Browse Skills

Offensive IoT provides a methodology for security testing IoT and embedded devices, covering hardware reconnaissance, firmware extraction, analysis, and exploitation. Use for pentests, smart-home assessments, ICS/OT testing, or embedded vulnerability research.

Offensive Mobile provides a methodology for penetration testing Android and iOS applications, covering static analysis, dynamic instrumentation with Frida, SSL pinning bypass, and insecure data storage audits.

Offensive Shellcode provides a reference for developing custom shellcode, loaders, and evasion techniques for offensive security engagements. Use when writing x86/x64 shellcode, implementing position-independent code, or evading AV/EDR.

OSINT Methodology provides a structured framework for open source intelligence campaigns, covering target profiling, collection workflows, data correlation, timeline reconstruction, and reporting.

Windows Mitigations covers Windows exploit mitigations such as ASLR, DEP, CFG, CET, SEHOP, and ACG, including known bypass techniques. Use it when researching Windows hardening, planning mitigation bypass strategies, or analyzing crash dumps to identify which protection stopped an exploit.

Windows Security Boundaries maps Windows security boundary taxonomy and enumerates attack surfaces such as kernel/user, sandbox, COM/RPC, and hypervisor boundaries, used when planning privilege escalation and sandbox escape paths.

Code Review reviews code diffs and files for security vulnerabilities (OWASP Top 10), error handling, complexity, naming conventions, and performance issues. Use when you need to review a PR, pull request, diff, merge request, or code changes.

Compute Ladder organizes model selection by provider health, using Tier 0 local models for most tasks and paid models only as break-glass. It triggers fallback on 429, timeout, or stream death—never on perceived task difficulty.

Create Agent creates and configures agent.yaml files, writes SOUL.md personality definitions, and sets up agent directory structures with skills, tools, and knowledge. Use it when you need to configure an agent, set up its skills and knowledge, or customize agent settings.

Document Review reviews financial documents (prospectuses, ADVs, marketing materials) for FINRA 2210 compliance, required disclosures, and balanced presentation. Use it when checking financial statements, audit documents, regulatory filings, or compliance issues.

Export & Import Agents converts agent definitions between frameworks such as Claude Code, OpenAI, CrewAI, Lyzr, and GitHub Models, and imports from Claude, Cursor, and CrewAI projects.

Get Started with GitAgent guides installation of gitagent and creation of a first agent using scaffolding, configuration, and validation. Use when new to gitagent or setting up an initial agent.