From ferris-search
Generates invocations for ferris-search MCP tools like web_search, fetch_web_content, fetch_github_readme, and domain-specific article fetchers. Explains tool usage, parameters, and troubleshooting.
npx claudepluginhub lispking/ferris-search --plugin ferris-searchThis skill uses the workspace's default tool permissions.
> **Version:** ferris-search 0.1.0 | **Last Updated:** 2026-03-31
Fetches GitHub repo documentation and code via gitmcp.io with semantic search, accurate file navigation, and LLM-optimized markdown. Use for repo analysis instead of raw URLs.
Gathers content from URLs (auto-detects Google/Slack/Notion/GitHub), web searches (Tavily/Exa), and local codebase into markdown artifacts for stable reasoning context.
Reads and searches GitHub repository documentation and code via gitmcp.io MCP service. Activates on GitHub URLs, owner/repo mentions, or queries like 'what does this repo do?' or 'search repo docs'.
Share bugs, ideas, or general feedback.
Version: ferris-search 0.1.0 | Last Updated: 2026-03-31
You are an expert at using the ferris-search MCP server tools. Help users by:
Refer to the local files for detailed documentation:
./references/tools-api.md - Complete tool parameter reference./references/engines.md - Search engine details and aliasesBefore answering questions, Claude MUST:
/sync-crate-skills ferris-search --force 更新文档"{
"tool": "web_search",
"query": "rust tokio tutorial",
"limit": 10
}
{
"tool": "web_search",
"query": "rust async runtime",
"engines": ["bing", "duckduckgo", "brave"],
"limit": 5
}
{
"tool": "web_search",
"query": "tokio async runtime stars:>1000",
"engines": ["github"],
"limit": 10
}
{
"tool": "web_search",
"query": "reqwest Client language:rust",
"engines": ["github_code"],
"limit": 10
}
{
"tool": "fetch_web_content",
"url": "https://doc.rust-lang.org/book/",
"max_chars": 50000
}
{
"tool": "fetch_github_readme",
"url": "https://github.com/tokio-rs/tokio"
}
// CSDN
{ "tool": "fetch_csdn_article", "url": "https://blog.csdn.net/..." }
// Juejin
{ "tool": "fetch_juejin_article", "url": "https://juejin.cn/post/..." }
// Zhihu
{ "tool": "fetch_zhihu_article", "url": "https://zhuanlan.zhihu.com/p/..." }
// LinuxDo
{ "tool": "fetch_linuxdo_article", "url": "https://linux.do/topic/..." }
| Tool | Required Params | Optional Params | URL Constraint |
|---|---|---|---|
web_search | query | engines, limit (1–50) | — |
fetch_web_content | url | max_chars (default 30000) | public HTTP/HTTPS |
fetch_github_readme | url | — | github.com |
fetch_csdn_article | url | — | csdn.net |
fetch_juejin_article | url | — | juejin.cn + /post/ |
fetch_zhihu_article | url | — | zhihu.com |
fetch_linuxdo_article | url | — | linux.do + /topic/ |
| Deprecated | Correct | Notes |
|---|---|---|
Passing engine as string "engines": "bing" | "engines": ["bing"] | Must be an array |
limit > 50 | limit: 50 | Clamped to max 50 |
Using fetch_web_content for CSDN/Juejin/Zhihu | Use domain-specific fetcher | Better extraction quality |
fetch_web_content when the URL matches["bing", "duckduckgo"] for global, add "baidu" for Chinese contentlimit ≤ 10 unless more results are explicitly neededmax_chars default (30000) is sufficient for most articles; increase only for very long documentsweb_search when you already have a URL"ddg", "duck duck go", "百度" all workexa engine requires EXA_API_KEY env var — warn user if they try to use it without onegithub searches repositories (name, description, stars, language); github_code searches code files (path, blob URL)GITHUB_TOKEN is optional for github/github_code — without it, GitHub rate-limits to 60 req/hr; with it, 5000 req/hr