Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jiushiwon/wg-skills --skill mobile-safe-area-audit-skillgit clone --depth 1 https://github.com/jiushiwon/wg-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jiushiwon/wg-skills/mobile-safe-area-audit-skill)<a href="https://agentmods.dev/skills/jiushiwon/wg-skills/mobile-safe-area-audit-skill"><img src="https://agentmods.dev/badge/skills/jiushiwon/wg-skills/mobile-safe-area-audit-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jiushiwon/wg-skills/mobile-safe-area-audit-skill"><img src="https://agentmods.dev/badge/skills/jiushiwon/wg-skills/mobile-safe-area-audit-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00091 | $0.01394 |
| Opus 5.5 | $0.00036 | $0.00558 |
| Sonnet 5.5 | $0.00018 | $0.00279 |
| Haiku 4.5 | $0.00009 | $0.00139 |
Grade A, and why
mobile-safe-area-audit-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
移动端安全区与键盘审计修复
面向 uni-app、微信小程序和移动 H5 的专项审计 Skill。目标不是给每页补一段 env(),而是找出顶部、底部、固定区、键盘分别由谁负责,再收口到项目已有的容器、mixin 或 composable。
适用与边界
适用:自定义导航、微信胶囊避让、iPhone Home Indicator、底部固定按钮、聊天输入框、长表单、底部 Tab、键盘弹起后的滚动内容。
不适用:普通 PC 页面间距审查使用 frontend-style-harmonizer-skill;品牌视觉或页面重设计使用对应 UI Skill。
默认只读。只有用户确认审计报告与基线后,才允许 --apply 做视觉层最小修复;不得改接口、路由、业务事件或数据结构。
触发示例
审计这个 uni-app 项目的安全区和键盘顶起问题 D:/projects/my-miniapp
为什么 iPhone 底部按钮会挡住最后一项,帮我先只读检查
检查微信胶囊、自定义导航和 fixed 提交按钮是否统一
确认报告后,修复已确认的底部安全区实现漂移
参数
| 参数 | 说明 | 默认值 |
|---|---|---|
[path] |
项目路径 | 当前目录 |
--report-only |
仅输出证据化报告 | 是 |
--scope |
top、bottom、keyboard、fixed、all |
all |
--apply |
在用户确认基线后执行最小视觉修复 | 否 |
必须执行的审计流程
- 识别运行端与既有真源:读取项目规则、导航容器、主题样式、safe-area mixin / Token / composable;区分原生导航、自绘导航、WebView 与沉浸式页面。
- 建立责任表:按
references/audit-checklist.md记录顶部胶囊、底部安全区、固定操作区、内容预留、键盘策略分别由哪个层负责。 - 扫描实现漂移:查找
env(safe-area-inset-*)、position:fixed/sticky、keyboardHeight、adjust-position、cursor-spacing、硬编码导航高度;与项目公共封装逐项对照。 - 判定证据边界:静态扫描只能判定实现漂移或遮挡风险;键盘、刘海屏、Home Indicator 的最终显示必须标为“待真机验证”。
- 输出报告:写入
<项目>/docs/mobile-safe-area-audit.md,每项给出文件位置、责任方、静态/视觉证据、风险等级、推荐基线和验证动作。 - 可选修复:仅当用户确认后,按
references/repair-patterns.md输出并应用最小 diff;优先复用项目已有 mixin、容器或 composable,不创建第二套安全区方案。 - 验证:构建通过后,至少验证 iOS / Android(若项目支持)上的顶部、底部、键盘弹起、键盘收起、滚动到最后一项五种状态;无法验证时明确留下待办。
决策红线
- 顶部胶囊避让、安全区、键盘策略必须先找项目现有真源;不能根据单个页面猜测全局规范。
- 发现页面手写
env(),而项目已有公共 mixin / 容器时,报告为实现漂移,不能直接声称页面已坏。 - 发现 fixed/sticky 操作栏,必须反查内容区是否预留“操作栏高度 + 底部安全区”;无真机只能报告遮挡风险。
- 页面和输入组件同时处理
keyboardHeight、自动顶起或 cursor spacing 时,必须列为双重位移风险并做真机验证。 - 自绘导航、原生导航、沉浸式 Hero 可以采用不同方案,但必须作为明确 Variant 记录,不能混为一套固定高度。
--apply只改已确认的视觉层责任归属;不得碰业务逻辑、请求、状态机、路由和权限。
输出格式
## P1:底部安全区实现漂移
- 文件:`pages/order/confirm.vue:142-153`
- 静态证据:页面直接写 `env(safe-area-inset-bottom)`;项目已有 `safe-area-bottom` mixin。
- 当前责任:页面私有样式。
- 推荐基线:公共 Footer / mixin。
- 真机验证:iPhone Home Indicator、列表最后一项、键盘弹起与收起。
- 结论:实现漂移;不宣称当前页面已出现遮挡。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 82 lines · 91 tokens per session scan A bf8988291570
mobile-safe-area-audit-skill is a skill published in the GitHub repository jiushiwon/wg-skills (134 stars, last pushed yesterday), licensed Apache-2.0. It adds 91 tokens to every session and 1,394 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.
mobile-safe-area-audit-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mobile-safe-area-audit-skilljiushiwon/wg-skills | Skill | 134 | yesterday | Apache-2.0 | A | 91 | Claude Code, Codex |
| mobile-nativeemilkowalski/skills | Skill | 54k | 2d ago | MIT | A | 167 | Claude Code, Codex |
| uniwinduni-stack/uniwind | Skill | 1.7k | yesterday | MIT | A | 130 | Claude Code, Codex |
| weapp-tailwindcss-react-nativesonofmagic/weapp-tailwindcss | Skill | 1.9k | 5d ago | MIT | A | 104 | Codex |
| mobile-ux-optimizercuriositech/some_claude_skills | Skill | 263 | yesterday | MIT | A | 76 | Claude Code |
| expo-tailwind-setupopenai/plugins | Skill | 7.8k | 3d ago | none | A | 27 | Codex |
| flutter-developmenttravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 41 | Claude Code, Codex |