How do I install the Research skill?

Run npx skillmds@latest add tomevault-io/research-14 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Research safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Research?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Research free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Research?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Research by tomevault-io — Agent Skill

Name: Research
Author: tomevault-io

Research

Deep research on technical topics, libraries, APIs, or concepts. Use when asked to research, investigate, explore deeply, or gather comprehensive information on a topic. Saves learnings to .agents/research/. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

Research Skill

Conducts deep research on technical topics, saving findings for future reference.

Capabilities

Web search for documentation, articles, and examples
Deep analysis using Oracle for complex reasoning
Cross-reference multiple sources
Save structured learnings to .agents/research/

Workflow

1. Clarify Scope

Before starting, confirm:

Topic: What exactly needs researching?
Depth: Quick overview or comprehensive deep-dive?
Focus: Implementation details, best practices, comparisons, or concepts?

2. Research Phase

Use these tools in combination:

Tool	Use For
`web_search`	Find documentation, articles, tutorials
`read_web_page`	Extract detailed content from URLs
`oracle`	Deep analysis, synthesizing findings, reasoning about trade-offs
`librarian`	Explore open-source implementations
`gh` (via Bash)	Fetch repo content, issues, PRs, releases when you have a direct GitHub URL

Note: librarian accesses GitHub repositories (public repos and private repos you've authorized). For local codebase searches, use finder or Grep instead. Use gh CLI for targeted queries like gh repo view, gh issue list, or gh release list.

Research strategy:

Start with web_search to find authoritative sources
Use read_web_page to extract key information
Consult oracle for analysis and synthesis
Use librarian to find real-world implementations

3. Document Findings

Save research to .agents/research/[topic-slug].md:

# Research: [Topic Name]

**Date:** YYYY-MM-DD
**Status:** Draft | Complete
**Tags:** [relevant, tags]

## Summary

[2-3 sentence overview of key findings]

## Key Learnings

- Learning 1
- Learning 2
- Learning 3

## Details

### [Subtopic 1]

[Detailed findings]

### [Subtopic 2]

[Detailed findings]

## Sources

- [Source Title](url) - Brief description of what was learned
- [Source Title](url) - Brief description

## Open Questions

- [ ] Question that needs further research
- [ ] Another question

## Related Research

- [[other-topic.md]] - How it relates

4. Synthesize & Report

Provide the user with:

Executive summary (3-5 bullet points)
Recommendations based on findings
Link to saved research file

File Naming Convention

Use kebab-case slugs: .agents/research/[topic-slug].md

Examples:

react-server-components.md
firebase-auth-patterns.md
zod-vs-yup-comparison.md

Deep Research Mode

For comprehensive research, use Oracle with focused prompts:

task: "Analyze [topic] considering:
- Current best practices
- Common pitfalls
- Performance implications
- Security considerations"

Quick Reference

Start research:

Research [topic] - [specific focus]

Check existing research:

ls -la .agents/research/

Update existing research: Add new sections or update status from Draft to Complete.

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: research-14description: Deep research on technical topics, libraries, APIs, or concepts. Use when asked to research, investigate, explore deeply, or gather comprehensive information on a topic. Saves learnings to .agents/research/. Use when this capability is needed.---# Research SkillConducts deep research on technical topics, saving findings for future reference.## Capabilities- Web search for documentation, articles, and examples- Deep analysis using Oracle for complex reasoning- Cross-reference multiple sources- Save structured learnings to `.agents/research/`## Workflow### 1. Clarify ScopeBefore starting, confirm:- **Topic**: What exactly needs researching?- **Depth**: Quick overview or comprehensive deep-dive?- **Focus**: Implementation details, best practices, comparisons, or concepts?### 2. Research PhaseUse these tools in combination:| Tool | Use For ||------|---------|| `web_search` | Find documentation, articles, tutorials || `read_web_page` | Extract detailed content from URLs || `oracle` | Deep analysis, synthesizing findings, reasoning about trade-offs || `librarian` | Explore open-source implementations || `gh` (via Bash) | Fetch repo content, issues, PRs, releases when you have a direct GitHub URL |> **Note:** `librarian` accesses GitHub repositories (public repos and private repos you've authorized). For local codebase searches, use `finder` or `Grep` instead. Use `gh` CLI for targeted queries like `gh repo view`, `gh issue list`, or `gh release list`.**Research strategy:**1. Start with `web_search` to find authoritative sources2. Use `read_web_page` to extract key information3. Consult `oracle` for analysis and synthesis4. Use `librarian` to find real-world implementations### 3. Document FindingsSave research to `.agents/research/[topic-slug].md`:```markdown# Research: [Topic Name]**Date:** YYYY-MM-DD**Status:** Draft | Complete**Tags:** [relevant, tags]## Summary[2-3 sentence overview of key findings]## Key Learnings- Learning 1- Learning 2- Learning 3## Details### [Subtopic 1][Detailed findings]### [Subtopic 2][Detailed findings]## Sources- [Source Title](url) - Brief description of what was learned- [Source Title](url) - Brief description## Open Questions- [ ] Question that needs further research- [ ] Another question## Related Research- [[other-topic.md]] - How it relates```### 4. Synthesize & ReportProvide the user with:1. **Executive summary** (3-5 bullet points)2. **Recommendations** based on findings3. **Link to saved research file**## File Naming ConventionUse kebab-case slugs: `.agents/research/[topic-slug].md`Examples:- `react-server-components.md`- `firebase-auth-patterns.md`- `zod-vs-yup-comparison.md`## Deep Research ModeFor comprehensive research, use Oracle with focused prompts:```texttask: "Analyze [topic] considering:- Current best practices- Common pitfalls- Performance implications- Security considerations"```## Quick Reference**Start research:**```textResearch [topic] - [specific focus]```**Check existing research:**```bashls -la .agents/research/```**Update existing research:**Add new sections or update status from Draft to Complete.---> Converted and distributed by [TomeVault](https://tomevault.io/claim/colmarius) — claim your Tome and manage your conversions.

Frequently asked questions