAML 静默决定。
+8. 普通 UI bug、局部样式或 CSS 修复、测试修复或探索性 spike 不更新 Context，可先改代码；一旦形成长期交互或视觉结论，继续对齐或交付前必须回写 Context 或 `DESIGN.md`。不要把 Context 机械补成代码改动摘要。
+9. 如果二者冲突，显式标记为实现漂移、缺失工作或 Context 过期。
+10. 如果涉及已有 UI，优先结合代码入口、运行截图或用户提供的参考图来描述差异。
+11. 当任务涉及设计稿、重做设计、视觉方案、设计系统、visual polish、frontend redesign 或 frontend styling，且存在可扫描的 UI 代码、页面文件、构建产物目录或本地/远程 URL 时，默认运行 `npx impeccable detect <target>`；实现前可用于识别既有视觉问题，实现后或交付前用于审查结果。没有可扫描目标、命令不可用或扫描失败时，说明原因并继续。
+12. 需要长期沉淀时：
+   - 项目级体验原则和屏幕清单写入 `global.md`。
+   - 模块级 screen contract、state、interaction 和视觉约束写入对应 area / subdomain Context。
+   - 颜色、字体、间距、圆角、组件视觉 token 和视觉 rationale 写入 `DESIGN.md`。
+   - 新 UI context unit 可新增 `project_context/areas/<unit>.md`，并更新 `global.md#Context Index`；复杂项目同时更新 `project_context/context.toml`。
+   - 如果 `upgrade` 自动把深层 `.md` 注册成 area，但语义上更像 foundation / contract / archive，后续应显式调整 manifest role；不要依赖自动迁移判断语义。
+13. Context 只能声明设计验收入口或 smoke 入口，不能伪造“已验证通过”。
+14. Verification / Deployment Role Context 只记录长期可复用的设计验证、smoke、部署或运行初始化路径事实：特殊准备、最短命令或路径、预期阶段 / 信号、可接受 warning、已排除的重复探索点。不要记录一次性测试日志、完整输出、临时 JSON、CI artifact、测试报告、release ledger、secret、token、cookie、device id、raw payload 或完整截图报告。
+15. 收尾时做 `Contract Conformance` 和 Context drift check，只报告轻量状态：`Context: 已更新 ...` 或 `Context: 本次无长期事实变化`。Conformance 说明本次契约满足情况、未满足或延期项和截图 / 手动检查入口；一次性证据、截图结果、测试日志、任务契约和实现摘要不写入 Context。
+
 ## 内部执行约束与 Conformance
 
 - `Context Delta` 只能是 `none` 或 `required`。`required` 先更新 owning Context 或 `DESIGN.md`；`none` 按现有事实工作，不制造 Context 噪音。
 - Agent 内部计划应保持页面 / 组件任务、用户判断、主辅信息归属、动作层级、输入语义、loading / empty / no-results / stale / error / degraded / success 状态、布局稳定性、非目标与验收入口清晰。
 - 触及 Product Surface 时，同时保持 surface platform、primary user question、main allows/forbids、drilldown ownership、long-task state requirement 和 verification 清晰；字段、枚举、JSON 和截图仅是实现证据。
+- 当 Product Surface 粒度不足以支持 material screen 时，使用 `screen-contract.md` 的按需结构保持 entry/exit/shared state、information hierarchy、regions、fixed/scroll/overlay ownership、navigation/variants 和 material controls 清晰；局部样式修复不补建 Screen Contract。
 - 外部来源的重要约束在内部分类为 Context / `DESIGN.md` 已覆盖、已更新、task-local、显式 out-of-scope 或需要用户决策；存在未处理项时不能声称全量完成。
 - 默认流程不要求或验证固定 `plan.md`、Task Contract 文件、Source-to-Context 表、Context-to-Implementation 表、matrix、verdict 或 evidence ledger；可选 scratch 没有固定名称或权威。
 - `Contract Conformance` 直接检查 controlling Context / `DESIGN.md` 是否到达正确 surface、状态、交互与验证路径并避开 forbidden shortcut。实现偏差修实现；缺少长期事实则返回 `Context Delta: required`，先更新长期事实再对齐。
 - small code task、普通 UI bug、局部 CSS 修复、小重构、测试修复或探索性 spike 不创建额外流程 artifact。
-
-## 信息呈现校准
-
-- 页面设计先回答：产品/页面定位是什么、要解决什么问题、用户需要什么、页面需要提供什么内容/能力/反馈；再决定元素放什么、放哪里、为什么。这是页面变更前置判断，不是实现后的视觉润色。常驻元素应证明它比位置、图标、状态、数据或交互提示更能省注意力。
-- 追求有效信息密度，而不是塞满页面。判断标准是更少无效 chrome、更少解释、更靠近真实内容和可执行动作；警惕用大标题、大容器、空卡片、假摘要或装饰区块制造仪式感。
-- 对返回、刷新、同步、关闭、搜索、展开/收起等熟悉动作，比较 icon-only、紧凑控件、文字按钮和图标+文字哪种最省注意力；如果使用 icon-only，必须保留 `aria-label`、`title`、tooltip 或 hover/focus 说明。动作不熟悉、风险高或需要区分多个相近命令时，文字通常更合适。
-- 常驻文字要克制。用户已经知道且不帮助行动的页面标题、面包屑、说明句或分区名，先判断是否可以删除，而不是先润色；必要解释可进入 tooltip、hover/focus 展开层、空态、详情页、帮助或 Context。
-- 空间应由内容价值支撑。内容少时布局可以收缩到内容附近；警惕保留一整行只有几个字的 header、空指标槽、空列表容器或没有真实数据支撑的摘要。
-- 信息架构按归属放置：真正跨页面的动作可放系统级 chrome，模块动作放模块内部，运维/连接/缓存/后台任务状态只在影响用户判断或行动时进入主工作面，低频系统解释放详情、日志、调试视图或文档。
-- 空态、加载态和错误态必须真实。不要用 fixture、看似真实的 fallback 行或“这里不展示示例数据”这类元说明遮住没有数据；筛选无结果、系统无数据和连接失败要视觉上可区分。
-- 页面稳定性是 UX 合同。滚动条出现、列表加载、tab 切换、虚拟列表高度变化、面板展开收起都不应导致布局跳动；需要时预留 `scrollbar-gutter`、稳定容器尺寸、固定关键控件尺寸和可预测的 loading skeleton。
-- 文案服务任务，不解释设计。主界面避免内部黑话、实现边界说明、生产/示例数据规则和后端来源说明；必要技术细节放到详情、日志、调试视图或运维区域。
-
-## 控件交互框架
-
-- 当界面涉及输入、选择、搜索、筛选、表单/配置、调度/时间窗口、预算/配额/限流或状态反馈时，先判断控件承载的交互语义，而不是直接沿用后端字段形态。
-- 判断输入数据是自由文本、枚举、实体选择、时间/区间、数量/预算还是规则配置；不同语义需要不同的可供性、约束、校验和错误恢复。
-- 明确用户完成动作前后需要的反馈状态：loading、empty、no results、error、disabled、saving、success 和 validation feedback 应该支持用户判断下一步。
-- 检查控件是否给足单位、范围、默认值、示例、推荐值、风险/成本/影响提示；解释应靠近决策点，低频细节可以进 tooltip、详情或帮助。
-- 检查可见标签、helper text、错误文案和状态文案是否是用户语言，而不是内部字段、接口名或枚举名。
-- 自由输入不是禁用项，但要和错误成本匹配：当格式固定、错误代价高或反馈复杂时，应考虑更明确的约束、选择机制或校验反馈。
-- 不把本框架读成固定控件清单：搜索是否自动触发、时间是否用 picker、预算是否用 stepper，都应由数据规模、API 成本、用户任务、错误成本和项目组件体系决定。
-
+
+## 信息呈现校准
+
+- 页面设计先回答：产品/页面定位是什么、要解决什么问题、用户需要什么、页面需要提供什么内容/能力/反馈；再决定元素放什么、放哪里、为什么。这是页面变更前置判断，不是实现后的视觉润色。常驻元素应证明它比位置、图标、状态、数据或交互提示更能省注意力。
+- 追求有效信息密度，而不是塞满页面。判断标准是更少无效 chrome、更少解释、更靠近真实内容和可执行动作；警惕用大标题、大容器、空卡片、假摘要或装饰区块制造仪式感。
+- 对返回、刷新、同步、关闭、搜索、展开/收起等熟悉动作，比较 icon-only、紧凑控件、文字按钮和图标+文字哪种最省注意力；如果使用 icon-only，必须保留 `aria-label`、`title`、tooltip 或 hover/focus 说明。动作不熟悉、风险高或需要区分多个相近命令时，文字通常更合适。
+- 常驻文字要克制。用户已经知道且不帮助行动的页面标题、面包屑、说明句或分区名，先判断是否可以删除，而不是先润色；必要解释可进入 tooltip、hover/focus 展开层、空态、详情页、帮助或 Context。
+- 空间应由内容价值支撑。内容少时布局可以收缩到内容附近；警惕保留一整行只有几个字的 header、空指标槽、空列表容器或没有真实数据支撑的摘要。
+- 信息架构按归属放置：真正跨页面的动作可放系统级 chrome，模块动作放模块内部，运维/连接/缓存/后台任务状态只在影响用户判断或行动时进入主工作面，低频系统解释放详情、日志、调试视图或文档。
+- 空态、加载态和错误态必须真实。不要用 fixture、看似真实的 fallback 行或“这里不展示示例数据”这类元说明遮住没有数据；筛选无结果、系统无数据和连接失败要视觉上可区分。
+- 页面稳定性是 UX 合同。滚动条出现、列表加载、tab 切换、虚拟列表高度变化、面板展开收起都不应导致布局跳动；需要时预留 `scrollbar-gutter`、稳定容器尺寸、固定关键控件尺寸和可预测的 loading skeleton。
+- 文案服务任务，不解释设计。主界面避免内部黑话、实现边界说明、生产/示例数据规则和后端来源说明；必要技术细节放到详情、日志、调试视图或运维区域。
+
+## 控件交互框架
+
+- 当界面涉及输入、选择、搜索、筛选、表单/配置、调度/时间窗口、预算/配额/限流或状态反馈时，先判断控件承载的交互语义，而不是直接沿用后端字段形态。
+- 判断输入数据是自由文本、枚举、实体选择、时间/区间、数量/预算还是规则配置；不同语义需要不同的可供性、约束、校验和错误恢复。
+- 明确用户完成动作前后需要的反馈状态：loading、empty、no results、error、disabled、saving、success 和 validation feedback 应该支持用户判断下一步。
+- 检查控件是否给足单位、范围、默认值、示例、推荐值、风险/成本/影响提示；解释应靠近决策点，低频细节可以进 tooltip、详情或帮助。
+- 检查可见标签、helper text、错误文案和状态文案是否是用户语言，而不是内部字段、接口名或枚举名。
+- 自由输入不是禁用项，但要和错误成本匹配：当格式固定、错误代价高或反馈复杂时，应考虑更明确的约束、选择机制或校验反馈。
+- 不把本框架读成固定控件清单：搜索是否自动触发、时间是否用 picker、预算是否用 stepper，都应由数据规模、API 成本、用户任务、错误成本和项目组件体系决定。
+
 ## 视觉质量校准
-
-- 先判断界面 register：品牌页、营销页、作品集等让设计承载表达；产品工具、后台、dashboard、表单等让设计服务任务。品牌界面可以更强烈地使用图像、色彩和编排；产品界面优先可扫读、稳定组件、熟悉交互和任务效率。
-- 已有 UI 优先保持身份连续性：先找现有 token、组件库、全局 CSS、Tailwind config、截图或代表性页面；除非用户明确要求重设计，不要推翻已建立的字体、颜色、组件语言。
-- 绿色地设计视觉体系时，先说明场景和色彩策略，再选 token：谁在什么环境下使用、界面应该 restrained / committed / full palette / drenched 到什么程度。不要按品类套默认审美。
-- 做设计方案或视觉规范时，显式检查：文字对比度、65-75ch 正文行长、清晰字号层级、响应式边界、44px 触控目标、焦点态、hover/active/disabled/loading/error/success 状态、空态/错误态/长文本、reduced motion 和文本不溢出。
-- 避免常见 AI 视觉反模式：嵌套卡片、无意义玻璃拟态、紫蓝渐变或渐变文字、灰字压在彩色背景上、默认米色/奶油色大背景、过度圆角、边框加大模糊阴影的幽灵卡片、每段一个圆角 icon tile、每节重复小号全大写 eyebrow 或 `01 / 02 / 03` 标记、bounce/elastic easing、空泛营销 buzzword。
-- 视觉审查时先分清问题类型：a11y / responsive / theming / interaction / copy / performance / anti-pattern。把真正影响用户理解、操作或品牌信任的问题列为高优先级；少量纯审美偏好不要淹没关键问题。
+
+- 先判断界面 register：品牌页、营销页、作品集等让设计承载表达；产品工具、后台、dashboard、表单等让设计服务任务。品牌界面可以更强烈地使用图像、色彩和编排；产品界面优先可扫读、稳定组件、熟悉交互和任务效率。
+- 已有 UI 优先保持身份连续性：先找现有 token、组件库、全局 CSS、Tailwind config、截图或代表性页面；除非用户明确要求重设计，不要推翻已建立的字体、颜色、组件语言。
+- 绿色地设计视觉体系时，先说明场景和色彩策略，再选 token：谁在什么环境下使用、界面应该 restrained / committed / full palette / drenched 到什么程度。不要按品类套默认审美。
+- 做设计方案或视觉规范时，显式检查：文字对比度、65-75ch 正文行长、清晰字号层级、响应式边界、44px 触控目标、焦点态、hover/active/disabled/loading/error/success 状态、空态/错误态/长文本、reduced motion 和文本不溢出。
+- 避免常见 AI 视觉反模式：嵌套卡片、无意义玻璃拟态、紫蓝渐变或渐变文字、灰字压在彩色背景上、默认米色/奶油色大背景、过度圆角、边框加大模糊阴影的幽灵卡片、每段一个圆角 icon tile、每节重复小号全大写 eyebrow 或 `01 / 02 / 03` 标记、bounce/elastic easing、空泛营销 buzzword。
+- 视觉审查时先分清问题类型：a11y / responsive / theming / interaction / copy / performance / anti-pattern。把真正影响用户理解、操作或品牌信任的问题列为高优先级；少量纯审美偏好不要淹没关键问题。
 - Harness 默认携带 Impeccable CLI 能力；做设计稿、重做设计、视觉设计方案、设计系统方案、frontend redesign、visual polish 或既有 UI 视觉审查时，默认尝试运行 `npx impeccable detect <target>` 作为辅助证据，不必等待用户点名。其输出只能作为设计缺陷线索，不是 Harness gate，也不能替代人工截图检查、项目测试或 `validate-context`。
 
 ## Design Authority Readiness / 设计权威就绪
 
 Use this check before material production UI: a new or redesigned screen, primary layout/navigation/theme/component system, high-fidelity implementation or substantial visual polish. Routine implementation with sufficient authority, local style fixes and explicit throwaway prototypes stay on the lightweight path.
 
+Configured is system-level visual authority only, not surface implementation-ready status. `DESIGN.md` 被识别为 configured 只说明项目级视觉系统不是 starter，不表示任一页面已可高保真实现。affected surface 还必须拥有充分的 Screen/Control meaning、覆盖该 claim 的 selected target/constraints、唯一 token source 和项目可执行的验证路径；任何缺失都按 UI Authority Closure 路由，而不是伪造一个全局 readiness 状态。
+
 - Read the owning surface/interaction Context, `DESIGN.md`, the authored exact-value token source and generation direction, existing production components/routes and every material design reference.
 - Classify each reference as `exact-target`, `constraint` or `inspiration`. Record the affected surface/route/component, project path or URI and relevant viewport/theme/mode/state. Exact targets authorize fidelity comparison only for those conditions; constraints authorize only their named rule; inspiration proves no reproduction claim.
 - Treat a missing `DESIGN.md`, its package starter with Design authority status: `unconfigured`, style-only prose, an inspiration-only set or conflicting references as insufficient authority for invented production layout.
-- If the user explicitly delegates design, use known product goals, preferences and references to author/select a separate target before implementation and update durable Context/`DESIGN.md` when the choice is stable. Ask only when an unknown material preference could change the result or the user reserves the choice.
+- If the user explicitly delegates standalone design-resource generation, use an available dedicated Product Design capability to author candidate or selected upstream Source. In this downstream Skill, adopt a selected target into durable Context/`DESIGN.md` only after UI Authority Closure. Ask only when an unknown material preference could change the result or the user reserves the choice.
 - Never use the implementation's own generated screenshot or diff as the target it claims to match. A target is selected Source; an implementation render is evidence. Baseline replacement requires deliberate review and cannot merely erase a failure.
 - Do not require Figma, a fixed `docs/design/**` tree, an image for every local change or universal pixel-perfect thresholds. Use project-native design assets and the smallest authority sufficient for the claimed fidelity.
 
 ## Visual Delivery Coverage / 视觉交付覆盖
 
-For material design-system, redesign, high-fidelity implementation or visual-polish work, keep a task-local **Visual Coverage Set** before implementation and verification. It is internal planning, not a required file, matrix, Context role, workflow artifact or completion authority.
+For material design-system, redesign, high-fidelity implementation or visual-polish work, keep a task-local **Visual Coverage Set** before implementation and verification. When external design Source declares coverage, reconcile it with current delivery scope rather than creating competing authority. The downstream working set remains internal planning, not a required file, matrix, Context role, workflow artifact or completion authority.
 
 - Select risk-proportional representative combinations across production surface/route/component, viewport, theme or product mode, interaction/state, content stress and accessibility/motion conditions. Do not expand the full Cartesian product unless Source explicitly requires full combination coverage, and never claim an unchecked combination.
 - Cover relevant states such as default, hover, focus, active, disabled, loading, empty/no-results, error, success and long/extreme content. Use the project's declared viewport, contrast, target-size, reduced-motion and localization rules rather than inventing universal thresholds.
@@ -105,32 +122,32 @@ For material design-system, redesign, high-fidelity implementation or visual-pol
 - Render and inspect the declared coverage with project-owned browser/component tests plus screenshots or manual review as appropriate. Report the combinations actually checked and any omitted or external review explicitly. A screenshot baseline may be updated only through deliberate review; replacing it merely to erase a diff is not verification.
 
 ## 输出边界
-
-- 不默认创建 `.work_products/**`、UI/UX 独立文档、handoff matrix、review/test/release 文档。
-- 不要求 lifecycle phase、plan task、phase gate 或阶段 Skill。
-- 如果用户明确要求独立设计稿、mock 或页面说明，可以临时生成；长期事实仍要提炼回 `project_context/**` 和 `DESIGN.md`。
-- `DESIGN.md` 是视觉设计系统事实源；项目流程、模块契约和下一步动作仍以 `project_context/**` 为准。
-- 如果普通页面实现已经有充分 Design Authority，或用户只要求修复 UI bug、局部改 CSS、换颜色、明确的 throwaway prototype，或只是泛泛提到“设计 / design / user experience”，不需要触发本 Skill；明确角色/产物、视觉体系工作，或 material production UI 缺失/冲突的 Design Authority 才使用。
-
-## DESIGN.md 使用规则
-
-- 使用 Google `@google/design.md` 格式：YAML front matter 存 tokens，Markdown body 存设计理由。
+
+- 不默认创建 `.work_products/**`、UI/UX 独立文档、handoff matrix、review/test/release 文档。
+- 不要求 lifecycle phase、plan task、phase gate 或阶段 Skill。
+- 如果用户明确要求独立设计稿、mock、线框图、原型或 Figma handoff，使用可用的专用 Product Design 能力；本 Skill 只在后续开发流程中采纳长期事实。
+- `DESIGN.md` 是视觉设计系统事实源；项目流程、模块契约和下一步动作仍以 `project_context/**` 为准。
+- 如果普通页面实现已经有充分 Design Authority，或用户只要求修复 UI bug、局部改 CSS、换颜色、明确的 throwaway prototype，或只是泛泛提到“设计 / design / user experience”，不需要触发本 Skill；durable 视觉体系/Context 采纳，或 material production UI 缺失/冲突的 Design Authority 才使用。明确要求设计资源产物但尚未进入采纳/实现流程时使用专用 Product Design 能力。
+
+## DESIGN.md 使用规则
+
+- 使用 Google `@google/design.md` 格式：YAML front matter 存 tokens，Markdown body 存设计理由。
 - 优先包含 `name`、`colors`、`typography`、`spacing`、`rounded` 和必要 `components` token。
 - 在 `Overview` 内维护 Design Authority 状态、唯一 authored token source/generation direction 和 design reference registry；每个 durable reference 记录稳定 id、surface/route/component、path/URI、`exact-target` / `constraint` / `inspiration` 解释及覆盖条件。不要添加 Google schema 不支持的 front-matter keys。
-- Markdown section 顺序优先为：`Overview`、`Colors`、`Typography`、`Layout`、`Elevation & Depth`、`Shapes`、`Components`、`Do's and Don'ts`。
-- 写入或修改后，如本地可用，运行 `npx @google/design.md lint DESIGN.md` 检查结构；不要把 lint 结果写成“已通过”除非本轮真实执行。
-- 需要给工程消费 token 时，可用 `npx @google/design.md export --format css-tailwind DESIGN.md` 或 `json-tailwind` 生成临时输出。
-
-## 建议沉淀位置
-
-- `global.md#UX / Screen Brief`：全局体验原则、主要屏幕、跨模块流程。
-- `areas/*.md#User / System Contract`：页面、组件、状态、交互和数据展示契约。
-- `areas/*.md#Key Constraints`：responsive、a11y、品牌/视觉边界、加载/空态/错误态约束。
-- role=`contract` Context：跨页面 / 跨域界面契约及其 durable rationale。
-- role=`decision-rationale` Context：更大或跨切面的稳定交互、信息架构或 surface ownership 取舍原因。
-- `areas/*/verification.md` 或 role=`verification` Context：UI smoke、截图验收、可访问性检查或项目自己的关键验证重复执行路径。
-- `areas/*/deployment.md` 或 role=`deployment` Context：前端部署、预览环境、运行拓扑或健康检查重复执行路径。
-- `project_context/context.toml`：复杂项目的产品域 area/context_unit、role、触发词、按需读取策略和可选边界规则。
+- Markdown section 顺序优先为：`Overview`、`Colors`、`Typography`、`Layout`、`Elevation & Depth`、`Shapes`、`Components`、`Do's and Don'ts`。
+- 写入或修改后，如本地可用，运行 `npx @google/design.md lint DESIGN.md` 检查结构；不要把 lint 结果写成“已通过”除非本轮真实执行。
+- 需要给工程消费 token 时，可用 `npx @google/design.md export --format css-tailwind DESIGN.md` 或 `json-tailwind` 生成临时输出。
+
+## 建议沉淀位置
+
+- `global.md#UX / Screen Brief`：全局体验原则、主要屏幕、跨模块流程。
+- `areas/*.md#User / System Contract`：页面、组件、状态、交互和数据展示契约。
+- `areas/*.md#Key Constraints`：responsive、a11y、品牌/视觉边界、加载/空态/错误态约束。
+- role=`contract` Context：跨页面 / 跨域界面契约及其 durable rationale。
+- role=`decision-rationale` Context：更大或跨切面的稳定交互、信息架构或 surface ownership 取舍原因。
+- `areas/*/verification.md` 或 role=`verification` Context：UI smoke、截图验收、可访问性检查或项目自己的关键验证重复执行路径。
+- `areas/*/deployment.md` 或 role=`deployment` Context：前端部署、预览环境、运行拓扑或健康检查重复执行路径。
+- `project_context/context.toml`：复杂项目的产品域 area/context_unit、role、触发词、按需读取策略和可选边界规则。
 - `DESIGN.md`：视觉 identity、design tokens、组件视觉规则、do/don't、视觉 rationale、唯一 token source/generation direction 和 design reference registry。
-
-不要编造 rationale；仅由当前代码或截图形态反推的理由、实现摘要、PR notes、命令输出、测试通过声明、截图审查、debug 过程和 agent reasoning 不进入 Context 或 `DESIGN.md`。
+
+不要编造 rationale；仅由当前代码或截图形态反推的理由、实现摘要、PR notes、命令输出、测试通过声明、截图审查、debug 过程和 agent reasoning 不进入 Context 或 `DESIGN.md`。

package/assets/skills/long-task-workflow/SKILL.md

@@ -1,84 +1,84 @@
----
-name: long-task-workflow
-description: Author, preflight, execute, resume, verify, or close one complete Single-Goal Delivery Contract in the current native Goal and workspace. Use only when explicitly invoked or a valid common-dir active authority binding exists.
----
-
-# Single-Goal Long-Task Workflow
-
-## Boundaries
-
-Use one current native Goal, one repository, one selected workspace, one complete Contract and one Final Gate. Never create a scheduler, model worker, agent runtime, App Server, branch, worktree, merge, push, PR, deployment, Campaign/SFC/Packet/Wave chain, matrix, verdict or second Contract plan. Never activate from task size alone.
-
-The host and user own model selection and native-Goal lifecycle. The workflow has exactly one user-choice checkpoint after the first Authority Lock and before implementation; Harness neither switches the model nor persists model-routing/checkpoint state. No checkpoint file, acknowledgement state, model route, model-tier scheduler, automatic model switch, `authority_revision_in_progress` state or native-Goal completion state is created. Outside that boundary, do not pause a healthy Goal solely to change or downgrade the model. Do not create a separate approval checkpoint for a defensible recommended plan choice. A targeted pre-Authority clarification is still required when a missing user preference could materially change research or selection; genuine Source conflicts or choices the user explicitly reserves may likewise require a decision before Authority Lock. Capability-related drift is handled by targeted repair plus the Final Gate. Never proactively spawn, assign or coordinate parallel subagents. Platform-native internal delegation, if it occurs, is opaque and non-authoritative and must converge into the unified current workspace snapshot before verification can count.
-
-`long-task-delivery-v2` is the only active Contract schema. `delivery-contract.yaml` is the root authoring file. New authoring uses inline Outcomes; existing `outcome_files` are physical compatibility only. `delivery-set` is retired and non-executing.
-
-## Controlling Objective
-
-Prevent false completion inside declared authority. Implementation may drift, fail or require rework, but every declared non-Result requirement and AC must remain traceable and every unsatisfied, unverifiable, insufficiently evidenced or stale item must block completion. Findings should localize repair through Source Item, Outcome, Claim, Assertion, Check, Proof Surface, Binding and owner boundary.
-
-Only fresh evidence from the complete current final snapshot may create machine acceptance. Otherwise report the task as unfinished or qualified. `machine_accepted_external_pending` means machine-verifiable authority passed while named external confirmation remains; it is not full delivery completion. Machine acceptance covers declared machine Authority and has no direct native-Goal effect. Never substitute prose, progress, historical tests, Receipts, one exit code or Agent judgment for the Final Gate.
-
-Prefer the lowest practical Authoring, Runtime, State, Recovery and verification cost that preserves the same false-completion interception. Add no mechanism whose distinct protection does not materially exceed its total cost.
-
-## Progressive Reference Loading
-
-Read only the reference needed for the current phase; these files are guidance, not new artifacts or authority:
-
-- Before creating or structurally revising Source markers, Outcomes, requirements, controls, obligations, architecture boundaries, paths, Bindings, Assertions or risk, read [`references/contract-authoring.md`](references/contract-authoring.md).
-- Before creating or repairing Checks, runners, Observations, proof surfaces, Playwright/structured evidence, Counterfactuals, Population or environment probes, read [`references/evidence-design.md`](references/evidence-design.md).
-- Before Preflight, Compile, protected revision, resume, targeted verify, Final Gate, Stop, close or abandon, read [`references/authority-lifecycle.md`](references/authority-lifecycle.md).
-
-Do not copy reference detail into another plan or state file. The same `delivery-contract.yaml`, active authority and current workspace remain the only lifecycle surfaces.
-
-## Contract Draft And Outcome Decomposition
-
-Before the first successful formal Compile, continuously revise the same non-authoritative `delivery-contract.yaml` as the Contract Draft. It need not be completed in one response; keep reading Source, repository and relevant Context and feed Preflight findings back into that same Draft. Draft authoring, Preflight, Compile, rolling execution, targeted verification and Final Gate are one `long-task-workflow` lifecycle. Do not create a standalone Contract Draft Skill, Draft Receipt, Authoring State, draft schema/CLI/runtime state or second plan.
-
-A Draft Outcome is an Outcome in that pre-Authority-Lock Draft, not a new schema field or runtime entity. Decompose only independently observable, decidable and target-verifiable results whose dependencies and owner boundary can be stated. Use those boundaries to keep a dependency-ready working set, target verification, localize failures, resume findings/next actions and stale local results precisely.
-
-`depends_on` means acceptance readiness. The current Goal may form a temporary Rolling Frontier from ready Outcomes and findings, but must not persist a scheduler, Worker queue, mandatory implementation DAG, model route or process tree. Never split for response/YAML/file length, implementation layer, module/file count, Agent capacity, Worker assignment or desired parallelism.
-
-> Outcome decomposes execution and diagnosis, not completion authority.
-
-## Entry And Authoring Loop
-
+---
+name: long-task-workflow
+description: Author, preflight, execute, resume, verify, or close one complete Single-Goal Delivery Contract in the current native Goal and workspace. Use only when explicitly invoked or a valid common-dir active authority binding exists.
+---
+
+# Single-Goal Long-Task Workflow
+
+## Boundaries
+
+Use one current native Goal, one repository, one selected workspace, one complete Contract and one Final Gate. Never create a scheduler, model worker, agent runtime, App Server, branch, worktree, merge, push, PR, deployment, Campaign/SFC/Packet/Wave chain, matrix, verdict or second Contract plan. Never activate from task size alone.
+
+The host and user own model selection and native-Goal lifecycle. The workflow has exactly one user-choice checkpoint after the first Authority Lock and before implementation; Harness neither switches the model nor persists model-routing/checkpoint state. No checkpoint file, acknowledgement state, model route, model-tier scheduler, automatic model switch, `authority_revision_in_progress` state or native-Goal completion state is created. Outside that boundary, do not pause a healthy Goal solely to change or downgrade the model. Do not create a separate approval checkpoint for a defensible recommended plan choice. A targeted pre-Authority clarification is still required when a missing user preference could materially change research or selection; genuine Source conflicts or choices the user explicitly reserves may likewise require a decision before Authority Lock. Capability-related drift is handled by targeted repair plus the Final Gate. Never proactively spawn, assign or coordinate parallel subagents. Platform-native internal delegation, if it occurs, is opaque and non-authoritative and must converge into the unified current workspace snapshot before verification can count.
+
+`long-task-delivery-v2` is the only active Contract schema. `delivery-contract.yaml` is the root authoring file. New authoring uses inline Outcomes; existing `outcome_files` are physical compatibility only. `delivery-set` is retired and non-executing.
+
+## Controlling Objective
+
+Prevent false completion inside declared authority. Implementation may drift, fail or require rework, but every declared non-Result requirement and AC must remain traceable and every unsatisfied, unverifiable, insufficiently evidenced or stale item must block completion. In particular, a proxy target, presence text, degradation path, fixed input, self-reported boundary effect or internal entrypoint must never substitute for the declared target behavior. Findings should localize repair through Source Item, Stage, Outcome, Claim, Assertion, Check, Evidence Capability, execution target, Binding and owner boundary.
+
+Only fresh evidence from the complete current final snapshot may create machine acceptance. Otherwise report the task as unfinished or qualified. `machine_accepted_external_pending` means machine-verifiable authority passed while named external confirmation remains; it is not full delivery completion. Machine acceptance covers declared machine Authority and has no direct native-Goal effect. Never substitute prose, progress, historical tests, Receipts, one exit code or Agent judgment for the Final Gate.
+
+Prefer the lowest practical Authoring, Runtime, State, Recovery and verification cost that preserves the same false-completion interception. Add no mechanism whose distinct protection does not materially exceed its total cost.
+
+## Progressive Reference Loading
+
+Read only the reference needed for the current phase; these files are guidance, not new artifacts or authority:
+
+- Before creating or structurally revising Source markers, Outcomes, requirements, controls, obligations, architecture boundaries, paths, Bindings, Assertions or risk, read [`references/contract-authoring.md`](references/contract-authoring.md).
+- Before creating or repairing Checks, runners, Observations, proof surfaces, Playwright/structured evidence, Counterfactuals, Population or environment probes, read [`references/evidence-design.md`](references/evidence-design.md).
+- Before Preflight, Compile, protected revision, resume, targeted verify, Final Gate, Stop, close or abandon, read [`references/authority-lifecycle.md`](references/authority-lifecycle.md).
+
+Do not copy reference detail into another plan or state file. The same `delivery-contract.yaml`, active authority and current workspace remain the only lifecycle surfaces.
+
+## Contract Draft And Outcome Decomposition
+
+Before the first successful formal Compile, continuously revise the same non-authoritative `delivery-contract.yaml` as the Contract Draft. It need not be completed in one response; keep reading Source, repository and relevant Context and feed Preflight findings back into that same Draft. Draft authoring, Preflight, Compile, rolling execution, targeted verification and Final Gate are one `long-task-workflow` lifecycle. Do not create a standalone Contract Draft Skill, Draft Receipt, Authoring State, draft schema/CLI/runtime state or second plan.
+
+A Draft Outcome is an Outcome in that pre-Authority-Lock Draft, not a new schema field or runtime entity. Decompose only vertical, independently observable, decidable and target-verifiable results whose dependencies and owner boundary can be stated; one Outcome belongs to one declared Stage and does not span materially different success paths. Declare the ordered Stage DAG and one gate Outcome per Stage in the same Contract. Use those boundaries to keep a stage-constrained dependency-ready working set, target verification, localize failures, resume findings/next actions and stale local results precisely.
+
+`depends_on` means acceptance readiness. The gate Outcome transitively depends on the rest of its Stage, later Stage Outcomes depend on prerequisite gate Outcomes, and every multi-Outcome gate proves cross-surface consistency. The current Goal derives a temporary Rolling Frontier from Stage and Outcome status, but must not persist a Stage Receipt, scheduler, Worker queue, mandatory implementation DAG, model route or process tree. Never split for response/YAML/file length, implementation layer, module/file count, Agent capacity, Worker assignment or desired parallelism.
+
+> Outcome decomposes execution and diagnosis, not completion authority.
+
+## Entry And Authoring Loop
+
 1. Read the user request or external proposal plus minimum controlling Context and decide `Context Delta: none|required`.
-   - For material production UI, read the Contract-authoring visual guidance before Compile. An unconfigured starter, style-only rule or inspiration-only reference is incomplete design authority unless Source explicitly scopes the result as prototype/non-fidelity or delegates a separate selected target before implementation.
-2. If a valid active binding exists, run `ty-context long-task resume <workdir>` and read the lifecycle reference.
-3. Otherwise author one complete Delivery Contract for the whole selected delivery. Do not create a second Contract plan, matrix or top-level Contract split.
-4. Preserve at least one real `source_path`. Wrap every material Source item in its original Markdown with non-rendering `ty-source-item:start/end` markers without rewriting the text; marked Source Item keys and `source_claim` keys are exactly equal.
-5. An ordinary prose plan or optional Source Plan remains valid Source after marker-only enumeration and does not need to match the recommended Source Plan structure. Preserve stable semantic keys and Markdown anchors where practical.
-6. Continue reading repository, Source and Context and revise the same Draft. A request to synthesize, refine, complete, implement or use judgment delegates plan-level authoring, but it does not invent the user's tradeoff priorities. Before comparative research or a material product, technical, architecture or provider selection, identify the criteria that could change the research scope, candidate set or recommendation. Infer them only from the user's words, Source, Context or controlling constraints. If quality versus cost, speed, reliability, privacy, lock-in, operational burden or another material priority is unknown or ambiguous, stop before that research or selection and ask one concise targeted clarification. Do not impose a questionnaire, re-ask known preferences or interrupt minor reversible choices whose recommendation would not change.
-7. Once the material preference envelope is clear, decide what research is needed. Use current authoritative or primary evidence for external capability, pricing, quota, license, compatibility, region, security posture or support claims. When one recommendation is then defensible, record it in real Source with the authoring instruction, preference/evidence basis and exact added meaning instead of pausing for approval. Append the delegated item without rewriting the user's original text when ordinary prose is the Source. Return only when authoritative requirements conflict, the user explicitly reserves the choice, a material preference remains unknown, critical semantics have no defensible recommendation or no falsifiable acceptance standard can be formed.
-8. Contract expansion remains limited to meaning-preserving structural decomposition, evidence-backed repository binding and choices first recorded as delegated real Source. Never place a new product rule, default, threshold, recovery behavior, permission or platform/data scope only in Contract YAML. Default plan delegation authorizes meaning, not action: payment, contracting, production deployment or publication, destructive production mutation, real permission grants, sensitive-data transmission and required legal/security/human approval remain named external confirmations. Any conflicting, user-reserved, missing-preference or unsupported semantic remains `decision_required`.
-9. Run read-only `ty-context long-task preflight <workdir>`, repair every error and `decision_required` finding in the same Draft, then formally Compile only when ready.
-10. When the first Compile returns `execution_model_checkpoint.required: true`, stop before implementation and ask the user to choose `continue_current_model` or switch models and then resume the active Long-Task. A task-specific choice already stated explicitly satisfies the checkpoint. Later revisions return `required: false` and do not repeat it.
-
-Architecture quality uses the existing authority model, not a new gate: when Source or controlling Context declares an architecture invariant, encode it as a Source-backed technical obligation/global constraint/forbidden shortcut plus owner/path/Binding boundaries and a project-owned executable Check. Functional acceptance cannot substitute when the architecture claim can fail independently. An unverifiable design preference remains task-local, durable Context or `decision_required`; it must not be promoted into false proof.
-
-## Rolling Execution
-
-After Authority Lock and the one-time execution-model checkpoint are satisfied, implement dependency-ready Outcomes in the current workspace. Small implementation plans and repair hypotheses are internal execution state and cannot silently change Product, Technical or Acceptance authority.
-
-Re-evaluate `Context Delta` whenever implementation or repair discovers a durable fact. Controlling Context changes use protected revision; graph-derived, non-explicit `implementation-index` and `archive` are Supporting Context in referenced mode and may auto-revise when only navigation/background changed. Full snapshot mode treats every selected Context file as controlling.
-
-Use targeted `verify --outcome/--check` only to drive repair. Progress is repair evidence only and never acceptance authority. Keep precise findings attached to the owning Source item, Claim, Assertion, Check, Binding and owner path. Do not add another model-switch pause or coordinate parallel subagents.
-
-When the Contract declares a target-runtime Check because a proxy can pass while the target fails independently, run it at the earliest owning Outcome's first runnable boundary. After accumulated changes to its declared `input_paths` or Binding carriers make the result stale, rerun it before dependent work grows. Coalesce related edits and use the cheapest reliable target Check; do not mandate a full environment rebuild per Outcome or per edit. This is rolling feedback through existing targeted verify, not acceptance, a trigger queue, platform taxonomy or new state.
-
-When implementation discovers a blocker or missing Contract paths, first classify the revision. Difficulty or delay alone never reclassifies machine-verifiable scope as external and never removes Source; a real scope, Product, Acceptance or machine/external boundary change must first be explicit marked Source. Proven monotonic evidence strengthening may use ordinary `compile --revise` directly. If every protected reason is only owner/expected-change/allowed-support expansion, continue editing the same `delivery-contract.yaml` and use `ty-context long-task diagnose-revision <workdir> [--outcome <key>] [--check <key>]` to exercise only existing active Check identities with unchanged runner/verifier authority; safe monotonic strengthening may coexist. Candidate diagnostics are transient: they authorize no acceptance and write no pending/approval state, Active Authority, cache, Progress or Receipt. Semantic changes, proof weakening, runner or verifier-content changes, and risk-increase candidates are preview-only and must not run; risk downgrade is rejected. When the candidate is complete, run ordinary `compile --revise` once, present its exact material decision summary to the user, and never approve it yourself. Keep the previous Authority active until exact approval and atomic adoption. Adoption is not delivery completion: discard historical/candidate evidence, run `status` or `resume`, and return to rolling implementation or repair under the revised Authority before Final Gate.
-
-## Live Final Authority
-
-Complete Context, implementation and project tests, create a clean candidate commit, then run `ty-context long-task final-gate <workdir>`.
-
-Final Gate recompiles Source authority, validates active task/revision/compiled/worktree identity, creates one Git-tree snapshot, reruns every required Global and Outcome Check and rechecks active identity before acceptance. A target-runtime Check must exercise its target in that current Gate execution; rerunning a reader for a historical or tracked status report is not live target proof. Final Gate, Stop and close never trust historical Progress, Receipt or compiled cache.
-
-Machine acceptance covers only declared machine authority. Preserve every pending external confirmation through `final-gate`, `status`, `resume`, `stop-check`, the package-owned Stop Hook and `close`; accepted output identifies `acceptance_scope: declared_machine_authority` and `native_goal_effect: none`, while `closed_scope: machine_authority` means only Authority cleanup. Do not invent external-confirmation or native-Goal tracking state.
-
-Before invoking platform-native Goal completion, perform one veto-only conformance review: compare the current Goal and user instructions with accepted marked Source, and check for pending revisions, unresolved blockers or omitted requirements. Any mismatch keeps the Goal active and returns to Source/Contract repair. A clean review does not add acceptance proof and never lets Agent judgment replace Final Gate.
-
-## Handoff
-
-Report implementation, effective risk, Claim Coverage, Live Gate result, acceptance scope, every pending external confirmation, Context status and blockers. Use verifier terms exactly: `progress_passing` means targeted repair evidence, `progress_stale` is not a current pass, `final_workflow_status: null` means unfinished, `authority_revision_adopted` means return to rolling execution, and `machine_accepted_external_pending` must retain its named confirmations. Never shorten implementation or targeted progress to “Outcome complete” or invent `implementation_complete`, `platform_smoke_verified` or another persistent status. State the threat-model limits: undeclared requirements cannot be discovered, installed verifier/Git metadata are trusted, native-Goal/model selection belongs to the host/user, and internal platform delegation is not observed.
+   - For material production UI, read the Contract-authoring visual guidance before Compile. Inspect any external design resources as ordinary Source, including selection basis, stable identity and declared surface/viewport/mode/state coverage. An unconfigured starter, candidate, style-only rule or inspiration-only reference is incomplete design authority unless Source explicitly scopes the result as prototype/non-fidelity or supplies a selected target before implementation.
+2. If a valid active binding exists, run `ty-context long-task resume <workdir>` and read the lifecycle reference.
+3. Otherwise author one complete Delivery Contract for the whole selected delivery. Declare the target profile, its non-empty required product target refs, each target's runtime family/root entrypoint, ordered Stages and vertical Outcomes. Do not create a second Contract plan, matrix or top-level Contract split.
+4. Preserve at least one real `source_path`. Wrap every material Source item in its original Markdown with non-rendering `ty-source-item:start/end` markers without rewriting the text; marked Source Item keys and `source_claim` keys are exactly equal.
+5. An ordinary prose plan, optional Source Plan or externally authored design resource remains valid Source after marker-only enumeration and does not need to match a recommended authoring structure. Preserve stable semantic keys and Markdown anchors where practical. External design authoring neither updates Context nor creates Contract authority by itself; candidate resources authorize no fidelity Claim.
+6. Continue reading repository, Source and Context and revise the same Draft. A request to synthesize, refine, complete, implement or use judgment delegates plan-level authoring, but it does not invent the user's tradeoff priorities. Before comparative research or a material product, technical, architecture or provider selection, identify the criteria that could change the research scope, candidate set or recommendation. Infer them only from the user's words, Source, Context or controlling constraints. If quality versus cost, speed, reliability, privacy, lock-in, operational burden or another material priority is unknown or ambiguous, stop before that research or selection and ask one concise targeted clarification. Do not impose a questionnaire, re-ask known preferences or interrupt minor reversible choices whose recommendation would not change.
+7. Once the material preference envelope is clear, decide what research is needed. Use current authoritative or primary evidence for external capability, pricing, quota, license, compatibility, region, security posture or support claims. When one recommendation is then defensible, record it in real Source with the authoring instruction, preference/evidence basis and exact added meaning instead of pausing for approval. Append the delegated item without rewriting the user's original text when ordinary prose is the Source. Return only when authoritative requirements conflict, the user explicitly reserves the choice, a material preference remains unknown, critical semantics have no defensible recommendation or no falsifiable acceptance standard can be formed.
+8. Contract expansion remains limited to meaning-preserving structural decomposition, evidence-backed repository binding and choices first recorded as delegated real Source. Never place a new product rule, default, threshold, recovery behavior, permission or platform/data scope only in Contract YAML. Default plan delegation authorizes meaning, not action: payment, contracting, production deployment or publication, destructive production mutation, real permission grants, sensitive-data transmission and required legal/security/human approval remain named external confirmations. Any conflicting, user-reserved, missing-preference or unsupported semantic remains `decision_required`.
+9. Give every Check an atomic Given/When scenario and journey role; give every Assertion the minimum all-of Evidence Capabilities that can actually prove its Claim. Separate required success and degradation Checks. Type every external confirmation with impacted Claim refs and target-blocking effect. Run read-only `ty-context long-task preflight <workdir>`, repair every error and `decision_required` finding in the same Draft, then formally Compile only when ready.
+10. When the first Compile returns `execution_model_checkpoint.required: true`, stop before implementation and ask the user to choose `continue_current_model` or switch models and then resume the active Long-Task. A task-specific choice already stated explicitly satisfies the checkpoint. Later revisions return `required: false` and do not repeat it.
+
+Architecture quality uses the existing authority model, not a new gate: when Source or controlling Context declares an architecture invariant, encode it as a Source-backed technical obligation/global constraint/forbidden shortcut plus owner/path/Binding boundaries and a project-owned executable Check. Functional acceptance cannot substitute when the architecture claim can fail independently. An unverifiable design preference remains task-local, durable Context or `decision_required`; it must not be promoted into false proof.
+
+## Rolling Execution
+
+After Authority Lock and the one-time execution-model checkpoint are satisfied, implement only Outcomes in the derived current Stage frontier, plus prerequisite regression repairs and current Finding repairs, in the current workspace. A later Stage cannot substitute for an unpassed earlier gate. Small implementation plans and repair hypotheses are internal execution state and cannot silently change Product, Technical or Acceptance authority.
+
+Re-evaluate `Context Delta` whenever implementation or repair discovers a durable fact. Controlling Context changes use protected revision; graph-derived, non-explicit `implementation-index` and `archive` are Supporting Context in referenced mode and may auto-revise when only navigation/background changed. Full snapshot mode treats every selected Context file as controlling.
+
+Use targeted `verify --outcome/--check` only to drive repair. Progress is repair evidence only and never acceptance authority. Keep precise findings attached to the owning Source item, Claim, Assertion, Check, Binding and owner path. Do not add another model-switch pause or coordinate parallel subagents.
+
+When the Contract declares a target-runtime Check because a proxy can pass while the target fails independently, run it at the earliest owning Outcome's first runnable boundary. Every required target is proved separately from its root; Browser evidence requires Playwright and Native/Desktop evidence requires the project binary. After accumulated changes to declared `input_paths` or Binding carriers make the result stale, rerun before dependent work grows. Coalesce related edits and use the cheapest reliable target Check; do not mandate a full environment rebuild per Outcome or per edit. This is rolling feedback through existing targeted verify, not acceptance, a trigger queue or per-target progress state.
+
+When implementation discovers a blocker or missing Contract paths, first classify the revision. Difficulty or delay alone never reclassifies machine-verifiable scope as external and never removes Source; a real scope, Product, Acceptance or machine/external boundary change must first be explicit marked Source. Proven monotonic evidence strengthening may use ordinary `compile --revise` directly. If every protected reason is only owner/expected-change/allowed-support expansion, continue editing the same `delivery-contract.yaml` and use `ty-context long-task diagnose-revision <workdir> [--outcome <key>] [--check <key>]` to exercise only existing active Check identities with unchanged runner/verifier authority; safe monotonic strengthening may coexist. Candidate diagnostics are transient: they authorize no acceptance and write no pending/approval state, Active Authority, cache, Progress or Receipt. Semantic changes, proof weakening, runner or verifier-content changes, and risk-increase candidates are preview-only and must not run; risk downgrade is rejected. When the candidate is complete, run ordinary `compile --revise` once, present its exact material decision summary to the user, and never approve it yourself. Keep the previous Authority active until exact approval and atomic adoption. Adoption is not delivery completion: discard historical/candidate evidence, run `status` or `resume`, and return to rolling implementation or repair under the revised Authority before Final Gate.
+
+## Live Final Authority
+
+Complete Context, implementation and project tests, create a clean candidate commit, then run `ty-context long-task final-gate <workdir>`.
+
+Final Gate recompiles Source authority, validates active task/revision/compiled/worktree identity, creates one Git-tree snapshot, reruns every required Global and Outcome Check and rechecks active identity before acceptance. It derives Stage results and target qualification from that run; it does not trust targeted Progress as a Stage pass. A target-runtime Check must exercise its exact target in that current Gate execution; rerunning a reader for a historical or tracked status report is not live target proof. Final Gate, Stop and close never trust historical Progress, Receipt or compiled cache.
+
+Machine acceptance covers only declared machine authority. Preserve every pending external confirmation through `final-gate`, `status`, `resume`, `stop-check`, the package-owned Stop Hook and `close`; accepted output identifies `acceptance_scope: declared_machine_authority` and `native_goal_effect: none`, while `closed_scope: machine_authority` means only Authority cleanup. Do not invent external-confirmation or native-Goal tracking state.
+
+Before invoking platform-native Goal completion, perform one veto-only conformance review: compare the current Goal and user instructions with accepted marked Source, and check for pending revisions, unresolved blockers or omitted requirements. Any mismatch keeps the Goal active and returns to Source/Contract repair. A clean review does not add acceptance proof and never lets Agent judgment replace Final Gate.
+
+## Handoff
+
+Report implementation, effective risk, Claim Coverage, Stage frontier/results, declared target profile, exact `target_state`, Live Gate result, acceptance scope, every pending external confirmation, Context status and blockers. Use verifier terms exactly: `progress_passing` means targeted repair evidence, `progress_stale` is not a current pass, `final_workflow_status: null` means unfinished, `authority_revision_adopted` means return to rolling execution, and `machine_accepted_external_pending` must retain its named confirmations. Contract target states are only `implementation_complete`, `target_profile_usable` and `production_release_ready`; terminal failure uses `not_accepted` or `blocked_external`. Never shorten targeted progress to “Outcome complete” or invent per-platform progress/status. State the threat-model limits: undeclared requirements cannot be discovered, installed verifier/Git metadata are trusted, native-Goal/model selection belongs to the host/user, and internal platform delegation is not observed.

package/assets/skills/long-task-workflow/agents/openai.yaml

@@ -1,4 +1,4 @@
-interface:
-  display_name: "Long-Task Workflow"
-  short_description: "Run one Delivery Contract in the current native Goal"
-  default_prompt: "Use /long-task-workflow to prepare, execute, resume, verify, or close one Canonical Delivery Contract in the current workspace."
+interface:
+  display_name: "Long-Task Workflow"
+  short_description: "Run one Delivery Contract in the current native Goal"
+  default_prompt: "Use /long-task-workflow to prepare, execute, resume, verify, or close one Canonical Delivery Contract in the current workspace."