Sherlock logo

Sherlock

Community
AlexAI-MCP
sherlock

OSINT username search across 400+ social networks using the Sherlock Project.

Overview

PublisherAlexAI-MCP
Repositoryhermes-CCC
Skill namesherlock
Stars
134
Forks
22
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 AlexAI-MCP on GitHub. Read the source before you install it.

Installation

Install the Sherlock 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/AlexAI-MCP/hermes-CCC/tree/master/skills/sherlock
  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/AlexAI-MCP/hermes-CCC.git /tmp/hermes-CCC
mkdir -p .claude/skills
cp -r /tmp/hermes-CCC/skills/sherlock .claude/skills/sherlock
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sherlock 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 Sherlock 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 Sherlock 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.

Sherlock

Purpose

  • Use this skill to search for username presence across many public social platforms and web services.
  • Sherlock is useful for OSINT, account enumeration, alias correlation, and open-source reconnaissance.
  • It is a reconnaissance utility, not a guarantee of identity resolution.

Install

bash
pip install sherlock-project

Alternative source install:

bash
git clone https://github.com/sherlock-project/sherlock
cd sherlock
python -m pip install -r requirements.txt
python sherlock.py username

Basic Search

bash
sherlock username
  • This searches a broad set of supported sites for a single username.
  • Output normally shows which sites likely contain a matching profile.
  • Results are only a starting point and should be verified manually.

Multiple Usernames

bash
sherlock user1 user2 user3
  • Use this when comparing handles across several candidate aliases.
  • Batch searching is useful when the target uses variations of the same naming pattern.
  • Keep the candidate list short enough to review carefully.

Output to a File

bash
sherlock username --output results.txt
  • Save results when you need an audit trail or want to compare scans over time.
  • Text output is convenient for quick archival, case notes, and manual review.

CSV Output

bash
sherlock username --csv
  • CSV output is useful for spreadsheet triage and bulk analysis.
  • This is the better option when integrating results into reporting or other tooling.

Restrict Search to Specific Sites

bash
sherlock username --site twitter github
  • Site filtering is useful when you only care about a narrow platform set.
  • Restricting sites speeds up focused investigations and reduces noise.
  • Use it for targeted checks like developer handles, gaming handles, or creator profiles.

Timeout Control

bash
sherlock username --timeout 10
  • Increase the timeout on slow or unstable networks.
  • Decrease it when you want faster but less patient scans.
  • Timeouts affect coverage and speed, so tune them to the environment.

Tor Support

bash
sherlock username --tor
  • This requires Tor to be installed and available.
  • Use Tor only when your environment and policy allow it.
  • Expect slower requests and occasional site behavior differences.

Print All Results

bash
sherlock username --print-all
  • This includes not-found results in addition to matches.
  • It is useful when you want a full per-site record rather than only positive hits.
  • Full output is better for documentation and reproducible analysis.

Practical Workflow

  1. Start with a single username search.
  2. Save results to a file or CSV.
  3. Filter to high-value platforms for deeper review.
  4. Manually verify candidate profiles.
  5. Correlate bios, avatars, links, timestamps, and naming patterns.

Verification Guidance

  • A found username is not proof that the account belongs to the same person.
  • Check profile metadata such as avatar reuse, linked websites, self-descriptions, and posting patterns.
  • Compare account creation dates, geographic references, and cross-links.
  • Treat weak matches as leads, not conclusions.

Good Use Cases

  • Brand protection checks
  • Public alias discovery
  • Security research on exposed usernames
  • Reconnaissance for incident response
  • Confirming whether a handle is broadly reused

Limitations

  • Site behavior changes can break detection.
  • Some platforms throttle or block automated requests.
  • False positives and false negatives both happen.
  • Private or suspended accounts may not appear reliably.

Output Handling

  • Keep raw outputs with timestamps when the result matters.
  • Store CSV when the data will be joined with other OSINT sources.
  • Re-run focused scans rather than assuming old results are still valid.

Ethical Use

  • Use Sherlock only for authorized research, defensive security work, or lawful OSINT.
  • Do not use it to harass, dox, stalk, or profile individuals without authorization.
  • Respect the legal and policy boundaries of your organization and jurisdiction.

Summary

  • Install with pip install sherlock-project or from the upstream GitHub repo.
  • Search one handle with sherlock username.
  • Search several with sherlock user1 user2 user3.
  • Save results with --output results.txt or --csv.
  • Restrict sites with --site twitter github.
  • Tune network behavior with --timeout 10 and optionally --tor.
  • Use --print-all when a complete site-by-site record is needed.

Frequently asked questions

What does the Sherlock AI skill do?

OSINT username search across 400+ social networks using the Sherlock Project.

Why use Sherlock on TypingMind?

Because you install it once and use it with any model. Sherlock 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 Sherlock in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/sherlock. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Sherlock?

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 Sherlock?

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

Is the Sherlock AI skill free?

Yes. It is published on GitHub by AlexAI-MCP 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 👇