Browse Skills

Provides expert analysis and guidance on Brazilian criminal law, specializing in domestic violence, Maria da Penha law, protective measures, and criminal procedure for both defense and prosecution.

Techniques for building reliable LLM-as-judge evaluation pipelines, including direct scoring, pairwise comparison, and bias mitigation. Use when implementing automated quality assessment for AI-generated outputs.

Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author info, and engagement metrics. No scraping or browser required.

Systematically address pull request review and issue comments using the GitHub CLI. Fetches comments, plans fixes, and responds to threads automatically.

Adds an iOS App Clip target to an Expo app, handling AASA files, associated domains, and smart app banners. Use when shipping a lightweight iOS Clip that is invoked from a URL alongside your parent app.

Create, iterate, and scale paid ad creative for Google Ads, Meta, LinkedIn, TikTok, and similar platforms. Use when generating headlines, descriptions, primary text, or large sets of ad variations for testing and performance optimization.

Normalize and analyze cross-channel ad campaign data from Google, Meta, LinkedIn, and more. Diagnose performance, quantify uncertainty, and propose evidence-labeled budget experiments for optimal spend allocation.

Automate ActiveCampaign CRM tasks using Rube MCP: manage contacts, tags, list subscriptions, enroll in automations, and create tasks. Ideal for AI agents handling marketing workflows.

Comprehensive techniques for attacking Microsoft Active Directory environments, covering reconnaissance, credential harvesting, Kerberos attacks, lateral movement, privilege escalation, and domain dominance for red team operations and penetration testing.

Routes a goal through an AI agent's scored-memory loop for structured deliberation and proposal submission. Use for tasks requiring meta-cognitive reasoning and commitment tracking.

Drain acc's open/waiting brain frames queue by reading typed holes and retrieved context, then submitting proposals via acc_act. Use this skill to clean up checkpointed frames from headless AI runs.

Helps triage open promises and close them with honest, real-world verdicts using the acc_act tool. Useful for accountability systems that require factual outcome validation.