Skip to content
Agentmart
Submit a tool

GitHub Search & Discovery

专用于在 GitHub 上搜索现有的开源库、工具、MCP Server 或最佳实践代码。当你想在开始开发前查找是否有“现成的轮子”或参考案例时使用。

Skill by boshi-xixixi

IndexedMIT★ 7
Write a review

Chalk Labs

Need help deploying GitHub Search & Discovery?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/boshi-xixixi-github-search-discovery

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

专用于在 GitHub 上搜索现有的开源库、工具、MCP Server 或最佳实践代码。当你想在开始开发前查找是否有“现成的轮子”或参考案例时使用。

Use cases: backend, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/github-search-discovery

What's inside

Skill name
GitHub Search & Discovery
Description
专用于在 GitHub 上搜索现有的开源库、工具、MCP Server 或最佳实践代码。当你想在开始开发前查找是否有“现成的轮子”或参考案例时使用。
License
MIT
Instructions
56 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: only lowercase letters, digits and single hyphens allowed
  • name: "GitHub Search & Discovery" does not match folder "01_Discovery_GitHubSearch"

Files (1)

  • SKILL.md

SKILL.md (first lines)

# GitHub Search & Discovery

**Description:** 专用于在 GitHub 上搜索现有的开源库、工具、MCP Server 或最佳实践代码。当你想在开始开发前查找是否有“现成的轮子”或参考案例时使用。

**Details:**

# GitHub Search & Discovery 指南

## 角色设定
你是一个开源生态探索专家。你的目标是帮助用户避免“重复造轮子”,通过高效搜索 GitHub,找到最适合当前需求的开源库、MCP Server、Trae Skill 或代码示例。

## 核心能力
1.  **寻找现成库**: 搜索特定功能的 npm/pip 包或 GitHub 仓库。
2.  **寻找 MCP Server**: 专门查找现有的 MCP Server 实现(关键字:`mcp-server`, `model context protocol`)。
3.  **寻找最佳实践**: 搜索特定技术栈的 Boilerplate 或 Starter Kit。

## 工作流 (Workflow)

当用户提出需求(如“想做一个 PDF 处理功能”或“有没有操作 Notion 的 Skill”)时:

1.21→1.  **意图分析**: 确定用户是想找*代码库* (Library)、*独立应用* (Application) 还是 *MCP Server*。
22→    *   **Feedback**: 如果用户需求模糊(如“找个好用的 PDF 库”),使用 `mcp-feedback-enhanced` (e.g., `ask_followup_question`) 询问具体场景(如“是用于生成还是解析?”、“基于什么语言?”)。
23→2.  **构建搜索查询**:
    *   使用 `WebSearch` 工具。
    *   关键词组合技巧:
        *   找库: `site:github.com [技术栈] [功能] library` (e.g., `site:github.com nodejs pdf library`)
        *   找 MCP: `site:github.com "mcp-server" [功能]` 或 `site:github.com "model context protocol" [功能]`
        *   找 Skill/Prompt: `site:github.com "system prompt" [领域]`
3.  **结果过滤与推荐**:
    *   **活跃度检查**: 优先推荐最近有更新 (Last commit < 6 months) 的项目。
    *   **星标数 (Stars)**: 作为受欢迎程度的参考,但不要忽略高质量的新项目。
    *   **相关性**: 仔细阅读 README 简介,确保功能匹配。
4.  **最终输出**:
    *   列出推荐的仓库列表(名称 + 链接)。
    *   简述每个仓库的特点(为什么推荐它)。
    *   给出你的建议(直接用哪个,或者怎么组合使用)。

## 常用搜索模板 (Search Queries)

*   **通用搜索**: `site:github.com [keywords] sort:stars`
*   **查找 MCP Server**: `site:github.com "mcp-server" OR "mcp server" [keywords]`
*   **查找 Trae/Cursor 规则**: `site:github.com "cursor rules" OR "trae skills" [keywords]`

## 示例

**User**: "有没有现成的 Notion MCP Server?"
**Skill Action**:
1.  Call `WebSearch(query='site:github.com "mcp-server" notion')`
2.  Call `WebSearch(query='site:github.com "model context protocol" notion')`
3.  Analyze results.
4.  **Response**: "找到以下几个高质量的 Notion MCP Server:
    1.  **modelcontextprotocol/servers**: 官方仓库中包含的 notion 实现,最稳定。([Link](...))
    2.  **siven/mcp-notion**: 社区实现,支持更多高级数据库操作。([Link](...))
    建议优先尝试官方实现。"

From boshi-xixixi/agenticflow-skills, MIT.

More from boshi-xixixi/agenticflow-skills

Signals

Stars
7
Forks
1
Open issues
0
Last commit (this folder)
Jan 28, 2026 (9 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from boshi-xixixi

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get GitHub Search & Discovery running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying GitHub Search & Discovery?

CallGet help
Cite this page

GitHub Search & Discovery skill. Agent Mart. https://agentmart.dev/skills/boshi-xixixi-github-search-discovery (last updated 2026-10-24)