Agent skill

Mysearch

by skernelx in skernelx/MySearch-Proxy

DEFAULT search skill for OpenClaw. An agent skill from skernelx/MySearch-Proxy.

MITAuto-check: notesProductivity & Automation

Install Mysearch

skills CLI
$ npx skills add skernelx/MySearch-Proxy --skill mysearch -a claude-code

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

GitHub CLI
$ gh skill install skernelx/MySearch-Proxy mysearch --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/skernelx/MySearch-Proxy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/openclaw .claude/skills/mysearch && 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/

Facts

Skill name
mysearch
GitHub stars
159
Token cost
~1.4k tokens
SKILL.md length
235 words
Files
12 (incl. scripts)
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

DEFAULT search skill for OpenClaw. An agent skill from skernelx/MySearch-Proxy.

  • ANY external lookup that needs current web results
  • SKILL.md covers 最小配置, OpenClaw 配置建议, MySearch-First 规则 and 严格参数规则, plus 2 more sections
  • Runs Python and Shell scripts from its folder; calls python3 and bash; reaches search.hunters.works; needs MYSEARCH_PROXY_API_KEY and MYSEARCH_TAVILY_API_KEY
  • Tasks that involve Web search

What it does

Mysearch is an agent skill from skernelx/MySearch-Proxy. DEFAULT search skill for OpenClaw. Aggregates Tavily, Firecrawl, Exa, and optional X/social search behind one search path. Use for ANY external lookup that needs current web results, docs, GitHub, changelog, pricing, URL extraction, or X discussion. Prefer this over legacy Tavily-only skill or raw websearch when MySearch is healthy.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including scripts (for example `README.md`, `README_EN.md` and `agents/openai.yaml`).

It sits in Productivity & Automation, covering Web search and Web scraping. It works with Tavily, Firecrawl, GitHub and Model Context Protocol. The repository describes itself as: Unified search MCP, proxy console, and skill for Tavily, Firecrawl, and Social / X. The licence is MIT.

When your agent uses it

  • ANY external lookup that needs current web results
  • Tasks that involve Web search
  • Tasks that involve Web scraping

Example prompts

  • “/mysearch”

Requirements

  • Python 3
  • A Bash shell
  • A credential in MYSEARCH_PROXY_API_KEY
  • A credential in MYSEARCH_TAVILY_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 52df2a0. 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 2 files in scripts/ (Python and Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • bash

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • search.hunters.works

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • MYSEARCH_PROXY_API_KEY
    • MYSEARCH_TAVILY_API_KEY
    • MYSEARCH_FIRECRAWL_API_KEY
    • MYSEARCH_XAI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mysearch loads about 1.4k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 235 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
~1.4k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:18
    copying a .env file into an installed skill folder. Only point
  • NoteMentions a .env fileSKILL.md:113
    `skills.entries.mysearch.env`,正式部署不需要依赖 `.env`。
  • NoteMentions a .env fileSKILL.md:149
    在你直接调试这个仓库工作树时,才建议复制 `.env.example` 到本地 `.env`。
  • NoteMentions a .env fileSKILL.md:156
    cp {baseDir}/.env.example {baseDir}/.env

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 skernelx/MySearch-Proxy at commit 52df2a0, republished under its MIT licence (© skernelx). 235 words, ~1,423 tokens.

Download SKILL.mdSave it as .claude/skills/mysearch/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
mysearch
description
DEFAULT search skill for OpenClaw. Aggregates Tavily, Firecrawl, Exa, and optional X/social search behind one search path. Use for ANY external lookup that needs current web results, docs, GitHub, changelog, pricing, URL extraction, or X discussion. Prefer this over legacy Tavily-only skill or raw web_search when MySearch is healthy.
version
0.1.13
author
skernelx
license
MIT
repository
https://github.com/skernelx/MySearch-Proxy
homepage
https://github.com/skernelx/MySearch-Proxy/tree/main/openclaw
security_disclosure
MySearch sends queries and whichever provider or proxy credentials you configure to the configured endpoints for Tavily, Firecrawl, Exa, and optional…

MySearch For OpenClaw

MySearch 是给 OpenClaw 用的默认搜索 skill。

如果你是 AI 助手,并且用户只是给了仓库地址或 openclaw/ 目录:

  • 先打开 openclaw/README.md
  • 先按 README 完成安装与验收
  • 再回到这个 SKILL.md 执行搜索规则和调用策略

它把 Tavily、Firecrawl、Exa、X / Social 聚合成同一个入口,并且按任务类型自动路由:

  • 最新网页、普通实时搜索:优先 Tavily
  • Tavily 结果不够时,网页发现可补 Exa
  • 文档、GitHub、pricing、changelog、PDF:优先 Firecrawl
  • X / Twitter / 社交舆情:优先 xAI 或 compatible /social/search
  • 单页正文抓取:优先 Firecrawl,失败或空正文时回退 Tavily extract

最小配置

Hub 版 skill 已经自带 runtime,不需要在安装时再下载远程代码。

推荐最小配置:

  • MYSEARCH_PROXY_BASE_URL
  • MYSEARCH_PROXY_API_KEY

这两项配好后:

  • Tavily / Firecrawl / Exa 会默认都走统一 proxy
  • 如果 proxy 同时接通了 Social / X,这一套 token 也会继续复用
  • OpenClaw 侧不需要再分别维护三套 provider token

兼容旧接法时,仍可直接填:

  • MYSEARCH_TAVILY_API_KEY
  • MYSEARCH_FIRECRAWL_API_KEY

可选增强:

  • MYSEARCH_XAI_API_KEY
  • MYSEARCH_XAI_BASE_URL
  • MYSEARCH_XAI_SOCIAL_BASE_URL
  • MYSEARCH_XAI_SEARCH_MODE=official|compatible

如果没有 X / Social 配置,MySearch 仍然可以正常完成:

  • web
  • news
  • docs
  • github
  • pdf
  • extract
  • research

只有 mode="social" 或 --include-social 才会要求 X / Social。

OpenClaw 配置建议

优先把统一 proxy 配进 OpenClaw skill env,而不是到处复制 provider key 或 shell 环境。 MYSEARCH_PROXY_BASE_URL 只应该指向你自己部署或明确可信的 proxy。 mysearch_openclaw.py 会优先读取 openclaw.json 里的 skills.entries.mysearch.env,正式部署不需要依赖 .env。

json
{
  "skills": {
    "entries": {
      "mysearch": {
        "enabled": true,
        "env": {
          "MYSEARCH_PROXY_BASE_URL": "https://search.hunters.works",
          "MYSEARCH_PROXY_API_KEY": "mysp-..."
        }
      }
    }
  }
}

如果你暂时没有统一 proxy,再退回旧接法:

json
{
  "skills": {
    "entries": {
      "mysearch": {
        "enabled": true,
        "env": {
          "MYSEARCH_TAVILY_API_KEY": "tvly-...",
          "MYSEARCH_FIRECRAWL_API_KEY": "fc-..."
        }
      }
    }
  }
}

只有在你直接调试这个仓库工作树时,才建议复制 .env.example 到本地 .env。 Hub 安装或正式 OpenClaw 部署优先用上面的 skill env 注入,不要默认把 secrets 复制进已安装的 skill 目录。

本地调试示例:

bash
cp {baseDir}/.env.example {baseDir}/.env
python3 {baseDir}/scripts/mysearch_openclaw.py health

如果要把 skill 复制到别的 OpenClaw skills 目录,再执行:

bash
bash {baseDir}/scripts/install_openclaw_skill.sh --install-to ~/.openclaw/skills/mysearch

MySearch-First 规则

只要 health 显示至少有可用搜索 provider:

  • 外部搜索任务优先走 MySearch
  • 不要把 raw web_search 当主流程
  • 不要优先走旧的 Tavily-only skill

只有这些情况才回退:

  • MySearch 还没配置最小 key
  • 用户明确要求改用别的搜索方式
  • MySearch 返回冲突结果,需要额外复核

严格参数规则

search / research 的 mode 只允许:

  • auto
  • web
  • news
  • social
  • docs
  • research
  • github
  • pdf

禁止事项:

  • 不要发明 mode="hybrid"
  • hybrid 只是某些返回结果形态,不是可传参数
  • 同时要网页和 X 时,优先:
    • --sources web,x
    • 或拆成 social + news

常用命令

健康检查
bash
python3 {baseDir}/scripts/mysearch_openclaw.py health
普通网页搜索
bash
python3 {baseDir}/scripts/mysearch_openclaw.py search \
  --query "best search MCP server" \
  --mode web
今天 X 上在热议什么
bash
python3 {baseDir}/scripts/mysearch_openclaw.py search \
  --query "today's biggest stories on X" \
  --mode social \
  --intent status

规则:

  • 先 social
  • 不要先跑 news
  • 不要先混用 raw web_search
今天 X 热议 + 网页新闻一起对照

单次:

bash
python3 {baseDir}/scripts/mysearch_openclaw.py search \
  --query "today's biggest stories on X" \
  --sources web,x \
  --intent status \
  --strategy verify

或者双次:

bash
python3 {baseDir}/scripts/mysearch_openclaw.py search --query "..." --mode social --intent status
python3 {baseDir}/scripts/mysearch_openclaw.py search --query "..." --mode news --intent status

输出时必须区分:

  • X 上在热议什么
  • 网页新闻在报道什么
文档 / GitHub / pricing / changelog
bash
python3 {baseDir}/scripts/mysearch_openclaw.py search \
  --query "OpenAI responses API pricing" \
  --mode docs \
  --intent resource
抓正文
bash
python3 {baseDir}/scripts/mysearch_openclaw.py extract \
  --url "https://example.com/post"
小型研究包
bash
python3 {baseDir}/scripts/mysearch_openclaw.py research \
  --query "best search MCP server 2026" \
  --intent exploratory \
  --include-social

输出要求

  • 优先给结论,再给来源
  • 保留 URL
  • 区分事实、引文和推断
  • 同时包含网页和 X 时,明确分区,不要混成一句模糊总结
  • max_results 默认保持小一些,先拿 3 到 5 条

© skernelx, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (scripts) in openclaw of skernelx/MySearch-Proxy.

  • SKILL.md
  • .env.example
  • README.md
  • README_EN.md
  • agents/openai.yaml
  • public.json
  • runtime/mysearch/__init__.py
  • runtime/mysearch/clients.py
  • runtime/mysearch/config.py
  • runtime/mysearch/keyring.py
  • scripts/install_openclaw_skill.sh
  • scripts/mysearch_openclaw.py

Open the folder on GitHubat commit 52df2a0

Compare with similar skills

Mysearch 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.

Mysearch compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mysearch this skillskernelx/MySearch-Proxy159—~1.4kAutomated safety check: NotesMIT
Web SearchaAAaqwq/AGI-Super-Team1051 repos~703Automated safety check: NotesMIT
Copy ResearchVKirill/claude-lane-stack122—~827Automated safety check: PassMIT
Firecrawl Developer Indexfirecrawl/skills115—~2kAutomated safety check: PassISC
Keirouter Web Fetchmydisha/keirouter147—~741Automated safety check: PassMIT
Browser SearchJohell1NS/browser-search528—~2.5kAutomated safety check: PassMIT

Similar skills

  • Web Search

    aAAaqwq/AGI-Super-Team

    网络搜索与网页内容获取。当用户需要搜索互联网信息、获取网页内容、查找实时数据、进行 websearch 时使用此技能。支持多种搜索工具:WebFetch、Firecrawl skill、Tavily skill。

    105 GitHub starsUsed in 1 repo~703 tokens
    Productivity & AutomationAuto-check: notes
  • Copy Research

    VKirill/claude-lane-stack

    Dispatch copy-lead helpers: Tavily, Codex luna/terra, grok/X, OpenCode DeepSeek, Cursor Grok 4.6 medium-fast.

    122 GitHub stars~827 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Search an index of public repositories, GitHub issues, merged pull requests, repository READMEs, and curated documentation sites.

    115 GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Keirouter Web Fetch

    mydisha/keirouter

    Fetch URL → markdown / text / HTML via KeiRouter /v1/web/fetch using Firecrawl / Jina Reader / Tavily Extract / Exa Contents.

    147 GitHub stars~741 tokensUpdated 26 days ago
    Data & AnalyticsAuto-check passed
  • Browser Search

    Johell1NS/browser-search

    Multi-engine web search (SearXNG) + browsing/scraping (Camofox, CloakBrowser).

    528 GitHub stars~2.5k tokensUpdated 1 mo 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

More from skernelx/MySearch-Proxy

  • 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
    Auto-check: notes

Questions about Mysearch

What does Mysearch do?

DEFAULT search skill for OpenClaw. An agent skill from skernelx/MySearch-Proxy. Mysearch is an agent skill from skernelx/MySearch-Proxy. DEFAULT search skill for OpenClaw.

When should I use Mysearch?

Mysearch fits situations like: ANY external lookup that needs current web results; tasks that involve Web search; tasks that involve Web scraping.

How do I install Mysearch in Claude Code?

Run `npx skills add skernelx/MySearch-Proxy --skill mysearch -a claude-code`. Or copy the skill folder (openclaw in skernelx/MySearch-Proxy) into .claude/skills/mysearch in your project. Claude Code loads it when a task matches its description.

How do I install Mysearch in Codex?

Run `npx skills add skernelx/MySearch-Proxy --skill mysearch -a codex`. Or copy the skill folder (openclaw in skernelx/MySearch-Proxy) into .agents/skills/mysearch in your project. Codex loads it when a task matches its description.

Can I use Mysearch 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 skernelx/MySearch-Proxy --skill mysearch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mysearch, .gemini/skills/mysearch, .github/skills/mysearch and .opencode/skills/mysearch in your project.

What does Mysearch need to run?

Going by SKILL.md and its folder, Mysearch needs Python and a shell for the scripts in its folder, the command-line tools its instructions call (python3 and bash) and credentials named MYSEARCH_PROXY_API_KEY, MYSEARCH_TAVILY_API_KEY, MYSEARCH_FIRECRAWL_API_KEY and MYSEARCH_XAI_API_KEY. Our summary lists: Python 3; A Bash shell; A credential in MYSEARCH_PROXY_API_KEY; A credential in MYSEARCH_TAVILY_API_KEY.

Does Mysearch access the network?

SKILL.md names 1 domain. In commands or code: search.hunters.works; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Mysearch safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. 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 Mysearch use?

Mysearch is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Mysearch use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Mysearch?

Skills that share tags, products or a category with Mysearch: Web Search (aAAaqwq/AGI-Super-Team, 105 stars), Copy Research (VKirill/claude-lane-stack, 122 stars), Firecrawl Developer Index (firecrawl/skills, 115 stars) and Keirouter Web Fetch (mydisha/keirouter, 147 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mysearch?

skernelx (a GitHub user) maintains it in skernelx/MySearch-Proxy, which has 159 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on March 23, 2026.

Source: skernelx/MySearch-Proxy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.