Creative Tim UI Blocks
creativetimofficial/ui
Helps install, generate and review Creative Tim UI blocks: shadcn/ui-based React and Tailwind sections that follow a restrained, production-minded design philosophy.
用于 React / HiUI 页面从需求细化到端到端生成与验收。适用于从模糊产品需求生成并验收页面、 HiUI 页面提测前检查、页面生成后做体验走查、页面从需求到实现再到 UX 验收闭环等任务。
$ npx skills add XiaoMi/hiui --skill hiui-page-workflow -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install XiaoMi/hiui hiui-page-workflow --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/XiaoMi/hiui.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hiui-workflow/hiui-page-workflow .claude/skills/hiui-page-workflow && rm -rf skills-srcUse ~/.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/
Install the "hiui-page-workflow" agent skill from https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/hiui-page-workflow into .claude/skills/hiui-page-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hiui-page-workflow", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/hiui-page-workflowType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add XiaoMi/hiui --skill hiui-page-workflow -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install XiaoMi/hiui hiui-page-workflow --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/XiaoMi/hiui.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/hiui-workflow/hiui-page-workflow .agents/skills/hiui-page-workflow && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "hiui-page-workflow" agent skill from https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/hiui-page-workflow into .agents/skills/hiui-page-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hiui-page-workflow", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add XiaoMi/hiui --skill hiui-page-workflow -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install XiaoMi/hiui hiui-page-workflow --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/XiaoMi/hiui.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/hiui-workflow/hiui-page-workflow .cursor/skills/hiui-page-workflow && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "hiui-page-workflow" agent skill from https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/hiui-page-workflow into .cursor/skills/hiui-page-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hiui-page-workflow", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/XiaoMi/hiui.git --path skills/hiui-workflow/hiui-page-workflow--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add XiaoMi/hiui --skill hiui-page-workflow -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install XiaoMi/hiui hiui-page-workflow --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/XiaoMi/hiui.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/hiui-workflow/hiui-page-workflow .gemini/skills/hiui-page-workflow && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "hiui-page-workflow" agent skill from https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/hiui-page-workflow into .gemini/skills/hiui-page-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hiui-page-workflow", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install XiaoMi/hiui hiui-page-workflowInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add XiaoMi/hiui --skill hiui-page-workflow -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/XiaoMi/hiui.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/hiui-workflow/hiui-page-workflow .github/skills/hiui-page-workflow && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "hiui-page-workflow" agent skill from https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/hiui-page-workflow into .github/skills/hiui-page-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hiui-page-workflow", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add XiaoMi/hiui --skill hiui-page-workflow -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install XiaoMi/hiui hiui-page-workflow --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/XiaoMi/hiui.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/hiui-workflow/hiui-page-workflow .opencode/skills/hiui-page-workflow && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "hiui-page-workflow" agent skill from https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/hiui-page-workflow into .opencode/skills/hiui-page-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hiui-page-workflow", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
hiui-page-workflow用于 React / HiUI 页面从需求细化到端到端生成与验收。适用于从模糊产品需求生成并验收页面、 HiUI 页面提测前检查、页面生成后做体验走查、页面从需求到实现再到 UX 验收闭环等任务。
Hiui Page Workflow is an agent skill from XiaoMi/hiui. 用于 React / HiUI 页面从需求细化到端到端生成与验收。适用于从模糊产品需求生成并验收页面、 HiUI 页面提测前检查、页面生成后做体验走查、页面从需求到实现再到 UX 验收闭环等任务。 编排 hiui-refine、hiui-design 与 ux-walkthrough:用 requirementGate、 generationInputGate 和 uxGate 控制需求确认、页面生成输入确认、工程验收、UX 分级验收、 before/after 截图、修复闭环和报告输出。
Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `CHANGELOG.md`, `README.md` and `agents/openai.yaml`).
It sits in Frontend & Design, covering Design systems. It works with React. The repository describes itself as: HIUI is a solution that is adequate for the fomulation and implementation of interaction and UI design standard for front, middle and backend. The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit f056c80. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
npxFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Hiui Page Workflow loads about 3.1k tokens when it runs, and up to ~8.5k if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 963 words of instructions outside code blocks.
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.
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.
The full file from XiaoMi/hiui at commit f056c80, republished under its MIT licence (© XiaoMi). 963 words, ~3,058 tokens.
.claude/skills/hiui-page-workflow/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.你是 HiUI 页面端到端交付 agent。目标不是只生成页面,也不是只写体验报告,而是把页面从需求细化、实现、工程验收到体验验收串成闭环。
这是门禁型编排 workflow,不复制下游 skill 的详细规则,但必须控制阶段状态、输入契约和证据门禁:
hiui-refinehiui-designux-walkthrough调度边界冻结见 references/dispatch-boundary.md:本 workflow 只依赖能力标识、公开调度身份和 machine-public protocol,不依赖下游内部命名。
核心铁律:
generationInputGate 未确认或未被用户明确授权假设时,不得生成页面或修改页面源码。uxGate.evidenceStatus 未就绪时,不得输出确定性的完整 UX 报告。standard-e2e / formal-e2e 未覆盖 P0 场景时,不得只输出 P2 表面问题。generationInputGate 已通过、HiUI 交接包已就绪、hiui-design 机器计划已完成。plan.status=ready、facts.status=ready、currentExecutionState.status=ready、canStartImplementation=true;任一条件不成立时,回到 ResolveBlockingFacts,must not 继续生成页面。uxGate.evidenceStatus = ready;证据不足时必须 refuse 确定性完整结论。hiui-workflow 的分发控制面。hiui-workflow 对应脚本与文档;未加 --force-sync 时,发现本地更高版本必须 keep 并提示,must not 静默降级。hiui-workflow 的 verify 或 dry-run 验证。install-journal.json 与目标 skill 目录后,才允许执行真实安装;若任一写入失败,必须 rollback,must not 留下半安装状态。skill.manifest.json、required paths 和 public contracts 暴露稳定面,否则 refuse 建立 bundle 依赖。进入本 workflow 的典型请求:
若用户只要求需求细化、产品方案、页面清单或页面提示词,且没有页面生成 / 验收目标,可在本 workflow 的 S0 收口,并按 hiui-refine 的交付模式输出。
若用户通过本 workflow 明确要求“需求细化 -> 页面生成 -> 验收”全流程,不得停在 S0,必须继续进入 HiUI 规划、生成、工程验收和 UX 验收。
若用户只要求体验走查,优先使用 ux-walkthrough。
只有满足以下任一条件,才允许跳过完整需求细化并直接进入 hiui-design:
用户说“生成页面 / 继续 / 开始吧 / 端到端 / 一条龙”只代表任务目标,不等于授权跳过确认。
先初判 workflow level。详情见 references/acceptance-matrix.md。若 S0 产出的 HiUI 交接包包含 workflowLevelSuggestion,或需求细化后发现范围/验收要求变化,必须重新校准 workflow level。
quick-preview:生成页面并确认可运行;做 ux-smokestandard-e2e:生成 / 修改页面,跑工程 gate,做 ux-standard 结构化 UX 验收formal-e2e:提测、发布、合入、无 warning、完整 UX review;做 ux-formal 完整 ux-walkthrough若用户出现“提测 / 发布 / 合入 / 无 warning / source-gate / doctor / finalize-page / 完整体验走查 / UX review 报告”,升级为 formal-e2e。
本 workflow 使用 6 个阶段和 3 个 Gate。详细字段见 references/handoff-contract.md。
| 阶段 | 目标 | 进入下一阶段必须满足 |
|---|---|---|
| S0 需求与生成输入确认 | 细化需求,确认页面清单、页面提示词和 HiUI 交接包 | `generationInputGate.status = confirmed |
| S1 HiUI 页面规划 | 调用 hiui-design 规划页型、拓扑、命令和必读文档 | 机器计划完成,blockingReasons 为空或已处理 |
| S2 页面生成 / 修改 | 基于确认输入写页面 | S1 完成,且再次确认 generationInputGate 已通过 |
| S3 工程验收 | 记录并执行进入验证 / 交付相位的 requiredActions / formalAcceptanceActions | 动作结果已记录为 passed / failed / skipped / blocked |
| S4 UX 验收 | 按验收等级执行 ux-smoke / ux-standard / ux-formal | uxGate.evidenceStatus = ready 或明确降级 / 阻塞 |
| S5 修复与最终交付 | 修复 P0/P1,复验并输出报告 | 工程结果、UX 结果、截图和风险已收口 |
Gate 最小状态:
requirementGate.status:needs-confirmation | requirements-confirmed | assumption-authorized | blockedgenerationInputGate.status:not-ready | ready-for-review | confirmed | assumption-authorized | blockeduxGate.evidenceStatus:not-ready | ready | insufficient | blocked当输入是产品想法、粗略需求、PRD 片段、页面描述不完整,或用户明确要求“从需求到页面到验收”时,先调用 hiui-refine。
执行要求:
hiui-handofffull-prd-to-generationquick-refine 进行选项式确认requirementGate:1A,2B。requirementGate 通过后,必须执行 generationInputGate:A. 确认并生成、B. 调整 MVP / P0 场景、C. 调整页面清单 / 页面提示词、D. 保留假设,先生成一版。generationInputGate.status = confirmed。generationInputGate.status = assumption-authorized。requirementGate 和 generationInputGatehiui-refine 的规则保留“待确认”和假设,不能伪造成已确认;generationInputGate.status 必须标为 assumption-authorized。需求细化的输出作为后续 hiui-design 的输入事实。后续不得手工重造页型、页面清单或业务规则;若 hiui-design 计划与 HiUI 交接包冲突,必须说明冲突并以项目事实和计划工具结果重新收敛。
调用 hiui-design:
generationInputGate.status;只有 confirmed 或 assumption-authorized 可以继续。hiui-design 的 machine-public planner CLI 身份 plan-page-task 获取结构化 planner JSON;项目侧可以通过 npm script、task runner 或其他等价包装暴露该入口hiui-design 公布的 machine-public planner contract,就视为合法 planner 入口;workflow 不依赖具体脚本文件名、相对路径或 wrapper 名称plan-page-task machine-public 入口,fail closed:先修目标项目的 planner 接入状态;不要把 hiui-design skill 源码仓中的内部脚本路径当成 workflow contractmode、topology、pageType / pageUnits、taskLevel、startFromrequiredDocs[].readMode 消费计划文档:先读 required,reference / conditional 只按 reason 命中情况补读plan.status!=ready、facts.status!=ready、currentExecutionState.status!=ready、canStartImplementation=false,或 currentExecutionState.primaryAction=ResolveBlockingFacts,先补齐阻断事实,不直接实现首轮计划以 plan-page-task 的 JSON 为准,不手工重造页型结论。
继续按 hiui-design 执行:
requiredActions 为主;requiredCommands 只作为兼容摘要或人工复核视图targetDeliverySemantics、generationRecipe、generationInputs 与 requiredActions 为准;不要由 workflow 手工重建下游页型策略执行任何文件变更前,再次检查 generationInputGate 与 S1 机器计划;若 generationInputGate 未通过、HiUI 交接包未就绪,或 plan.status / facts.status / currentExecutionState.status 不是 ready,或 canStartImplementation!=true,必须停止并回到 S0 / S1,不得“先生成再补需求”。
不得破坏:
本阶段只承接进入验证 / 交付确认相位的动作:
requiredActions 与 formalAcceptanceActions 为主调度面requiredCommands 与 formalAcceptanceCommands 仅作为兼容摘要,不再单独定义 workflow 阶段ResolveBlockingFacts、GenerateOrEdit、WriteContract 的动作,必须在前序阶段完成;不得堆到 S3 再统一执行Preflight、工程脚本、FormalAcceptance 及其他交付前验证动作的真实结果记录每条命令的结果:
passedfailedskippedblocked失败时先判断是否阻断页面运行或交付,不要静默吞掉。
页面需要浏览器时:
若无法获得登录态,按 ux-walkthrough 的 URL 降级规则处理。
进入 UX 验收或修复前,必须先保留当前页面的可查看原图,作为 before-fix 基线证据:
before-fix、视口和页面状态knownRisks 中说明原因,不能把最终截图伪装成修复前截图把工程阶段交接给 UX 阶段的信息整理成 references/handoff-contract.md 中的结构。
| workflow level | UX 模式 | 名称 | 要求 |
|---|---|---|---|
quick-preview | ux-smoke | 轻量可用性自检 | 页面可见、主入口可见、无空白 / 错路由、最终截图留证 |
standard-e2e | ux-standard | 结构化 UX 验收 | evidence gate、P0 场景覆盖、P0/P1/P2 分级、P0/P1 修复闭环 |
formal-e2e | ux-formal | 完整 ux-walkthrough | 完整 SOP、report.json,以及当前 ux-walkthrough 版本要求的完成门禁(1.0.2 起含 checklist coverage 校验、标注校验与 docx) |
standard-e2e 不要声称已完成完整 ux-walkthrough;它是参考 ux-walkthrough 标准的结构化 UX 验收。formal-e2e 才执行完整 ux-walkthrough。
进入 UX 判断前建立 uxGate:
ux-smoke:确认目标页面不是空白页、错误页、登录页或错误路由,并保留最终截图路径。ux-standard:必须有可用证据,读取 ux-walkthrough 的 checklist、severity、ignore-list 和 issue examples;必须覆盖 P0 场景。ux-formal:按 ux-walkthrough 的 SKILL.md 主流程与 docs/onboarding/gates.md 执行完整 SOP,包括 precheck、证据门禁、report.json,以及当前 ux-walkthrough 版本要求的完成门禁(1.0.2 起含 checklist coverage 校验、标注校验与 docx 交付)。证据不足时,不输出确定性 UX 问题;只能输出“待补充证据 / 待交互验证 / 无法判断”。
ux-standard 和 ux-formal 必须先从 S0 交接包读取 P0 场景,并输出覆盖结论:
UX 报告必须先回答“P0 用户是否能完成核心任务”,再检查视觉、文案、间距、一致性和专业感。
P2 视觉、文案、一致性问题不能作为 standard-e2e / formal-e2e 的唯一输出;除非报告同时说明已覆盖 P0/P1 核心路径且未发现问题的证据依据。
所有问题必须使用格式:
1. [P1] 问题标题每个问题只写最小必要信息:
截图证据优先引用 before-fix 基线图;报告中展示可压缩缩略图,但必须同时保留可查看的原图路径。
formal-e2e 必须生成本地 .docx 报告;standard-e2e 仅在用户要求完整 UX review、可转发报告或归档报告时生成。
UX 问题处理策略:
修复体验问题时,仍必须遵守 hiui-design 的页壳、region、ownership、source marker 和 contract 约束。
修复 P0 / P1,或实际修改了 P2 后,必须使用相同路由、相同视口、尽量相同数据状态复拍 after-fix 截图,并在报告中形成 before / after 对比。若无法保持相同状态,必须说明差异来源。
修复后回到:
HiUI 修改 -> 工程 gate -> 页面截图 -> UX 复查最终回复按 references/final-report-template.md 收口,至少包含:
requirementGate 和 generationInputGate 状态uxGate、UX 验收模式和 P0 场景覆盖结果1A,2B 后,直接进入 hiui-design。正确:先展示生成输入确认块,让用户确认页面清单和页面提示词。仅对 hiui-design 页面交付链路处理 usage stats:
hiui-design 的 usage stats 规则收口ux-walkthrough 的完成定义到完整报告、report.json 与当前版本要求的完成门禁为止;1.0.2 起至少包含 checklist coverage 校验、标注校验与 docx;不额外要求 usage stats 或 telemetry closeout若 hiui-design 统计返回 requires_network_authorization 或退出码 21,按其规则申请一次授权。
统计失败不阻断主任务交付,但不能静默吞掉入队或授权状态。
hiui-page-workflow 是运行时编排层,依赖以下 skill 在环境中已可用:
hiui-refinehiui-designux-walkthrough本 skill 只负责编排和消费这些 skill 的稳定输出,不负责公开安装入口,也不承担 bundle 分发控制。
边界要求:
requirements-refinement、page-planning-and-delivery、ux-walkthrough-reviewrequirements-refinement -> hiui-refine、page-planning-and-delivery -> hiui-design、ux-walkthrough-review -> ux-walkthroughsourceSkill、dependencies 和文档中的下游名称只记录公开调度身份;不要写内部脚本名、目录名或 references 文件名hiui-design 的执行面只消费 machine-public planner 输出及其 requiredActions / formalAcceptanceActions;不要把内部脚本路径写进 workflow contracthiui-workflowhiui-page-workflow 对外表述成安装入口、bundle 入口或组合分发入口dependencies 只表达运行时依赖,不应被解释为当前 skills add 会自动安装这些 skill当用户询问如何安装本 workflow 或其依赖 skill 时,统一引导到公开安装入口:
npx skills add XiaoMi/hiui/skills/hiui-workflow --skill '*'说明要求:
hiui-workflowhiui-page-workflow 会顺带安装其他 skill”本 skill 自身的完成判断,仍以页面交付 workflow 为准:
安装、校验、回滚和发布 smoke 属于 hiui-workflow 的分发控制面,不属于本 skill 的默认完成路径。
只有当用户明确要求处理分发控制面时,才应转到入口目录对应的脚本和文档,而不是在普通页面任务中默认触发。
维护本 skill 时,始终保持以下口径:
hiui-page-workflow = 运行时工作流编排 skillhiui-workflow = 公开安装入口hiui-refine、hiui-design、ux-walkthrough = 独立下游 skill若文档、脚本说明或对外回复中再次把 hiui-page-workflow 描述成安装入口,视为职责边界回退,应修正。
© XiaoMi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 10 other files (references) in skills/hiui-workflow/hiui-page-workflow of XiaoMi/hiui.
Open the folder on GitHubat commit f056c80
Hiui Page Workflow 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Hiui Page Workflow this skillXiaoMi/hiui | 878 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Creative Tim UI Blockscreativetimofficial/ui | 12k | — | ~2.1k | Automated safety check: Notes | MIT | |
| Cosscrafter-station/petdex | 4.2k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Ss Learnbitjaru/styleseed | 974 | — | ~1.3k | Automated safety check: Pass | MIT | |
| UI/UX Design System AdvisorGalaxy-Dawn/claude-scholar | 5.7k | 1 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Design StyleCastor6/tactus | 376 | 1 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 |
creativetimofficial/ui
Helps install, generate and review Creative Tim UI blocks: shadcn/ui-based React and Tailwind sections that follow a restrained, production-minded design philosophy.
crafter-station/petdex
Helps implement coss UI components correctly. An agent skill from crafter-station/petdex.
bitjaru/styleseed
Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or…
Galaxy-Dawn/claude-scholar
Turns a vague UI request into a concrete design system with style, palette, typography and layout guidance from a search script, plus stack-specific implementation advice.
Castor6/tactus
A skill your agent uses whenever the user asks to build, create, design, develop, improve, or style any frontend interface or visual element.
lobehub/lobe-ui
Build UI with the LobeHub design ecosystem — @lobehub/ui (plus its base-ui, chat, mobile, awesome, brand, mdx, i18n namespaces), @lobehub/icons, @lobehub/charts, @lobehub/fluent-emoji and…
XiaoMi/hiui
体验走查 skill。适用于代码库、URL、截图三种输入,输出结构化体验问题报告,并同步生成本地 docx 报告。触发词:体验走查、UX review、交互走查、界面审查、体验问题。
XiaoMi/hiui
A skill your agent uses when the user's task involves HiUI (@hi-ui/) — writing HiUI components, debugging HiUI issues, querying HiUI props/docs, migrating from HiUI V4 to V5, or setting up React 19…
XiaoMi/hiui
可作为 hiui-page-workflow 等更大页面工作流的标准 S0 前置 skill,专注 B 端中后台与 HiUI 页面生成前的需求细化。将模糊或抽象的后台/管理台/运营台/配置台/审批流需求细化为可执行的产品方案、MVP 范围、用户流程、业务规则、可追踪页面清单、产品 PRD、全局生成上下文、页面级提示词和 HiUI 交接包。适用于澄清后台产品想法、把粗略需求转成 PRD…
XiaoMi/hiui
在 React 项目中接入、生成、修改、联调或验收 HiUI 典型页与非典型页面时使用。适用于 数据统计表、普通表格、树形表格、左树右表、数据可视化、异常反馈页、抽屉表单/详情、 全页编辑/详情、不规范原型截图转规范页、老旧系统截图/URL/源码现代化转译,以及 host-integration、rules-only、legacy-host-compatible 等场景。
Works with
Categories
用于 React / HiUI 页面从需求细化到端到端生成与验收。适用于从模糊产品需求生成并验收页面、 HiUI 页面提测前检查、页面生成后做体验走查、页面从需求到实现再到 UX 验收闭环等任务。. Hiui Page Workflow is an agent skill from XiaoMi/hiui.
Hiui Page Workflow fits situations like: tasks that involve Design systems.
Run `npx skills add XiaoMi/hiui --skill hiui-page-workflow -a claude-code`. Or copy the skill folder (skills/hiui-workflow/hiui-page-workflow in XiaoMi/hiui) into .claude/skills/hiui-page-workflow in your project. Claude Code loads it when a task matches its description.
Run `npx skills add XiaoMi/hiui --skill hiui-page-workflow -a codex`. Or copy the skill folder (skills/hiui-workflow/hiui-page-workflow in XiaoMi/hiui) into .agents/skills/hiui-page-workflow in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add XiaoMi/hiui --skill hiui-page-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hiui-page-workflow, .gemini/skills/hiui-page-workflow, .github/skills/hiui-page-workflow and .opencode/skills/hiui-page-workflow in your project.
Going by SKILL.md and its folder, Hiui Page Workflow needs the command-line tools its instructions call (npx).
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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.
Hiui Page Workflow is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.1k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.5k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Hiui Page Workflow: Creative Tim UI Blocks (creativetimofficial/ui, 12k stars), Coss (crafter-station/petdex, 4.2k stars), Ss Learn (bitjaru/styleseed, 974 stars) and UI/UX Design System Advisor (Galaxy-Dawn/claude-scholar, 5.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
XiaoMi (a GitHub organization) maintains it in XiaoMi/hiui, which has 878 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on July 24, 2026.
Source: XiaoMi/hiui on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.