agentleFS
amanning3390amanning3390/hermeshub/skills/web-researcher/SKILL.md

web-researcher

Skill48 starsChanged 5 months agoMITView on GitHub

Advanced web research — search, extract, and synthesize information from multiple sources. Use when the user needs research, fact-checking, competitive analysis, or information gathering.

  • Reads credentials

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always cite sources — never present research without attribution

    line 60
  2. Distinctive:

    Every claim should have at least one source URL

    line 67

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Web Researcher

Multi-source research agent with structured synthesis.

When to Use

  • User asks to research a topic, company, person, or technology
  • User needs competitive analysis or market research
  • User wants fact-checking or source verification
  • User needs summarized information from multiple web sources

Procedure

  1. Parse the research query to identify key topics and constraints
  2. Generate 3-5 diverse search queries covering different angles
  3. Execute searches in parallel using available search tools
  4. For each promising result, extract the full page content
  5. Cross-reference facts across multiple sources
  6. Synthesize findings into a structured report with citations
  7. Flag any conflicting information between sources

Research Output Format

# Research: [Topic]

## Key Findings
- Finding 1 (Source: [url])
- Finding 2 (Source: [url])

## Detailed Analysis
[Structured analysis with inline citations]

## Sources
1. [Title](url) - Relevance: High/Medium/Low
2. [Title](url) - Relevance: High/Medium/Low

## Confidence & Gaps
- Confidence: High/Medium/Low
- Information gaps: [what couldn't be verified]

Pitfalls

  • Always cite sources — never present research without attribution
  • Cross-reference claims across at least 2 sources
  • Note when information is from a single source only
  • Be explicit about information freshness and publication dates
  • Distinguish between facts, analysis, and speculation

Verification

  • Every claim should have at least one source URL
  • Key facts should be cross-referenced across sources
  • Report should explicitly state confidence level

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.