sickn33/agentic-awesome-skills

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.

Creates slide decks from text, outlines, documents, or a reference image using the 2slides API. It can also add voice narration and export slides as images or audio.

Expert system for building interactive 3D web experiences using Three.js, React Three Fiber, Spline, and WebGL. Covers product configurators, 3D portfolios, and immersive websites.

A structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness, ensuring statistical rigor and valid experiment design.

Helps plan, design, and implement A/B tests and experiments. Guides you through hypothesis formulation, sample size, metrics selection, and result analysis for growth experimentation.

Orchestrates coding tasks as a state machine from issue intake through implementation, review, deployment, and acceptance verification, ensuring every acceptance criterion has evidence before completion. Use for end-to-end delivery with minimal human re-intervention.

Automate finding and fixing WCAG 2.2 accessibility issues. Use report mode for audits or fix mode to audit, edit, and verify. Supports live-DOM auditing, browser MCPs, and static HTML.

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.

Audit web and mobile experiences for WCAG compliance, identify barriers, and provide remediation guidance to ensure inclusive digital products.

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.

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.

Provides expert legal analysis and strategy for cases involving Maria da Penha Law, domestic violence, feminicide, and Brazilian criminal procedure. Useful for victims, defendants, lawyers, and students seeking technical legal guidance.

Analyzes a project's niche to inject domain-specific knowledge, regulations, and standards. Use after identifying the niche to align product, design, and technology with industry requirements.

Designs, writes, and deploys new Claude Code skills following the Diamond Standard. Use this skill to generate custom, expert-level agent capabilities with a structured workflow.

Diagnoses AI project workspaces and creates optimal technical roadmaps, either from scratch or for existing codebases. Best used at project inception to plan tasks and assemble an expert AI squad, with all communication in Spanish.

Triage open promises and close them with honest, real-world verdicts using acc_act(runtime='outcome'). Ideal for agentic workflows tracking commitments.

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.

Audit deployed Vercel apps for cost and performance issues using production metrics, project configuration, code scans, and version-aware recommendations.

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.