MCPInstall

research

Comprehensive research combining web search and AI synthesis. Use for deep research on topics, comparing technologies, investigating libraries, and finding GitHub issues related to problems.

Installs
52
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/johnlindquist/claude --skill research
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads research automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Research - Deep Investigation

Thorough research combining multiple sources and AI synthesis.

Prerequisites

  • gh CLI for GitHub searches
  • gemini CLI for AI synthesis
brew install gh
pip install google-generativeai
gh auth login
export GEMINI_API_KEY=your_api_key

Research Operations

Deep Research

Comprehensive multi-angle investigation:

# Step 1: Gather information from multiple angles
TOPIC="your research topic"
OBJECTIVE="what you're trying to learn"

# Web search synthesis
gemini -m pro -o text -e "" "Research '$TOPIC' comprehensively.

OBJECTIVE: $OBJECTIVE

Provide:
1. Executive summary (3-5 bullet points)
2. Key findings with sources
3. Different perspectives and debates
4. Knowledge gaps and uncertainties
5. Actionable recommendations"

Quick Research

Fast answers for straightforward questions:

gemini -m pro -o text -e "" "Quick research: [question]

Provide:
- Direct answer
- Key facts
- Important caveats
- Actionable next step"

Technology Comparison

gemini -m pro -o text -e "" "Compare these technologies for [use case]:

CANDIDATES:
1. [Tech A]
2. [Tech B]
3. [Tech C]

CRITERIA:
- Performance
- Learning curve
- Community/ecosystem
- Maintenance burden
- Production readiness

Include real-world adoption examples and common pitfalls."

Library Investigation

# GitHub search for the library
gh search repos "[library name]" --json fullName,description,stargazersCount,updatedAt --limit 5

# Check issues
gh search issues "[library] bug" --json title,url,state --limit 10

# AI analysis
gemini -m pro -o text -e "" "Evaluate [library] for production use:

1. Maturity and stability
2. Maintenance status
3. Common issues
4. Alternatives to consider
5. Recommendation"

GitHub Issues Search

Find related issues for debugging:

# Search GitHub issues
gh search issues "[error message]" --json repository,title,url,state --limit 20

# Search in specific repo
gh search issues "[error]" --repo owner/repo --json title,url,state

# Search with labels
gh search issues "[topic]" --label "bug" --state open

Research Patterns

Before Adopting a Library

#!/bin/bash
LIB="$1"

echo "=== GitHub Presence ==="
gh search repos "$LIB" --json fullName,stargazersCount,updatedAt --limit 3

echo ""
echo "=== Open Issues ==="
gh search issues "$LIB bug" --state open --json title,url --limit 5

echo ""
echo "=== AI Evaluation ==="
gemini -m pro -o text -e "" "Should I use $LIB in production? Consider maintenance, alternatives, and common issues."

Debugging with External Search

ERROR="your error message"

# Search for similar issues
gh search issues "$ERROR" --json repository,title,url,state --limit 10

# Search discussions
gh search issues "$ERROR" type:discussion --limit 5

# AI analysis of error
gemini -m pro -o text -e "" "Explain this error and likely causes: $ERROR"

Architectural Research

gemini -m pro -o text -e "" "Research best practices for: [architecture topic]

Specifically:
1. What do industry leaders (FAANG, etc.) do?
2. What are the tradeoffs?
3. Common mistakes to avoid
4. When to use vs. when to avoid
5. Concrete implementation guidance"

Staying Current

# Recent news on a topic
gemini -m pro -o text -e "" "What are the latest developments in [technology] as of 2024? Include version updates, new features, and ecosystem changes."

# Recent GitHub activity
gh search repos "[technology]" --created ">2024-01-01" --sort stars --json fullName,description,stargazersCount --limit 10

Output Synthesis

Standard Research Output

## Executive Summary
- Key point 1
- Key point 2
- Key point 3

## Detailed Findings
### Finding 1
[Details and evidence]

### Finding 2
[Details and evidence]

## Critical Analysis
- What's contested or uncertain
- What biases might exist
- What's missing

## Recommendations
1. Immediate action
2. Further investigation needed
3. Decisions to make

Comparison Output

## Quick Verdict
[1-2 sentence recommendation]

## Detailed Comparison
| Criterion | Option A | Option B | Option C |
|-----------|----------|----------|----------|
| Performance | ... | ... | ... |
| Ease of use | ... | ... | ... |

## Recommendation
[Detailed reasoning]

Best Practices

  1. State objective clearly - What decision are you trying to make?
  2. Use multiple sources - GitHub + web + AI synthesis
  3. Check recency - Technology changes quickly
  4. Verify claims - AI can hallucinate; cross-reference
  5. Save valuable research - Store in memory for future reference
  6. Follow up gaps - Research what's uncertain

FAQ

What does the research skill do?

Comprehensive research combining web search and AI synthesis. Use for deep research on topics, comparing technologies, investigating libraries, and finding GitHub issues related to problems.

How do I install research?

Run npx skills add https://github.com/johnlindquist/claude --skill research in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/research/ (personal) or .claude/skills/research/ (project).

Which AI agents can use research?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is research safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains research?

It is published by johnlindquist in johnlindquist/claude. It has 52 recorded installs.

More from johnlindquist/claude

View all →

gemini-image

johnlindquist/claude

Analyze images using Gemini's vision capabilities. Use for image analysis, text extraction from screenshots, and visual content understanding.

Media & Creative1.2K installs

memory

johnlindquist/claude

Persistent knowledge storage using basic-memory CLI. Use to save notes, search memories semantically, and build context for topics across sessions.

Docs & Writing362 installs

raycast-extension

johnlindquist/claude

Open the skill to read its SKILL.md instructions.

321 installs

brainstorm

johnlindquist/claude

Generate ideas and explore possibilities with AI. Use for creative problem solving, generating alternatives, and expanding on concepts.

deepwiki

johnlindquist/claude

Query DeepWiki for repository documentation and structure. Use to understand open source projects, find API docs, and explore codebases.

Docs & Writing269 installs

think

johnlindquist/claude

Open the skill to read its SKILL.md instructions.

258 installs

Popular productivity & automation skills

View category →

agent-browser

vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

OfficialProductivity & Automation1.3M installs

lark-doc

open.feishu.cn

飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

lark-base

open.feishu.cn

飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。

lark-drive

open.feishu.cn

飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。

lark-shared

open.feishu.cn

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.

lark-im

open.feishu.cn

飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。