用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/agentic-in/elephant-agent --skill sherlock命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Keeps lightweight public-web discovery available for prompts, scheduled jobs, and follow-up research.
Open Notes.app and create or update iCloud notes on macOS using memo when possible and AppleScript when direct app automation is more reliable.
Open Reminders.app and create macOS reminders with AppleScript when the user wants follow-ups in Apple's reminders system.
正在显示 SKILL.md
基于 SOC 职业分类
| name | Sherlock |
| skill_id | sherlock |
| description | OSINT username search across 400+ social networks. Hunt down social media accounts by username. |
| version | 1.0.0 |
| source_kind | elephant-builtin |
| category | security |
| default_enabled | false |
Hunt down social media accounts by username across 400+ social networks using the Sherlock Project.
pipx install sherlock-project or pip install sherlock-projectdocker run -it --rm sherlock/sherlock)Before doing anything else, verify sherlock is available:
sherlock --version
If the command fails:
pipx install sherlock-project (recommended) or pip install sherlock-projectExtract the username directly from the user's message if clearly stated.
Examples where you should NOT use clarify:
nasajohndoe123alicebobOnly use clarify if:
When extracting, take the exact username as stated — preserve case, numbers, underscores, etc.
Default command (use this unless user specifically requests otherwise):
sherlock --print-found --no-color "<username>" --timeout 90
Optional flags (only add if user explicitly requests):
--nsfw — Include NSFW sites (only if user asks)--tor — Route through Tor (only if user asks for anonymity)Do NOT ask about options via clarify — just run the default search. Users can request specific options if needed.
Run via the terminal tool. The command typically takes 30-120 seconds depending on network conditions and site count.
Example terminal call:
{
"command": "sherlock --print-found --no-color \"target_username\"",
"timeout": 180
}
Sherlock outputs found accounts in a simple format. Parse the output and present:
<username>.txt by defaultExample output parsing:
[+] Instagram: https://instagram.com/username
[+] Twitter: https://twitter.com/username
[+] GitHub: https://github.com/username
Present findings as clickable links when possible.
If Sherlock finds no accounts, this is often correct — the username may not be registered on checked platforms. Suggest:
? wildcard: sherlock "user?name"Some sites are slow or block automated requests. Use --timeout 120 to increase wait time, or --site to limit scope.
--tor requires Tor daemon running. If user wants anonymity but Tor isn't available, suggest:
--proxy with an alternative proxySome sites always return "found" due to their response structure. Cross-reference unexpected results with manual checks.
Aggressive searches may trigger rate limits. For bulk username searches, add delays between calls or use --local with cached data.
pipx install sherlock-project
pip install sherlock-project
docker pull sherlock/sherlock
docker run -it --rm sherlock/sherlock <username>
Available on Debian 13+, Ubuntu 22.10+, Homebrew, Kali, BlackArch.
This tool is for legitimate OSINT and research purposes only. Remind users:
After running sherlock, verify:
<username>.txt file created (default output) if using file output--print-found used, output should only contain [+] lines for matchesUser: "Can you check if the username 'johndoe123' exists on social media?"
Agent procedure:
sherlock --version (verify installed)sherlock --print-found --no-color "johndoe123" --timeout 90Response format:
Found 12 accounts for username 'johndoe123':
• https://twitter.com/johndoe123 • https://github.com/johndoe123 • https://instagram.com/johndoe123 • [... additional links]
Results saved to: johndoe123.txt
User: "Search for username 'alice' including NSFW sites"
Agent procedure:
sherlock --print-found --no-color --nsfw "alice" --timeout 90