# Browser Research Agent

> Compatibility workflow for browser-backed evidence capture. Deprecated: use web-research for primary-source research, citations, freshness, and gap analysis.

- Skill: `memi-design/browser-research-agent` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add memi-design/browser-research-agent`
- Raw SKILL.md: https://api.skillmd.com/api/skills/memi-design/browser-research-agent/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: memi-design (https://skillmd.com/u/memi-design)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/memi-design/browser-research-agent

---


# Browser Research Agent

> Deprecated compatibility slug. Use `web-research` for new work. This payload remains self-contained for clients that installed the historical name.

Run browser-backed research agents that capture evidence, citations, and source freshness.

## When to Use

Use this Note when a Memoire or Studio run needs browser research, web evidence, citation capture, source comparison.

## Workflow

1. Start with primary sources, then use secondary sources only to find more primary evidence.
2. Record source URL, access date, claim, confidence, and whether the fact is time-sensitive.
3. Use screenshots for visual UI claims and direct API responses for machine-readable facts.
4. Separate quotes from paraphrases and keep quoted excerpts short.
5. Finish with an evidence table and a list of claims that still need verification.


## Sources

- https://developers.openai.com/codex/use-cases
- https://github.com/nousresearch/hermes-agent
- https://docs.openclaw.ai/cli