Agent skill / SnailSploit
### offensive-osint
Core file
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionoffensive-osintExecute the skills CLI command in your project's root directory to begin installation:
Package manager
npx skills add https://github.com/SnailSploit/Claude-Red --skill offensive-osintFetches offensive-osint from SnailSploit/Claude-Red and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate offensive-osint. Access via /offensive-osintin your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
Copy the command for your terminal
Package manager
npx skills add https://github.com/SnailSploit/Claude-Red --skill offensive-osintWorks with
| name | offensive-osint |
| description | "Comprehensive OSINT methodology skill for offensive security, red team intelligence gathering, and bug bounty reconnaissance. Covers domain recon, email harvesting, social media profiling, GitHub/code leaks, Shodan/Censys enumeration, breach data lookup, employee profiling, infrastructure mapping, cryptocurrency tracing, geospatial intelligence, and AI-assisted analysis workflows. Use when performing reconnaissance against a target domain or organization, investigating a person or entity, tracing cryptocurrency flows, geolocating images or events, or building an attack-surface map." |
run_id and tool versions for reproducibility| Tool | Notes |
|---|---|
| Carrot2 | Clusters results by topic |
| etools | Metasearch engine |
| Kagi | Privacy-first, non-personalized results |
| Brave Search | Independent index; Goggles for custom ranking |
| PDF Search | Search PDF files and view table of contents |
| Google Fact Check Explorer | Cross-site fact-check search |
| Tool | Purpose |
|---|---|
| Sherlock | Username search across social networks |
| Maigret | Collect profiles by username from many sites |
| What's My Name | Username search across platforms |
| Holehe | Check if email is registered on platforms |
| Epieos | Email address pivots and metadata |
| OSINT Industries | Email/username/phone lookups |
| Hunter.io | Find email addresses for a domain |
| EmailRep | Email reputation and associated data |
| Emailable | Verify email existence |
| Mugetsu | X/Twitter username history |
| RocketReach / Apollo | Email enrichment and pattern guessing |
| PhoneInfoga | Phone number intelligence framework |
Browser extensions: GetProspect, SignalHire
| Platform | Tool |
|---|---|
| Picuki — view profiles without account | |
| X/Twitter | snscrape — preferred CLI scraper; use Twint only as fallback |
| Graph Search, sowsearch.info, lookup-id.com, whopostedwhat.com | |
| Facebook (research) | Meta Content Library — CrowdTangle successor (researcher-gated) |
| YouTube/Twitch | Social Blade — analytics |
| TikTok | Tokboard — trend and profile analytics |
| Reveddit — removed content; RedTrack.social — user history | |
| Bluesky | Firesky — real-time firehose; SkyView — follower graphs |
| Mastodon | FediSearch — cross-instance search; Fedifinder — find Twitter users on Mastodon |
| Faces | Search4Faces |
Russia: Rusprofile, Kontur.Focus (freemium), zakupki.gov.ru (procurement), EGRUL/EGRIP (official, captcha-gated)
China: GSXT (National Enterprise Credit), Qichacha/Tianyancha (freemium), MIIT ICP/Beian (ICP filings)
| Chain | Explorer |
|---|---|
| Bitcoin | Blockchain.com, Blockchair |
| Ethereum | Etherscan |
| BNB Chain | BSCScan |
| Polygon PoS | PolygonScan |
| Solana | Solscan |
| Multi-chain | OKLink [Freemium], Cielo |
L2 Explorers: Arbiscan, Optimistic Etherscan, BaseScan, zkSync Era, L2Beat (risk/TVL comparison)
Street View: Google Street View, Apple Maps, Yandex Maps, Baidu Maps
Warning: Never paste PII, sensitive IOCs, or unique pivots into cloud LLMs. They log inputs and may use them for training. Use local models (Ollama, LM Studio) for sensitive analysis.
| Tool | Strength |
|---|---|
| ChatGPT (paid) | Log parsing, dataset analysis, Code Interpreter for CSVs/JSON, GPT-4 Vision for image OCR |
| Claude (paid) | 200K token context for large document dumps and report synthesis |
| Gemini 1.5 Pro | 2M token context; Deep Research mode with citations |
| Perplexity Pro (paid) | Real-time web search + reasoning; multi-query synthesis |
Local/privacy-preserving: Ollama (Llama 3, Mistral), LM Studio, GPT4All
Evidence handling:
run_id and tool versions for reproducibilityhttps://t.me/s/<channel>Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
SnailSploit/Claude-Red
SnailSploit/Claude-Red
SnailSploit/Claude-Red
SnailSploit/Claude-Red
SnailSploit/Claude-Red
SnailSploit/Claude-Red
offensive-osint fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
We added offensive-osint from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
offensive-osint reduced setup friction for our internal harness; good balance of opinion and flexibility.
offensive-osint is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Useful defaults in offensive-osint — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
I recommend offensive-osint for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Registry listing for offensive-osint matched our evaluation — installs cleanly and behaves as described in the markdown.
Useful defaults in offensive-osint — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Registry listing for offensive-osint matched our evaluation — installs cleanly and behaves as described in the markdown.
Solid pick for teams standardizing on skills: offensive-osint is focused, and the summary matches what you get after install.
showing 1-10 of 44