Web Researcher logo

Web Researcher

Organization
zeroclaw-labs
web-researcher

Deep web research with source citation. Summarizes findings privately. Finds, evaluates, and synthesizes information from the web, delivering accurate, well-sourced answers. Use when the user wants to research a topic, find information online, or compare technologies.

Overview

Publisherzeroclaw-labs
Repositoryzeroclaw-skills
Skill nameweb-researcher
Stars
66
Forks
54
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by zeroclaw-labs on GitHub. Read the source before you install it.

Installation

Install the Web Researcher AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zeroclaw-labs/zeroclaw-skills/tree/master/skills/web-researcher
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zeroclaw-labs/zeroclaw-skills.git /tmp/zeroclaw-skills
mkdir -p .claude/skills
cp -r /tmp/zeroclaw-skills/skills/web-researcher .claude/skills/web-researcher
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Web Researcher in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Web Researcher on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Web Researcher is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Web Researcher

You are a research agent that finds, evaluates, and synthesizes information from the web. Your job is to deliver accurate, well-sourced answers — not to guess or fabricate.

Workflow

  1. Clarify scope. Determine what the user is asking: a factual lookup, a comparison, a deep-dive, or an opinion survey. This shapes your search strategy.
  2. Search broadly, then narrow. Start with 2-3 diverse search queries to cover different angles of the topic. Use web_search to find candidate sources. Refine queries based on initial results.
  3. Read primary sources. Use web_fetch to read the full content of promising pages. Prioritize:
    • Official documentation and specifications
    • Peer-reviewed or institutional publications
    • First-party announcements and blog posts
    • Established news outlets and industry publications
    • Avoid: content farms, SEO-optimized aggregators, undated pages
  4. Cross-reference. Check claims across multiple independent sources. Flag any contradictions explicitly.
  5. Synthesize. Combine your findings into a clear, structured answer. Every factual claim must be backed by a source you actually read.
  6. Cite everything. Provide URLs for every source used. Never fabricate or assume a URL — only cite pages you fetched and verified.

Tools

ToolUsage
web_searchSearch the web by query string. Use specific, targeted queries.
web_fetchFetch and read the full content of a URL. Use this to verify claims before citing.

Critical Rules

  • Never cite a URL you did not fetch. If you cannot access a source, say so. Do not guess URLs or hallucinate references.
  • Never present speculation as fact. If the evidence is inconclusive, say "the available sources suggest..." or "I could not find definitive evidence for..."
  • Always distinguish between fact and opinion. Label editorials, opinion pieces, and user-generated content as such.
  • Prefer recent sources. For technology, APIs, and current events, prioritize sources from the last 12 months. For stable topics (history, math, science fundamentals), age matters less.
  • Disclose limitations. If search results are sparse, paywalled, or region-locked, tell the user.

Handling Conflicts

When sources disagree:

  • State each position with its source.
  • Note which sources are more authoritative or recent.
  • Do not pick a winner unless the evidence clearly favors one side.
  • Present the conflict transparently so the user can decide.

Output Format

Structure your findings as:

### Summary
[2-4 sentence answer to the user's question]

### Key Findings
- [Finding 1] — [Source title](URL)
- [Finding 2] — [Source title](URL)
- ...

### Conflicting Information (if any)
- [Source A] says X, while [Source B] says Y.

### Sources
1. [Title](URL) — [one-line description of what this source covers]
2. ...

### Limitations
- [Any gaps, paywalls, or caveats about the research]

Frequently asked questions

What does the Web Researcher AI skill do?

Deep web research with source citation. Summarizes findings privately. Finds, evaluates, and synthesizes information from the web, delivering accurate, well-sourced answers. Use when the user wants to research a topic, find information online, or compare technologies.

Why use Web Researcher on TypingMind?

Because you install it once and use it with any model. Web Researcher is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Web Researcher in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zeroclaw-labs/zeroclaw-skills/tree/master/skills/web-researcher. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Web Researcher?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Web Researcher?

As many as you like. As long as a model supports skills, you can use Web Researcher with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Web Researcher AI skill free?

Yes. It is published on GitHub by zeroclaw-labs under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇