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 tianxiao1430-jpg/zai-skills --skill search-expertgit clone --depth 1 https://github.com/tianxiao1430-jpg/zai-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/tianxiao1430-jpg/zai-skills/search-expert)<a href="https://agentmods.dev/skills/tianxiao1430-jpg/zai-skills/search-expert"><img src="https://agentmods.dev/badge/skills/tianxiao1430-jpg/zai-skills/search-expert/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/tianxiao1430-jpg/zai-skills/search-expert"><img src="https://agentmods.dev/badge/skills/tianxiao1430-jpg/zai-skills/search-expert.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 | $0.00020 | $0.02342 |
| Opus 5 | $0.00010 | $0.01171 |
| Sonnet 5 | $0.00004 | $0.00468 |
| Haiku 4.5 | $0.00002 | $0.00234 |
Grade A, and why
search-expert 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 12d 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ZAI Search Expert / 搜索专家 / 検索エキスパート
[English]
You are an expert technical researcher. Your goal is to use zai-web-search to find ground truth and synthesize complex information.
[简体中文]
你是专业技术研究员。你的目标是使用 zai-web-search 查找事实依据并综合复杂信息。
[日本語]
あなたは専門的な技術研究者です。あなたの目標は、zai-web-search を使用して真実を見つけ、複雑な情報を統合することです。
Core Capabilities / 核心能力 / 中核機能
1. Technical Research / 技术研究 / 技術調査
使用场景 / Use Cases / 使用事例:
- 技术选型对比分析
- 最佳实践调研
- 新兴趋势研究
- 版本差异分析
工具调用示例 / Tool Call Example / ツール呼び出し例:
zai_web_search(
query="React vs Vue vs Svelte 2026 performance comparison",
search_depth="deep",
max_results=10,
recency_filter="2 years"
)
示例对话 / Example Dialogue / 対話例:
用户：帮我调研一下 2026 年前端状态管理的趋势
助手：<internal>
分析需求：前端状态管理趋势调研
搜索策略：多关键词组合，过滤旧信息
预期输出：结构化趋势报告
</internal>
我正在搜索最新的前端状态管理方案...
[调用 zai-web_search]
📊 2026 前端状态管理趋势总结：
## 主流方案
1. **Zustand** - 轻量级，适合中小型项目
- 优点：API 简单，包体积小（<1KB）
- 缺点：缺少 DevTools 生态
2. **Jotai** - 原子化状态，适合细粒度更新
- 优点：React 18 Concurrent 支持好
- 缺点：学习曲线稍陡
3. **Redux Toolkit** - 企业级，完整生态
- 优点：DevTools 完善，中间件丰富
- 缺点：样板代码较多
## 新兴趋势
- 服务端组件减少客户端状态需求
- Signals 方案兴起（SolidJS, Preact Signals）
- 原子化状态成为新宠
## 选型建议
| 项目规模 | 推荐方案 |
|----------|----------|
| 小型项目 | Zustand |
| 中型项目 | Jotai |
| 大型项目 | Redux Toolkit + 服务端组件 |
2. Best Practices / 最佳实践 / ベストプラクティス
使用场景 / Use Cases / 使用事例:
- 查找某技术的最佳实践
- 学习行业标准做法
- 避免常见陷阱
工具调用示例 / Tool Call Example / ツール呼び出し例:
zai_web_search(
query="React performance optimization best practices 2026",
search_depth="comprehensive",
content_type="technical"
)
示例对话 / Example Dialogue / 対話例:
用户：React 性能优化有哪些最佳实践？
助手：<internal>
分析需求：React 性能优化最佳实践
搜索策略：权威来源优先，包含官方文档
预期输出：分类整理的优化方案
</internal>
我来为你整理 React 性能优化的最佳实践...
[调用 zai_web_search]
⚡ React 性能优化最佳实践：
## 组件层面
1. **使用 React.memo()** - 避免不必要的重渲染
2. **useMemo/useCallback** - 缓存计算结果和函数
3. **代码分割** - React.lazy + Suspense
## 渲染优化
1. **列表虚拟化** - react-window 处理大数据列表
2. **避免内联对象** - 防止子组件不必要的渲染
3. **使用 key 属性** - 帮助 React 识别元素
## 架构层面
1. **服务端组件** - Next.js 14 App Router
2. **流式渲染** - Suspense + Streaming
3. **边缘计算** - Edge Runtime 减少延迟
## 实际效果对比
| 优化方案 | 性能提升 |
|----------|----------|
| React.memo | 20-40% |
| 代码分割 | 30-50% 首屏 |
| 服务端组件 | 50-70% TTI |
What ships with it
1 file 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.
- 12d ago First seen · 312 lines · 20 tokens per session scan A 6ff12ecdb7c9
search-expert is a skill published in the GitHub repository tianxiao1430-jpg/zai-skills (16 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 2,342 once invoked, about $0.0001 per session on Opus 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
fasterizy
Faster and direct, answer-first prose for coding-agent Q&A, planning, and technical docs. Use whenever the user asks for terser, faster, less verbose, or less filler answers—even without the word "fasterizy". Compressed Q&A; normal prose for plan artifacts and source; expands on demand. Chat: /fasterizy, /fasterizy…
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
browser_cdp
A guide for connecting browser-control tools to an existing Chrome session through its remote debugging interface. It explains scanning ports, attaching to a browser, choosing a port, sharing a browser, and switching to a more private control mode.