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 OPPO-Mente-Lab/X-OmniClaw --skill taobao-searchgit clone --depth 1 https://github.com/OPPO-Mente-Lab/X-OmniClawWrote 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/oppo-mente-lab/x-omniclaw/taobao-search)<a href="https://agentmods.dev/skills/oppo-mente-lab/x-omniclaw/taobao-search"><img src="https://agentmods.dev/badge/skills/oppo-mente-lab/x-omniclaw/taobao-search/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/oppo-mente-lab/x-omniclaw/taobao-search"><img src="https://agentmods.dev/badge/skills/oppo-mente-lab/x-omniclaw/taobao-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.02867 |
| Opus 5.5 | $0.00014 | $0.01147 |
| Sonnet 5.5 | $0.00007 | $0.00573 |
| Haiku 4.5 | $0.00003 | $0.00287 |
Grade A, and why
taobao-search 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 2mo ago.
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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taobao Search Tool
通过淘宝 Deep Link 直达搜索页面,浏览商品并为用户提供购物建议。
🎯 When to Use
Use this skill when user asks about:
✅ 商品搜索 - "帮我找阿迪达斯今年新款男鞋" ✅ 品牌查找 - "搜一下耐克跑步鞋" ✅ 比价购物 - "淘宝上看看有什么好的蓝牙耳机" ✅ 新品浏览 - "今年有什么新款连衣裙" ✅ 特定条件搜索 - "200元以内的双肩包"
📋 Workflow
标准搜索流程
1. 解析用户意图,提取搜索关键词
2. 通过 device(action="open", uri="taobao://...") 跳转淘宝搜索页
3. 等待淘宝 App 加载搜索结果:device(action="act", kind="wait", timeMs=1500)
4. 拉取页面 UI 树:device(action="snapshot", format="compact")
—— 这是商品名/价格/店铺/销量等文字信息的**唯一来源**
5. 从 snapshot 返回的 text 节点里逐条提取商品信息(详见 Step 3)
6. 基于提取到的具体商品信息回答用户(200字以内,必须包含真实数字和细节)
⚠️ 绝对禁止: 不要用
read_file读截图 PNG(如read_file("/sdcard/.xomniclaw/workspace/screenshots/*.png"))。PNG 是二进制,read_file 会以 UTF-8 解码出大量乱码并撑爆上下文窗口,整个 session 会被context window exceeds limit终止。只用device(action="snapshot")读页面文字。
🔗 Deep Link 构造规则
淘宝搜索 Deep Link 格式:
taobao://s.taobao.com/search?q={关键词}
关键词用 + 连接多个搜索词,示例:
| 用户意图 | 搜索关键词 | Deep Link |
|---|---|---|
| 阿迪达斯今年新款男鞋 | 阿迪达斯+2026+新款+男鞋 | taobao://s.taobao.com/search?q=阿迪达斯+2026+新款+男鞋 |
| 耐克跑步鞋 | 耐克+跑步鞋 | taobao://s.taobao.com/search?q=耐克+跑步鞋 |
| 200元蓝牙耳机 | 蓝牙耳机 | taobao://s.taobao.com/search?q=蓝牙耳机 |
🚀 X-OmniClaw Implementation
Tool: device (DeviceTool — 统一设备控制工具)
⚠️ 重要: 不要使用 shell am start 命令跳转 Deep Link(会因 SecurityException 权限拒绝),必须使用 device(action="open", uri="...") 通过 X-OmniClaw 应用上下文发起 ACTION_VIEW Intent。
Step 1: Deep Link 跳转淘宝搜索页
// 构造搜索关键词
val keyword = "阿迪达斯+2026+新款+男鞋"
val deepLink = "taobao://s.taobao.com/search?q=$keyword"
// 通过 device tool 的 open action + uri 参数跳转
device(action = "open", uri = deepLink)
Step 2: 等待页面加载并拉取 UI 树
// 等待淘宝 App 启动并加载搜索结果
device(action = "act", kind = "wait", timeMs = 1500)
// 拉取页面 UI 树(含所有可见文本节点) —— 商品信息的唯一来源
device(action = "snapshot", format = "compact")
不要在这一步用
screenshot:screenshot只用于内部 grounding(定位点击坐标),不会把图像内容送给你。snapshot才会把页面上每个可见文本节点(含商品名、价格、店铺名)以纯文本方式返回给你。
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.
- 2mo ago First seen · 239 lines · 35 tokens per session scan A cf5c084887d7
taobao-search is a skill published in the GitHub repository OPPO-Mente-Lab/X-OmniClaw (267 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 2,867 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
ahk-consultant
Get technical advice or review on an approach, idea, or change. References available skills for best practices. No tasks created, no harness tracking.
ordercli
Foodora-only CLI for checking past orders and active order status (Deliveroo WIP).
nano-banana-pro-openrouter
Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.
skill-creator-linter
Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xmlescape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
glycoengineering
Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.