Agent skill

UX Walkthrough

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。

Install UX Walkthrough

skills CLI

$ npx skills add XiaoMi/hiui --skill ux-walkthrough -a claude-code

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

GitHub CLI

$ gh skill install XiaoMi/hiui ux-walkthrough --agent claude-code

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

Manual copy

$ git clone --depth 1 https://github.com/XiaoMi/hiui.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hiui-workflow/ux-walkthrough .claude/skills/ux-walkthrough && rm -rf skills-src

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

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

Paste into Claude Code

Install the "ux-walkthrough" agent skill from https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/ux-walkthrough into .claude/skills/ux-walkthrough/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ux-walkthrough", 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

$skill-installer install https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/ux-walkthrough

Type 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.

skills CLI

$ npx skills add XiaoMi/hiui --skill ux-walkthrough -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install XiaoMi/hiui ux-walkthrough --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/XiaoMi/hiui.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/hiui-workflow/ux-walkthrough .agents/skills/ux-walkthrough && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "ux-walkthrough" agent skill from https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/ux-walkthrough into .agents/skills/ux-walkthrough/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ux-walkthrough", 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.

skills CLI

$ npx skills add XiaoMi/hiui --skill ux-walkthrough -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install XiaoMi/hiui ux-walkthrough --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/XiaoMi/hiui.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/hiui-workflow/ux-walkthrough .cursor/skills/ux-walkthrough && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "ux-walkthrough" agent skill from https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/ux-walkthrough into .cursor/skills/ux-walkthrough/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ux-walkthrough", 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

$ gemini skills install https://github.com/XiaoMi/hiui.git --path skills/hiui-workflow/ux-walkthrough

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add XiaoMi/hiui --skill ux-walkthrough -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install XiaoMi/hiui ux-walkthrough --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/XiaoMi/hiui.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/hiui-workflow/ux-walkthrough .gemini/skills/ux-walkthrough && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "ux-walkthrough" agent skill from https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/ux-walkthrough into .gemini/skills/ux-walkthrough/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ux-walkthrough", 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.

GitHub CLI

$ gh skill install XiaoMi/hiui ux-walkthrough

Installs 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).

skills CLI

$ npx skills add XiaoMi/hiui --skill ux-walkthrough -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/XiaoMi/hiui.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/hiui-workflow/ux-walkthrough .github/skills/ux-walkthrough && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "ux-walkthrough" agent skill from https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/ux-walkthrough into .github/skills/ux-walkthrough/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ux-walkthrough", 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.

skills CLI

$ npx skills add XiaoMi/hiui --skill ux-walkthrough -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install XiaoMi/hiui ux-walkthrough --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/XiaoMi/hiui.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/hiui-workflow/ux-walkthrough .opencode/skills/ux-walkthrough && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "ux-walkthrough" agent skill from https://github.com/XiaoMi/hiui/tree/master/skills/hiui-workflow/ux-walkthrough into .opencode/skills/ux-walkthrough/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ux-walkthrough", 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.

Facts

Skill name: ux-walkthrough
GitHub stars: 877
Token cost: ~1.3k tokens
SKILL.md length: 351 words
Files: 56 (incl. scripts, references)
Skills in repo: 5
Repo updated: Jul 24, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 2 steps: 若 A 返回 try_url_walkthrough 或启动 dev 后拿到本地… → 若 dev 启动失败或 A 返回…
Tasks that involve Word documents
SKILL.md covers 路径约定, 角色与标准, 交付边界 and 输入 → 模式, plus 6 more sections
Calls python3

What it does

UX Walkthrough is an agent skill from 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。

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 60 other files, including scripts and reference files (for example `README.md`, `agents/openai.yaml` and `docs/onboarding/execution-sop.md`).

It sits in Frontend & Design, covering Word documents, UX design and Design systems. It works with Microsoft Word. 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.

When your agent uses it

Tasks that involve Word documents
Tasks that involve UX design
Tasks that involve Design systems

Example prompts

“/ux-walkthrough”

Requirements

Python 3

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

若 A 返回 try_url_walkthrough 或启动 dev 后拿到本地 URL → 切换 url 模式：浏览器截图 + 标注图，report.json 的 source=url
若 dev 启动失败或 A 返回 fallback_code_walkthrough → source=code，附录注明「未启动项目，结论基于代码推断」；只强报 code 可确定的体验问题

What it can do on your machine

Read from SKILL.md and the folder at commit f056c80. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
- python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

UX Walkthrough loads about 1.3k tokens when it runs, and up to ~33k if it reads all its reference files. Until then it costs about 27 tokens; SKILL.md has 351 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~27
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~33k

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

Safety

Auto-check passed

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

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

SKILL.md

The full file from XiaoMi/hiui at commit f056c80, republished under its MIT licence (© XiaoMi). 351 words, ~1,308 tokens.

Download SKILL.mdSave it as .claude/skills/ux-walkthrough/SKILL.md (or your agent's skills folder). This skill also uses 55 other files; get the full folder from GitHub.

name: ux-walkthrough
description: 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。
version: 1.0.2

UX Walkthrough

对产品进行系统性体验走查，输出结构化报告与生成本地 .docx。

路径约定

<SKILL_ROOT> = 本 skill 目录的绝对路径。

bash

python3 <SKILL_ROOT>/scripts/<脚本>.py ...

角色与标准

角色：资深 B 端体验设计专家；给可执行建议，不是主观吐槽
主标准：references/ux-checklist.md（UX 体验规则）
HiUI 典型页：references/hiui-template-baseline.md（Delta 走查；模板库全部典型页型，见该文页型索引）
辅助：Nielsen、WCAG、品牌规范；冲突时以效率、理解成本、错误恢复、专业感为准
优先级：以 references/severity-rubric.md 为准，不用 checklist 预设 P 级代替

交付边界

本 skill 的正式完成面只包括：完整 Markdown 报告、结构化 report.json、标注校验和本地 .docx
本 public skill 不定义 usage stats、telemetry closeout、网络补传或授权重试 after-hook
若上游 workflow 需要统计或发布态补传，必须由页面生成 / 发布 skill 自己定义和承担，不得默认追加到本 skill
生成 .docx 依赖 Python 包 python-docx；若环境缺失，该任务只能报告 docx_generation 失败，不能宣称完整完成

输入 → 模式

输入	模式	文档
本地项目目录	`code`	`references/mode.md#code`
`http(s)` URL	`url`	`references/mode.md#url`
图片	`screenshot`	`references/mode.md#screenshot`

无法判断时，只问一句最小必要澄清。

三阶段主流程

A 前置检查 → B 走查与报告 → C 生 docx 与完成自检

阶段 A：前置检查

bash

python3 <SKILL_ROOT>/scripts/precheck_walkthrough.py <输入> --json

只读 next_action、mode、status、gate；code 模式额外读 runtime_probe
continue_walkthrough → 进入 B；否则补证据 / 澄清 / 失败说明，不写完整报告
code 输入且 gate 通过后，next_action 可能被 runtime 探测改写：
- try_url_walkthrough → 对 runtime_probe.reachable_urls[0] 再跑 URL precheck，阶段 B 按 url 走
- start_dev_server_then_url_walkthrough → 先启动 runtime_probe.suggested_dev_command；成功则 URL precheck，失败则收窄 code
- fallback_code_walkthrough → 阶段 B 按 code 走，但须遵守体验边界（见 mode-code.md § 体验边界）

阶段 B：走查与报告

code 运行时优先（混合走查）：

若 A 返回 try_url_walkthrough 或启动 dev 后拿到本地 URL → 切换 url 模式：浏览器截图 + 标注图，report.json 的 source=url
若 dev 启动失败或 A 返回 fallback_code_walkthrough → source=code，附录注明「未启动项目，结论基于代码推断」；只强报 code 可确定的体验问题

顺序（不可变）：

HiUI 前置（若适用）：识别页型 → 读 references/hiui-template-baseline.md 对应节（页型索引列全量页型）
分批逐项走查：按 references/walkthrough-worksheet.md 的 Batch 1→4 顺序，逐条对照 references/ux-checklist.md 判断；每批填完工作表再进下一批
命中条目且需参考时，读该条 related_examples 指向的锚点（禁止通读 issue-examples/*.md 全文）；HiUI 页先问是否与 baseline 合规默认一致
references/ignore-list.md（含 §5 HiUI）→ 去掉误报
references/severity-rubric.md → 定 P0/P1/P2

输出： 对话中完整 Markdown 报告（references/report-template.md）

整理 report.json 前，必须为 全部 17 条 填写 checklist_coverage（见 report-json.md）：

pass 必须写 pass: <验证证据，>=8 字>，禁止裸 pass
issue / pending:... / n/a:... 规则见 report-json.md
禁止在交付报告中输出「HiUI 模板对齐」模块（HiUI Delta 仅走查阶段内部使用；issue 描述可保留 [HiUI-偏离] / [业务域] 标签）
标题格式：序号. [P级]标题
URL/截图模式：确定 issue 须有标注图与 images[].bbox
证据不足 → 标「待确认 / 待交互验证」，不写确定问题；仍不足则回到阶段 A，不硬写完整报告

Show full SKILL.md (130 more words)Show less

阶段 C：生 docx 与完成自检

标注（screenshot / url 必做）：禁止手估 --box；须用 annotate_issue.py（或 locate_in_screenshot.py + preview_bbox.py + annotate.py），输出到 output/annotations/*-annotated.png（流程见 annotation-style.md § 标注流程）
按 references/report-json.md 整理 report.json；URL/截图模式的 issues[].images[] 须指向标注版、设 "annotated": true，并记录 "bbox": [x,y,w,h]
校验 checklist 覆盖门禁：

bash

python3 <SKILL_ROOT>/scripts/validate_checklist_coverage.py --report-json <report.json> --json

校验标注门禁：

bash

python3 <SKILL_ROOT>/scripts/validate_report_annotations.py --report-json <report.json> --json

执行：

bash

python3 <SKILL_ROOT>/scripts/generate_docx.py \
  --report-json <report.json> \
  --output <SKILL_ROOT>/output/<项目名>-ux-report-<YYYYMMDD>.docx \
  --json

命名、嵌图与交付边界：references/report-json.md § DOCX
screenshot / url：generate_docx.py 默认校验 checklist 覆盖与标注；未通过则不得 success 完成判断
标注图：references/annotation-style.md（先 § 标注流程，再 § 样式）；推荐工具：annotate_issue.py
失败 → 说明卡住位置和直接原因，不能说已完整完成

完成定义（缺一不可）

A：precheck 已通过，或已明确说明无法继续的原因
B：对话中已输出完整报告（非摘要）
C：success 路径 docx 已 generated；失败路径已说明失败阶段和原因

已分析 / 已出报告 / 已生 json 均不等于完成，docx 未生成不算完整完成。

分阶段读文档

阶段	必读	按需
A	`mode.md` 对应锚点	`gates.md` § 阶段 A
B	walkthrough-worksheet, hiui-template-baseline（HiUI 时）, checklist, ignore-list, severity-rubric	—
C	report-template, report-json, annotation-style	`annotate_issue.py`, `validate_checklist_coverage.py`, `validate_report_annotations.py`

默认不读： 底层脚本源码及与单次走查无关的维护说明

底层脚本（仅单层调试）

bash

python3 <SKILL_ROOT>/scripts/detect_input_mode.py <输入> --json
python3 <SKILL_ROOT>/scripts/probe_dev_server.py <项目路径> --json
python3 <SKILL_ROOT>/scripts/check_evidence_gate.py --source <mode> ... --json

交付前自检

报告完整，非摘要
每问题有：位置、描述、改进建议
标题：序号. [P级]标题
已按 walkthrough-worksheet Batch 1→4 逐项检查
checklist_coverage 17 条均已填写，且 pass 均含 >=8 字验证证据
validate_checklist_coverage.py 已通过
URL/截图：每问题有标注图，且 images[].bbox 已记录
validate_report_annotations.py 已通过
docx 已生成，或已说明失败原因
末尾附 docx 绝对路径（success 时）

附录

门禁与完成判断：docs/onboarding/gates.md
检查清单：references/ux-checklist.md
分批工作表：references/walkthrough-worksheet.md
报告模板：references/report-template.md
标注规范：references/annotation-style.md

Files

SKILL.md and 55 other files (scripts, references) in skills/hiui-workflow/ux-walkthrough of XiaoMi/hiui.

SKILL.md
.gitignore
README.md
agents/openai.yaml
docs/onboarding/execution-sop.md
docs/onboarding/gates.md
references/annotation-style.md
references/changelog.md
references/hiui-template-baseline.md
references/ignore-list.md
references/issue-examples/flow.md
references/issue-examples/interaction.md
references/issue-examples/visual.md
references/mode-code.md
references/mode-screenshot.md
references/mode-url.md
… and 40 more

Open the folder on GitHubat commit f056c80

Compare with similar skills

UX Walkthrough 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.

UX Walkthrough compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
UX Walkthrough this skillXiaoMi/hiui	877	—	~1.3k	Automated safety check: Pass	MIT	2 mo ago
Impeccablebestofjs/bestofjs	3.1k	27 repos	~2.6k	Automated safety check: Pass	MIT	4 days ago
Color Auditrome-os/rome	725	—	~2.7k	Automated safety check: Pass	MIT	today
Edit Figma Designwarpdotdev/warp	65k	1 repos	~2.4k	Automated safety check: Pass	AGPL-3.0	today
Super UI UX Designsyahiidkamil/Software-Engineer-AI-Agent-Atlas	401	—	~9k	Automated safety check: Pass	None	3 mo ago
Intentghaida/intent	206	—	~11k	Automated safety check: Pass	CC0-1.0	2 mo ago

Similar skills

Impeccable
bestofjs/bestofjs
A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…
3.1k GitHub starsUsed in 27 repos~2.6k tokens
Frontend & DesignAuto-check passed
Color Audit
rome-os/rome
Audit a design system's color palette against measurable color-science disciplines — WCAG/APCA contrast of declared token pairs, perceptual (OKLCH) ramp uniformity, color-blindness safety of…
725 GitHub stars~2.7k tokensUpdated today
Frontend & DesignAuto-check passed
Edit Figma Design
warpdotdev/warp
Creates or revises Figma designs from a written description using the Figma MCP authoring tools, in a new blank file or an existing one.
65k GitHub starsUsed in 1 repo~2.4k tokens
Frontend & DesignAuto-check passed
Super UI UX Design
syahiidkamil/Software-Engineer-AI-Agent-Atlas
Complete UI/UX design capability — a wiki-style knowledge map of design theory (UX laws, Nielsen heuristics, usability, visual hierarchy, typography, contrast/WCAG, design systems…
401 GitHub stars~9k tokensUpdated 3 mo ago
Frontend & DesignAuto-check passed
Intent
ghaida/intent
The entry point for Intent, a UX and design strategy system.
206 GitHub stars~11k tokensUpdated 2 mo ago
Frontend & DesignAuto-check passed
Penpot Uiux Design
github/awesome-copilot
Official
Comprehensive guide for creating professional UI/UX designs in Penpot using MCP tools.
40k GitHub starsUsed in 1 repo~3k tokens
Frontend & DesignAuto-check passed

Questions about UX Walkthrough

What does UX Walkthrough do?

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。. UX Walkthrough is an agent skill from XiaoMi/hiui.

When should I use UX Walkthrough?

UX Walkthrough fits situations like: tasks that involve Word documents; tasks that involve UX design; tasks that involve Design systems.

How do I install UX Walkthrough in Claude Code?

Run `npx skills add XiaoMi/hiui --skill ux-walkthrough -a claude-code`. Or copy the skill folder (skills/hiui-workflow/ux-walkthrough in XiaoMi/hiui) into .claude/skills/ux-walkthrough in your project. Claude Code loads it when a task matches its description.

How do I install UX Walkthrough in Codex?

Run `npx skills add XiaoMi/hiui --skill ux-walkthrough -a codex`. Or copy the skill folder (skills/hiui-workflow/ux-walkthrough in XiaoMi/hiui) into .agents/skills/ux-walkthrough in your project. Codex loads it when a task matches its description.

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

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

What does UX Walkthrough need to run?

Going by SKILL.md and its folder, UX Walkthrough needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does UX Walkthrough access the network?

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

Is UX Walkthrough safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does UX Walkthrough use?

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

How many tokens does UX Walkthrough use?

About 1.3k tokens (SKILL.md is roughly 5.2k 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 31k tokens, read only when the agent opens those files.

What are the alternatives to UX Walkthrough?

Skills that share tags, products or a category with UX Walkthrough: Impeccable (bestofjs/bestofjs, 3.1k stars), Color Audit (rome-os/rome, 725 stars), Edit Figma Design (warpdotdev/warp, 65k stars) and Super UI UX Design (syahiidkamil/Software-Engineer-AI-Agent-Atlas, 401 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains UX Walkthrough?

XiaoMi (a GitHub organization) maintains it in XiaoMi/hiui, which has 877 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.

Install UX Walkthrough

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

UX Walkthrough

路径约定

角色与标准

交付边界

输入 → 模式

三阶段主流程

阶段 A：前置检查

阶段 B：走查与报告

阶段 C：生 docx 与完成自检

完成定义（缺一不可）

分阶段读文档

底层脚本（仅单层调试）

交付前自检

附录

Files

Compare with similar skills

Similar skills

More from XiaoMi/hiui

Related

Questions about UX Walkthrough