Browse Skills

Diff a live page's accessibility violations against a baseline to surface regressions or fixes. By default compares uncommitted changes; branch comparison also supported.

Audits a live page for accessibility issues, pinpoints each WCAG violation with a selector, and returns a fix worklist without editing. Ideal for developers and QA to locate issues before making changes.

Drains a queue of open or waiting brain frames that were checkpointed by headless agent runs, using acc_act to continue deliberation. Use when you need to process pending deliberation tasks from an AI agent system.

Routes a goal through acc's scored-memory loop, deliberates on returned brain_frames, and submits proposals to continue the loop. Use for agentic problem-solving with memory scoring.

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

Automate ActiveCampaign CRM operations including contact management, tagging, list subscriptions, automation enrollment, and task creation using Rube MCP and Composio tools.

Analyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating causality.

Generate high-performing headlines, descriptions, and primary text for Google Ads, Meta, LinkedIn, TikTok, and more. Iterate based on performance data and platform constraints.

Add an iOS App Clip target to an Expo app. Use when the user mentions App Clip, AASA, apple-app-site-association, appclips, smart app banner, or wants to ship a lightweight iOS Clip invoked from a URL alongside their parent app.

Automatically fetch, categorize, and respond to GitHub Pull Request review comments and issues using the gh CLI. Ensures systematic feedback resolution and saves time in PR review cycles.

Fetches any X/Twitter post as clean JSON using the ADHX API. Returns full article content, author info, and engagement metrics — ideal for LLM analysis, summarization, or data extraction.

Implements LLM-as-judge techniques for evaluating model outputs with direct scoring, pairwise comparison, and bias mitigation. Use when building automated evaluation pipelines or comparing AI-generated responses.