Agent skill

Huge AI Search

by wangwingzero in wangwingzero/huge-ai-search

Searches the live web through Google AI Mode via Huge AI Search (MCP or CLI).

MITAuto-check passedProductivity & Automation

Install Huge AI Search

skills CLI

$ npx skills add wangwingzero/huge-ai-search --skill huge-ai-search -a claude-code

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

GitHub CLI

$ gh skill install wangwingzero/huge-ai-search huge-ai-search --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/wangwingzero/huge-ai-search.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/huge-ai-search .claude/skills/huge-ai-search && 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 "huge-ai-search" agent skill from https://github.com/wangwingzero/huge-ai-search/tree/main/skills/huge-ai-search into .claude/skills/huge-ai-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huge-ai-search", 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/wangwingzero/huge-ai-search/tree/main/skills/huge-ai-search

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 wangwingzero/huge-ai-search --skill huge-ai-search -a codex

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

GitHub CLI

$ gh skill install wangwingzero/huge-ai-search huge-ai-search --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/wangwingzero/huge-ai-search.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/huge-ai-search .agents/skills/huge-ai-search && 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 "huge-ai-search" agent skill from https://github.com/wangwingzero/huge-ai-search/tree/main/skills/huge-ai-search into .agents/skills/huge-ai-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huge-ai-search", 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 wangwingzero/huge-ai-search --skill huge-ai-search -a cursor

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

GitHub CLI

$ gh skill install wangwingzero/huge-ai-search huge-ai-search --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/wangwingzero/huge-ai-search.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/huge-ai-search .cursor/skills/huge-ai-search && 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 "huge-ai-search" agent skill from https://github.com/wangwingzero/huge-ai-search/tree/main/skills/huge-ai-search into .cursor/skills/huge-ai-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huge-ai-search", 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/wangwingzero/huge-ai-search.git --path skills/huge-ai-search

--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 wangwingzero/huge-ai-search --skill huge-ai-search -a gemini-cli

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

GitHub CLI

$ gh skill install wangwingzero/huge-ai-search huge-ai-search --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/wangwingzero/huge-ai-search.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/huge-ai-search .gemini/skills/huge-ai-search && 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 "huge-ai-search" agent skill from https://github.com/wangwingzero/huge-ai-search/tree/main/skills/huge-ai-search into .gemini/skills/huge-ai-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huge-ai-search", 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 wangwingzero/huge-ai-search huge-ai-search

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 wangwingzero/huge-ai-search --skill huge-ai-search -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/wangwingzero/huge-ai-search.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/huge-ai-search .github/skills/huge-ai-search && 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 "huge-ai-search" agent skill from https://github.com/wangwingzero/huge-ai-search/tree/main/skills/huge-ai-search into .github/skills/huge-ai-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huge-ai-search", 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 wangwingzero/huge-ai-search --skill huge-ai-search -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 wangwingzero/huge-ai-search huge-ai-search --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/wangwingzero/huge-ai-search.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/huge-ai-search .opencode/skills/huge-ai-search && 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 "huge-ai-search" agent skill from https://github.com/wangwingzero/huge-ai-search/tree/main/skills/huge-ai-search into .opencode/skills/huge-ai-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huge-ai-search", 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: huge-ai-search
GitHub stars: 144
Token cost: ~563 tokens
SKILL.md length: 148 words
Files: 2 (incl. references)
Skills in repo: 1
Repo updated: Sep 6, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Searches the live web through Google AI Mode via Huge AI Search (MCP or CLI).

Works in 3 steps: 有 MCP search 工具（名称可能是 search 或… → 没有 MCP → 运行 CLI（见下方）。先 huge-ai-search… → 两者都不可用 → 告诉用户先安装：npm i -g…
The user needs current information
SKILL.md covers 调用顺序, 提问规则, MCP 参数 and CLI（无 MCP 时）, plus 3 more sections
Calls npx, node and npm

What it does

Huge AI Search is an agent skill from wangwingzero/huge-ai-search. Searches the live web through Google AI Mode via Huge AI Search (MCP or CLI). Use when the user needs current information, official docs, bug causes, API usage, comparisons, or any uncertain fact; when asked to 搜索, 搜一下, google, web search, or follow up on a previous Huge AI search; and before implementing unfamiliar libraries.

Its SKILL.md is about 560 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/cli.md`).

It sits in Productivity & Automation, covering Web search and MCP servers. It works with Model Context Protocol. The licence is MIT.

When your agent uses it

The user needs current information
Any uncertain fact
Follow up on a previous Huge AI search
Before implementing unfamiliar libraries

Example prompts

“Use the huge-ai-search skill to search the live web through Google AI Mode via Huge AI Search (MCP or CLI)”
“/huge-ai-search”

Requirements

Node.js

Workflow steps

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

有 MCP search 工具（名称可能是 search 或 mcp_huge_ai_search_search）→ 直接调工具。
没有 MCP → 运行 CLI（见下方）。先 huge-ai-search --help 确认命令可用。
两者都不可用 → 告诉用户先安装：npm i -g huge-ai-search，并执行一次 npx -y -p huge-ai-search@latest huge-ai-search-setup。

What it can do on your machine

Read from SKILL.md and the folder at commit 20d1596. 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
Shell commands in SKILL.md call:
- npx
- node
- npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npx and npm, which can reach the network depending on how they are called.
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

Huge AI Search loads about 563 tokens when it runs, and up to ~927 if it reads all its reference files. Until then it costs about 86 tokens; SKILL.md has 148 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~86
When it runs · the whole SKILL.md, loaded when a task matches: ~563
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~927

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from wangwingzero/huge-ai-search at commit 20d1596, republished under its MIT licence (© wangwingzero). 148 words, ~563 tokens.

Download SKILL.mdSave it as .claude/skills/huge-ai-search/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: huge-ai-search
description: Searches the live web through Google AI Mode via Huge AI Search (MCP or CLI). Use when the user needs current information, official docs, bug causes, API usage, comparisons, or any uncertain fact; when asked to 搜索, 搜一下, google, web search, or follow up on a previous Huge AI search; and before implementing unfamiliar libraries.

Huge AI Search

通过 Google AI Mode 做联网搜索。先 MCP，没有 MCP 再走 CLI。不要自己写 Playwright，也不要改用无追问能力的普通搜索来替代。

调用顺序

有 MCP search 工具（名称可能是 search 或 mcp_huge_ai_search_search）→ 直接调工具。
没有 MCP → 运行 CLI（见下方）。先 huge-ai-search --help 确认命令可用。
两者都不可用 → 告诉用户先安装：npm i -g huge-ai-search，并执行一次 npx -y -p huge-ai-search@latest huge-ai-search-setup。

提问规则

用自然语言提问，不要堆关键词。
技术词条用「X 是什么 / what is X」，不要只丢一个单词。
非琐碎问题必须追问 2–3 次。初次搜索只是开门。

MCP 参数

参数	说明
`query`	自然语言问题
`language`	`zh-CN` / `en-US` / `ja-JP` / `ko-KR` / `de-DE` / `fr-FR`
`follow_up`	同一会话追问时为 `true`
`session_id`	上次结果里的 `session_id`
`image_path`	本地图片绝对路径（单图）
`create_image`	`true` 时走画图模式

CLI（无 MCP 时）

Windows PowerShell / CMD / Unix 通用：

bash

huge-ai-search search --query "问题" --language zh-CN --format json

未全局安装时：

bash

npx -y huge-ai-search search --query "问题" --language zh-CN --format json

本仓库开发中：

bash

node dist/index.js search --query "问题" --language zh-CN --format json

追问：

bash

huge-ai-search search --query "结合我的场景该怎么选？" --follow-up --session-id "<上次 session_id>" --format json

stdout 是结果；日志在 stderr。解析 JSON 时读 data.answer_markdown 和 data.session_id。
非 TTY 默认就是 JSON，不必强记 --format。
CLI 每次都是新进程。--follow-up 只能复用浏览器登录态，不能复用 MCP 那种页内对话。没有 MCP 时，把上一轮要点写进下一条 query 再搜。
完整参数：huge-ai-search help search 或 huge-ai-search schema search。字段说明见 references/cli.md。

追问流程（必须）

概况：{主题} 是什么？核心概念和常见用法？ → 记下 session_id
场景：如果我的场景是 {具体约束}，应该怎么做？（follow_up: true）
避坑：有哪些常见坑和反模式？（同一 session_id）

话题变了就开新搜索（follow_up: false），不要硬追。

输出给用户

用搜索到的结论回答，附关键来源。
不要把 session_id、debug 标记原样丢给用户；自己留下一轮追问即可。
失败且文案要求 setup / 登录 / 验证码：把命令给用户，等他们完成后重试。不要假装搜到了。

不要做

不要用网页抓取或别的搜索工具绕过本 Skill。
不要在能搜之前就对不确定的 API / 报错下结论。
用户明确说「不要搜索」时才跳过。

Files

SKILL.md and 1 other file (references) in skills/huge-ai-search of wangwingzero/huge-ai-search.

SKILL.md
references/cli.md

Open the folder on GitHubat commit 20d1596

Compare with similar skills

Huge AI Search 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.

Huge AI Search compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Huge AI Search this skillwangwingzero/huge-ai-search	144	—	~563	Automated safety check: Pass	MIT	1 mo ago
Mysearchskernelx/MySearch-Proxy	159	—	~3k	Automated safety check: Notes	None	6 mo ago
Perplexity Web MCP Bridgejacob-bd/perplexity-web-mcp	197	—	~7.6k	Automated safety check: Pass	MIT	5 days ago
Agent Searchlennney/agent-search-mcp	110	—	~1.9k	Automated safety check: Pass	Apache-2.0	18 days ago
Bright Data MCPbrightdata/skills	264	1 repos	~3.7k	Automated safety check: Pass	MIT	2 days ago
Skillredf0x1/camofox-mcp	117	—	~3.1k	Automated safety check: Pass	MIT	1 mo ago

Similar skills

Mysearch
skernelx/MySearch-Proxy
Install, verify, debug, and use MySearch MCP/Skill. An agent skill from skernelx/MySearch-Proxy.
159 GitHub stars~3k tokensUpdated 6 mo ago
Productivity & AutomationAuto-check: notes
Perplexity Web MCP Bridge
jacob-bd/perplexity-web-mcp
Searches the web and queries premium AI models through Perplexity's own web interface, tracking quota carefully across quick, Pro and Deep Research tiers.
197 GitHub stars~7.6k tokensUpdated 5 days ago
Productivity & AutomationAuto-check passed
Agent Search
lennney/agent-search-mcp
Use Agent Search MCP for free-first English and Chinese web search with compact evidence and minimal tool calls.
110 GitHub stars~1.9k tokensUpdated 18 days ago
Productivity & AutomationAuto-check passed
Bright Data MCP
brightdata/skills
Bright Data MCP handles ALL web data operations. An agent skill from brightdata/skills.
264 GitHub starsUsed in 1 repo~3.7k tokens
Productivity & AutomationAuto-check passed
Skill
redf0x1/camofox-mcp
Anti-detection browser automation MCP skill for OpenClaw agents with 47 tools for navigation, interaction, observation, extraction, downloads, profiles, sessions, and stealth web search.
117 GitHub stars~3.1k tokensUpdated 1 mo ago
Productivity & AutomationAuto-check passed
Add Tavily Tool to NanoClaw
nanocoai/nanoclaw
Registers Tavily's keyless remote MCP server, search and extract, for selected NanoClaw agent groups by pinning an mcp-remote bridge and running it through an approval-gated config step.
31k GitHub stars~1.7k tokensUpdated 3 days ago
Productivity & AutomationAuto-check passed

Works with

Model Context Protocol

Questions about Huge AI Search

What does Huge AI Search do?

Searches the live web through Google AI Mode via Huge AI Search (MCP or CLI). Huge AI Search is an agent skill from wangwingzero/huge-ai-search. Searches the live web through Google AI Mode via Huge AI Search (MCP or CLI).

When should I use Huge AI Search?

Huge AI Search fits situations like: the user needs current information; any uncertain fact; follow up on a previous Huge AI search; before implementing unfamiliar libraries.

How do I install Huge AI Search in Claude Code?

Run `npx skills add wangwingzero/huge-ai-search --skill huge-ai-search -a claude-code`. Or copy the skill folder (skills/huge-ai-search in wangwingzero/huge-ai-search) into .claude/skills/huge-ai-search in your project. Claude Code loads it when a task matches its description.

How do I install Huge AI Search in Codex?

Run `npx skills add wangwingzero/huge-ai-search --skill huge-ai-search -a codex`. Or copy the skill folder (skills/huge-ai-search in wangwingzero/huge-ai-search) into .agents/skills/huge-ai-search in your project. Codex loads it when a task matches its description.

Can I use Huge AI Search 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 wangwingzero/huge-ai-search --skill huge-ai-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/huge-ai-search, .gemini/skills/huge-ai-search, .github/skills/huge-ai-search and .opencode/skills/huge-ai-search in your project.

What does Huge AI Search need to run?

Going by SKILL.md and its folder, Huge AI Search needs the command-line tools its instructions call (npx, node and npm). Our summary lists: Node.js.

Does Huge AI Search access the network?

SKILL.md contains no URLs. Its commands use npx and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Huge AI Search 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. Review the folder before installing.

What licence does Huge AI Search use?

Huge AI Search 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 Huge AI Search use?

About 563 tokens (SKILL.md is roughly 2.3k 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 364 tokens, read only when the agent opens those files.

What are the alternatives to Huge AI Search?

Skills that share tags, products or a category with Huge AI Search: Mysearch (skernelx/MySearch-Proxy, 159 stars), Perplexity Web MCP Bridge (jacob-bd/perplexity-web-mcp, 197 stars), Agent Search (lennney/agent-search-mcp, 110 stars) and Bright Data MCP (brightdata/skills, 264 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Huge AI Search?

wangwingzero (a GitHub user) maintains it in wangwingzero/huge-ai-search, which has 144 GitHub stars. The repository was last updated on September 6, 2026.

Source: wangwingzero/huge-ai-search on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Huge AI Search

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

Huge AI Search

调用顺序

提问规则

MCP 参数

CLI（无 MCP 时）

追问流程（必须）

输出给用户

不要做

Files

Compare with similar skills

Similar skills

Mysearch

Perplexity Web MCP Bridge

Agent Search

Bright Data MCP

Skill

Add Tavily Tool to NanoClaw

Related

Questions about Huge AI Search