Agent skills for Claude Desktop

Detect AI-generated deepfake audio used in voice phishing (vishing) by extracting spectral features (MFCC, spectral centroid, spectral…

This skill enables Claude to detect infrastructure drift from a desired state.

Detect Living Off the Land Binaries (LOLBins/LOLBAS) abuse including

Detect malicious scheduled task creation and modification using Sysmon

Detect command injection against Modbus TCP/RTU in ICS/SCADA environments by monitoring unauthorized writes, anomalous function codes…

Detects MSBuild projects with conflicting OutputPath or IntermediateOutputPath.

Detect and block spearphishing emails that use personalized, researched

Detect process injection techniques (T1055) - including DLL injection, process

Generates Detox E2E tests for React Native apps in JavaScript.

Automate Detrack tasks via Rube MCP (Composio).

Extreme lightweight end-to-end development workflow with requirements clarification, intelligent backend selection, parallel codeagent…

Automates web browser interactions using persistent sessions and AI-friendly snapshots to navigate, test, and scrape websites autonomously.

Use only when the user explicitly asks for a commit message without review.

Diagnoses and resolves test failures, build errors, and environment issues using targeted diagnostic strategies and minimal context.

- **Role**: China e-commerce multi-platform operations and campaign strategy specialist - **Personality**: Results-obsessed, data-driven…

Audit development environment (CLI tools, runtimes) before code.

Scaffold a new GPU lesson using forge_scene.h for the rendering baseline

Implements code tasks using a strict Test-Driven Development (TDD) workflow to ensure high-quality, production-ready results.

Initializes new development projects through interactive tech stack selection and automated scaffolding.

Run the current worktree as a production-shaped local dev instance — core, Slack, web UI, admin, portal, on a real Pi LLM + Postgres…

Switch AIWG CLI to dev mode (local repo source), rebuild, deploy dev tools, and run a health check — all via the Steward agent