This breaks down research requests into structured investigations with subtopics, key findings, and open questions. It's designed to trigger when users say things like "what is known about" or "research X" and produces a consistent output format with a TL;DR, findings organized by subtopic, and suggested follow-ups. The approach is solid for getting organized summaries instead of wall-of-text responses. One thing to note: the quality will depend heavily on Claude's existing knowledge about your topic, since this is a prompting pattern rather than a web search tool. Best for well-established topics where you want a thoughtful breakdown rather than the latest news.

GitHub stars
2.8K
last updated
May 28, 2026

Install

$ npx -y skills add open-gitagent/opengap --skill research --agent claude-code

Installs into .claude/skills of the current project.

Files

Research

Instructions

When researching a topic:

  1. Identify the core question or area of interest
  2. Break it into 3-5 key subtopics
  3. For each subtopic, provide factual information with reasoning
  4. Note areas of uncertainty or debate
  5. Synthesize findings into a coherent summary

Output Format

## TL;DR
[Brief summary]

## Research Findings

### [Subtopic]
- [Key point with supporting reasoning]

## Open Questions
- [Areas that need further investigation]

## Suggested Follow-ups
- [Related questions the user might want to explore]

Example Output

## TL;DR
WebAssembly (Wasm) is a binary instruction format that enables near-native performance in browsers and increasingly in server-side contexts.

## Research Findings

### Browser Support & Adoption
- All major browsers support Wasm since 2017 — Chrome, Firefox, Safari, Edge
- Used in production by Figma (rendering engine), Google Earth (3D), and AutoCAD (web port)

### Performance Characteristics
- Typically 1.1-1.5x native speed for compute-heavy tasks
- **Uncertain**: Exact overhead varies significantly by workload type and runtime

Sponsors

Details

Repository
github.com/open-gitagent/opengap
Categories
Documentation, Data Science & ML
License
MIT
First seen
Jun 11, 2026

More from open-gitagent/opengap

All 18
1opensensenova avatarsn-da-non-spreadsheet-analysisopensensenova/sensenova-skillsWord / PDF / PPT 文档解析与数据分析引擎。覆盖三类文件格式的全量提取、表格数值化、图表理解与跨文档汇总分析。**遇到以下任一情况就主动使用本 skill**:①用户上传或指定了 .docx / .doc / .pdf / .pptx / .ppt 文件并要求分析、提取或统计其中内容;②用户出现触发词:W0skills.sh installs
2PackmindHub avatartest-factory-patternsPackmindHub/packmindThis skill provides guidance for writing test factories in the Packmind codebase. It should be used when creating or updating factory functions in `**/test/*Fac0skills.sh installs
3reactjs avatarreact-expertreactjs/react.devThe react-expert skill enables developers and documentation contributors to research React APIs and concepts by analyzing authoritative...0skills.sh installs
4rknall avatarGitLab Stack Creatorrknall/claude-skillsCreate new GitLab stack projects from templates with proper directory structure, git configuration, validation hooks, and documentation. Use when initializing n0skills.sh installs
5samarv avataropportunity-framingsamarv/ShanonFrame customer opportunities as unmet needs, pain points, and desires rather than solutions. Use when writing opportunities for an Opportunity Solution Tree, va0skills.sh installs
6shinpr avatarmcp-local-ragshinpr/mcp-local-ragSearch, ingest, expand chunk context, or manage local documents via a local RAG MCP server (tools: query_documents, read_chunk_neighbors, ingest_file, ingest_da0skills.sh installs