
Web Research
- 3.6k installs
- 27.3k repo stars
- Updated August 5, 2026
- langchain-ai/deepagents
web-research is a skill that delegates web searches to subagents, saves findings to files, and synthesizes cited research reports for online topics.
About
web-research orchestrates multi-source online research using delegated subagents and file-based handoffs. Before delegating, the agent must create a research folder, break the question into two to five non-overlapping subtopics, and write research_plan.md with the main question, subtopics, expected information, and synthesis plan. Simple fact-finding uses one to two subtopics; comparative analysis assigns one subtopic per comparison element up to three; complex investigations use three to five. For each subtopic, the task tool spawns a research subagent with a clear question, instructions to save findings to research_[topic]/findings_[subtopic].md, and a budget of three to five web searches. Up to three subagents may run in parallel. After completion, list_files and read_file review local findings, then synthesize a response with integrated insights and source URLs; optional research_report.md captures the final write-up. fetch_url handles remote URLs; read_file is for local files only. Best practices emphasize planning before delegating, distinct subagent scopes, file-based communication, and stopping after sufficient coverage rather than over-searching.
- Mandatory research_plan.md with subtopics before spawning any research subagents.
- Delegates via task tool with three to five web searches per subtopic and up to three parallel subagents.
- File-based handoffs: findings saved to research_[topic]/findings_[subtopic].md for synthesis.
- Synthesis reads local findings with list_files and read_file; fetch_url for remote URLs only.
- Subtopic count scales by task type: 1-2 for facts, per-element for comparisons, 3-5 for complex investigations.
Web Research by the numbers
- 3,634 all-time installs (skills.sh)
- +87 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #223 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
web-research capabilities & compatibility
- Capabilities
- research plan creation with subtopic breakdown · parallel subagent delegation via task tool · file based findings persistence · multi source synthesis with url citations · optional final research_report.md output
- Use cases
- research · web search · orchestration
- Runs
- Runs locally
npx skills add https://github.com/langchain-ai/deepagents --skill web-researchAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 3.6k |
|---|---|
| repo stars | ★ 27.3k |
| Security audit | 2 / 3 scanners passed |
| Last updated | August 5, 2026 |
| Repository | langchain-ai/deepagents ↗ |
How do I research a topic online with parallel subagents and produce a cited synthesis without losing findings in chat?
Research topics online by delegating subagents to search the web, save findings to files, and synthesize cited reports.
Who is it for?
Agents that need structured multi-subtopic web research with file-based subagent handoffs and cited final reports.
Skip if: Skip when the answer is already in local project files or you need deep offline document analysis without web search.
When should I use this skill?
User asks to research a topic online, search the web, compare options, find current information, or produce a research report.
What you get
A research folder with plan and per-subtopic findings files plus a synthesized answer citing source URLs from saved research.
- research plan file
- cited research report
By the numbers
- Requires creating a dedicated research_[topic_name] folder before subagent delegation
Files
Web Research Skill
Research Process
Step 1: Create and Save Research Plan
Before delegating to subagents, you MUST:
1. Create a research folder - Organize all research files in a dedicated folder relative to the current working directory:
mkdir research_[topic_name]This keeps files organized and prevents clutter in the working directory.
2. Analyze the research question - Break it down into distinct, non-overlapping subtopics
3. Write a research plan file - Use the write_file tool to create research_[topic_name]/research_plan.md containing:
- The main research question
- 2-5 specific subtopics to investigate
- Expected information from each subtopic
- How results will be synthesized
Planning Guidelines:
- Simple fact-finding: 1-2 subtopics
- Comparative analysis: 1 subtopic per comparison element (max 3)
- Complex investigations: 3-5 subtopics
Step 2: Delegate to Research Subagents
For each subtopic in your plan:
1. Use the `task` tool to spawn a research subagent with:
- Clear, specific research question (no acronyms)
- Instructions to write findings to a file:
research_[topic_name]/findings_[subtopic].md - Budget: 3-5 web searches maximum
2. Run up to 3 subagents in parallel for efficient research
Subagent Instructions Template:
Research [SPECIFIC TOPIC]. Use the web_search tool to gather information.
After completing your research, use write_file to save your findings to research_[topic_name]/findings_[subtopic].md.
Include key facts, relevant quotes, and source URLs.
Use 3-5 web searches maximum.Step 3: Synthesize Findings
After all subagents complete:
1. Review the findings files that were saved locally:
- First run
list_files research_[topic_name]to see what files were created - Then use
read_filewith the file paths (e.g.,research_[topic_name]/findings_*.md) - Important: Use
read_filefor LOCAL files only, not URLs
2. Synthesize the information - Create a comprehensive response that:
- Directly answers the original question
- Integrates insights from all subtopics
- Cites specific sources with URLs (from the findings files)
- Identifies any gaps or limitations
3. Write final report (optional) - Use write_file to create research_[topic_name]/research_report.md if requested
Note: If you need to fetch additional information from URLs, use the fetch_url tool, not read_file.
Best Practices
- Plan before delegating - Always write research_plan.md first
- Clear subtopics - Ensure each subagent has distinct, non-overlapping scope
- File-based communication - Have subagents save findings to files, not return them directly
- Systematic synthesis - Read all findings files before creating final response
- Stop appropriately - Don't over-research; 3-5 searches per subtopic is usually sufficient
Related skills
Forks & variants (1)
Web Research has 1 known copy in the catalog totaling 54 installs. They canonicalize to this original listing.
- smithery.ai - 54 installs
How it compares
Pick web-research when citations, parallel subagents, and on-disk research folders are required; skip it for single-page summaries without sourced reports.
FAQ
How many web searches does each research subagent get?
Three to five web searches maximum per subtopic subagent, with up to three subagents running in parallel.
Where do subagents save their findings?
To research_[topic_name]/findings_[subtopic].md using write_file, not returned directly in chat.
Should I use read_file or fetch_url for sources?
read_file for local findings files only; use fetch_url when you need additional information from remote URLs.
Is Web Research safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.