[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EADWF4QVAS0MNXRDAB925Q":3,"skill-same:01M7EADWF4QVAS0MNXRDAB925Q":62},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M7EADWF4QVAS0MNXRDAB925Q","sherlock",null,"Find accounts for a username across 400+ platforms.","sanjeevafk\u002Fagent-skills","sanjeevafk","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F230678117?v=4","01M7C540EFY46ETG1NNWKS5X3Q","Sanjeev","01M7C540F366J5C1D587BMKH9Q",0,"MIT","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fcollections\u002Fhermes-agent\u002Fskills\u002Fsherlock\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sherlock\ndescription: Find accounts for a username across 400+ platforms.\nversion: 1.0.0\nauthor: unmodeled-tyler\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [osint, security, username, social-media, reconnaissance]\n    category: security\nprerequisites:\n  commands: [sherlock]\n---\n\n# Sherlock OSINT Username Search\n\nHunt down social media accounts by username across 400+ social networks using the [Sherlock Project](https:\u002F\u002Fgithub.com\u002Fsherlock-project\u002Fsherlock).\n\n## When to Use\n\n- User asks to find accounts associated with a username\n- User wants to check username availability across platforms\n- User is conducting OSINT or reconnaissance research\n- User asks \"where is this username registered?\" or similar\n\n## Requirements\n\n- Sherlock CLI installed: `pipx install sherlock-project` or `pip install sherlock-project`\n- Alternatively: Docker available (`docker run -it --rm sherlock\u002Fsherlock`)\n- Network access to query social platforms\n\n## Procedure\n\n### 1. Check if Sherlock is Installed\n\n**Before doing anything else**, verify sherlock is available:\n\n```bash\nsherlock --version\n```\n\nIf the command fails:\n- Offer to install: `pipx install sherlock-project` (recommended) or `pip install sherlock-project`\n- **Do NOT** try multiple installation methods — pick one and proceed\n- If installation fails, inform the user and stop\n\n### 2. Extract Username\n\n**Extract the username directly from the user's message if clearly stated.**\n\nExamples where you should **NOT** use clarify:\n- \"Find accounts for nasa\" → username is `nasa`\n- \"Search for johndoe123\" → username is `johndoe123`\n- \"Check if alice exists on social media\" → username is `alice`\n- \"Look up user bob on social networks\" → username is `bob`\n\n**Only use clarify if:**\n- Multiple potential usernames mentioned (\"search for alice or bob\")\n- Ambiguous phrasing (\"search for my username\" without specifying)\n- No username mentioned at all (\"do an OSINT search\")\n\nWhen extracting, take the **exact** username as stated — preserve case, numbers, underscores, etc.\n\n### 3. Build Command\n\n**Default command** (use this unless user specifically requests otherwise):\n```bash\nsherlock --print-found --no-color \"\u003Cusername>\" --timeout 90\n```\n\n**Optional flags** (only add if user explicitly requests):\n- `--nsfw` — Include NSFW sites (only if user asks)\n- `--tor` — Route through Tor (only if user asks for anonymity)\n\n**Do NOT ask about options via clarify** — just run the default search. Users can request specific options if needed.\n\n### 4. Execute Search\n\nRun via the `terminal` tool. The command typically takes 30-120 seconds depending on network conditions and site count.\n\n**Example terminal call:**\n```json\n{\n  \"command\": \"sherlock --print-found --no-color \\\"target_username\\\"\",\n  \"timeout\": 180\n}\n```\n\n### 5. Parse and Present Results\n\nSherlock outputs found accounts in a simple format. Parse the output and present:\n\n1. **Summary line:** \"Found X accounts for username 'Y'\"\n2. **Categorized links:** Group by platform type if helpful (social, professional, forums, etc.)\n3. **Output file location:** Sherlock saves results to `\u003Cusername>.txt` by default\n\n**Example output parsing:**\n```\n[+] Instagram: https:\u002F\u002Finstagram.com\u002Fusername\n[+] Twitter: https:\u002F\u002Ftwitter.com\u002Fusername\n[+] GitHub: https:\u002F\u002Fgithub.com\u002Fusername\n```\n\nPresent findings as clickable links when possible.\n\n## Pitfalls\n\n### No Results Found\nIf Sherlock finds no accounts, this is often correct — the username may not be registered on checked platforms. Suggest:\n- Checking spelling\u002Fvariation\n- Trying similar usernames with `?` wildcard: `sherlock \"user?name\"`\n- The user may have privacy settings or deleted accounts\n\n### Timeout Issues\nSome sites are slow or block automated requests. Use `--timeout 120` to increase wait time, or `--site` to limit scope.\n\n### Tor Configuration\n`--tor` requires Tor daemon running. If user wants anonymity but Tor isn't available, suggest:\n- Installing Tor service\n- Using `--proxy` with an alternative proxy\n\n### False Positives\nSome sites always return \"found\" due to their response structure. Cross-reference unexpected results with manual checks.\n\n### Rate Limiting\nAggressive searches may trigger rate limits. For bulk username searches, add delays between calls or use `--local` with cached data.\n\n## Installation\n\n### pipx (recommended)\n```bash\npipx install sherlock-project\n```\n\n### pip\n```bash\npip install sherlock-project\n```\n\n### Docker\n```bash\ndocker pull sherlock\u002Fsherlock\ndocker run -it --rm sherlock\u002Fsherlock \u003Cusername>\n```\n\n### Linux packages\nAvailable on Debian 13+, Ubuntu 22.10+, Homebrew, Kali, BlackArch.\n\n## Ethical Use\n\nThis tool is for legitimate OSINT and research purposes only. Remind users:\n- Only search usernames they own or have permission to investigate\n- Respect platform terms of service\n- Do not use for harassment, stalking, or illegal activities\n- Consider privacy implications before sharing results\n\n## Verification\n\nAfter running sherlock, verify:\n1. Output lists found sites with URLs\n2. `\u003Cusername>.txt` file created (default output) if using file output\n3. If `--print-found` used, output should only contain `[+]` lines for matches\n\n## Example Interaction\n\n**User:** \"Can you check if the username 'johndoe123' exists on social media?\"\n\n**Agent procedure:**\n1. Check `sherlock --version` (verify installed)\n2. Username provided — proceed directly\n3. Run: `sherlock --print-found --no-color \"johndoe123\" --timeout 90`\n4. Parse output and present links\n\n**Response format:**\n> Found 12 accounts for username 'johndoe123':\n>\n> • https:\u002F\u002Ftwitter.com\u002Fjohndoe123\n> • https:\u002F\u002Fgithub.com\u002Fjohndoe123\n> • https:\u002F\u002Finstagram.com\u002Fjohndoe123\n> • [... additional links]\n>\n> Results saved to: johndoe123.txt\n\n---\n\n**User:** \"Search for username 'alice' including NSFW sites\"\n\n**Agent procedure:**\n1. Check sherlock installed\n2. Username + NSFW flag both provided\n3. Run: `sherlock --print-found --no-color --nsfw \"alice\" --timeout 90`\n4. Present results","# Sherlock OSINT Username Search\n\nHunt down social media accounts by username across 400+ social networks using the [Sherlock Project](https:\u002F\u002Fgithub.com\u002Fsherlock-project\u002Fsherlock).\n\n## When to Use\n\n- User asks to find accounts associated with a username\n- User wants to check username availability across platforms\n- User is conducting OSINT or reconnaissance research\n- User asks \"where is this username registered?\" or similar\n\n## Requirements\n\n- Sherlock CLI installed: `pipx install sherlock-project` or `pip install sherlock-project`\n- Alternatively: Docker available (`docker run -it --rm sherlock\u002Fsherlock`)\n- Network access to query social platforms\n\n## Procedure\n\n### 1. Check if Sherlock is Installed\n\n**Before doing anything else**, verify sherlock is available:\n\n```bash\nsherlock --version\n```\n\nIf the command fails:\n- Offer to install: `pipx install sherlock-project` (recommended) or `pip install sherlock-project`\n- **Do NOT** try multiple installation methods — pick one and proceed\n- If installation fails, inform the user and stop\n\n### 2. Extract Username\n\n**Extract the username directly from the user's message if clearly stated.**\n\nExamples where you should **NOT** use clarify:\n- \"Find accounts for nasa\" → username is `nasa`\n- \"Search for johndoe123\" → username is `johndoe123`\n- \"Check if alice exists on social media\" → username is `alice`\n- \"Look up user bob on social networks\" → username is `bob`\n\n**Only use clarify if:**\n- Multiple potential usernames mentioned (\"search for alice or bob\")\n- Ambiguous phrasing (\"search for my username\" without specifying)\n- No username mentioned at all (\"do an OSINT search\")\n\nWhen extracting, take the **exact** username as stated — preserve case, numbers, underscores, etc.\n\n### 3. Build Command\n\n**Default command** (use this unless user specifically requests otherwise):\n```bash\nsherlock --print-found --no-color \"\u003Cusername>\" --timeout 90\n```\n\n**Optional flags** (only add if user explicitly requests):\n- `--nsfw` — Include NSFW sites (only if user asks)\n- `--tor` — Route through Tor (only if user asks for anonymity)\n\n**Do NOT ask about options via clarify** — just run the default search. Users can request specific options if needed.\n\n### 4. Execute Search\n\nRun via the `terminal` tool. The command typically takes 30-120 seconds depending on network conditions and site count.\n\n**Example terminal call:**\n```json\n{\n  \"command\": \"sherlock --print-found --no-color \\\"target_username\\\"\",\n  \"timeout\": 180\n}\n```\n\n### 5. Parse and Present Results\n\nSherlock outputs found accounts in a simple format. Parse the output and present:\n\n1. **Summary line:** \"Found X accounts for username 'Y'\"\n2. **Categorized links:** Group by platform type if helpful (social, professional, forums, etc.)\n3. **Output file location:** Sherlock saves results to `\u003Cusername>.txt` by default\n\n**Example output parsing:**\n```\n[+] Instagram: https:\u002F\u002Finstagram.com\u002Fusername\n[+] Twitter: https:\u002F\u002Ftwitter.com\u002Fusername\n[+] GitHub: https:\u002F\u002Fgithub.com\u002Fusername\n```\n\nPresent findings as clickable links when possible.\n\n## Pitfalls\n\n### No Results Found\nIf Sherlock finds no accounts, this is often correct — the username may not be registered on checked platforms. Suggest:\n- Checking spelling\u002Fvariation\n- Trying similar usernames with `?` wildcard: `sherlock \"user?name\"`\n- The user may have privacy settings or deleted accounts\n\n### Timeout Issues\nSome sites are slow or block automated requests. Use `--timeout 120` to increase wait time, or `--site` to limit scope.\n\n### Tor Configuration\n`--tor` requires Tor daemon running. If user wants anonymity but Tor isn't available, suggest:\n- Installing Tor service\n- Using `--proxy` with an alternative proxy\n\n### False Positives\nSome sites always return \"found\" due to their response structure. Cross-reference unexpected results with manual checks.\n\n### Rate Limiting\nAggressive searches may trigger rate limits. For bulk username searches, add delays between calls or use `--local` with cached data.\n\n## Installation\n\n### pipx (recommended)\n```bash\npipx install sherlock-project\n```\n\n### pip\n```bash\npip install sherlock-project\n```\n\n### Docker\n```bash\ndocker pull sherlock\u002Fsherlock\ndocker run -it --rm sherlock\u002Fsherlock \u003Cusername>\n```\n\n### Linux packages\nAvailable on Debian 13+, Ubuntu 22.10+, Homebrew, Kali, BlackArch.\n\n## Ethical Use\n\nThis tool is for legitimate OSINT and research purposes only. Remind users:\n- Only search usernames they own or have permission to investigate\n- Respect platform terms of service\n- Do not use for harassment, stalking, or illegal activities\n- Consider privacy implications before sharing results\n\n## Verification\n\nAfter running sherlock, verify:\n1. Output lists found sites with URLs\n2. `\u003Cusername>.txt` file created (default output) if using file output\n3. If `--print-found` used, output should only contain `[+]` lines for matches\n\n## Example Interaction\n\n**User:** \"Can you check if the username 'johndoe123' exists on social media?\"\n\n**Agent procedure:**\n1. Check `sherlock --version` (verify installed)\n2. Username provided — proceed directly\n3. Run: `sherlock --print-found --no-color \"johndoe123\" --timeout 90`\n4. Parse output and present links\n\n**Response format:**\n> Found 12 accounts for username 'johndoe123':\n>\n> • https:\u002F\u002Ftwitter.com\u002Fjohndoe123\n> • https:\u002F\u002Fgithub.com\u002Fjohndoe123\n> • https:\u002F\u002Finstagram.com\u002Fjohndoe123\n> • [... additional links]\n>\n> Results saved to: johndoe123.txt\n\n---\n\n**User:** \"Search for username 'alice' including NSFW sites\"\n\n**Agent procedure:**\n1. Check sherlock installed\n2. Username + NSFW flag both provided\n3. Run: `sherlock --print-found --no-color --nsfw \"alice\" --timeout 90`\n4. Present results",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":34,"description":7,"prerequisites":38},"unmodeled-tyler","1.0.0",{"hermes":27},{"tags":28,"category":30},[29,30,31,32,33],"osint","security","username","social-media","reconnaissance",[35,36,37],"linux","macos","windows",{"commands":39},[5],"main","4e084e84eb42fc53e144c89c0f7f48b39c8a4b0f","collections\u002Fhermes-agent\u002Fskills\u002Fsherlock",1,"https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills","https:\u002F\u002Fgithub.com\u002Fsanjeevafk","First make it work. Then make it right. Then make it fast.","2026-11-14 13:36:16",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add sanjeevafk\u002Fagent-skills --skill sherlock",{"tool":54,"command":55},"bunx","bunx skills add sanjeevafk\u002Fagent-skills --skill sherlock",{"tool":57,"command":58},"pnpm","pnpm dlx skills add sanjeevafk\u002Fagent-skills --skill sherlock","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fcollections\u002Fhermes-agent\u002Fskills\u002Fsherlock\u002FSKILL.md",true,[],[63,70,78,87,95,102],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7EFHX67M3KKXT1BXVPA5ADT","zarr-python","Chunked N-D arrays for cloud storage (Zarr-Python 3). Compressed arrays, parallel I\u002FO, S3\u002FGCS via fsspec, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7EFFQGM51TZBGRENXY50ZYM","whiteboard-diagrams","Create accurate, simple, hand-drawn whiteboard diagrams from a user's process, system, architecture, learning workflow, comparison, or causal explanation. Use when the user asks for a scribbly whiteboard visual, educational workflow graphic, hand-drawn explainer, or diagram like the bundled reference; ask one focused clarification question when the subject or relationships are missing, then generate and visually verify the final image.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwhiteboard-diagrams\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwhiteboard-diagrams\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7EFF1CSQNTDMHFK4ZGY6NYK","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7EFE8106X6C28FT8PA74427","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7EFCSNZM9G7ZHS6F127Q71X","verification-loop","A comprehensive verification system for Claude Code sessions.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M7EFCE7EZMKPRYDDNKBQ9EEH","vercel-deploy","Deploy applications and websites to Vercel. Use when the user requests deployment actions like \"deploy my app\", \"deploy and give me the link\", \"push this live\", or \"create a preview deployment\".","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-deploy\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-deploy\u002FSKILL.md",[],[]]