Skill UI

Internal mobile-app workflow to add a single Dataverse table to an existing Mobile Offline Profile. Used by mobile orchestrators to configure offline data availability without re-running full profile setup. Skips per-table questionnaire for tables already in profile.

Adds Microsoft Teams connector to a Power Apps code app. Guides users through connection setup, configuring chat and channel operations, and building the app. Ideal for developers integrating Teams messaging in Power Apps.

Adds Work IQ (M365 Copilot Search) to a Power Apps code app via the Work IQ Copilot MCP connector, then wires up a production-ready McpSession wrapper for AI-powered, knowledge-grounded search and chat over internal Microsoft 365 content.

Creates an Agent Authority Charter to define permissions, delegation, approvals, escalation, and audit requirements for AI agents before enterprise or regulated deployment. Helps legal, compliance, risk, and product teams document what an agent may and may not do, prepare for human review, and ensure auditable governance across the agent lifecycle.

A tiered memory system for AI agents that promotes facts through four levels (L0-L3) based on recurrence and human confirmation. It uses only standard library without databases or LLMs to keep context clean. Hooks automate session capture and promotion, ensuring stable knowledge persists while transient data is discarded.

Authoritative question-answering engine for the EU Artificial Intelligence Act (Regulation 2024/1689), grounded in 70 official EU source documents. Provides article-level citations, explains concepts, obligations, high-risk classification, penalties, timelines, and cross-framework topics like AI Act and GDPR.

Builds a structured audit trail of AI-assisted legal tasks. Documents prompts, uploaded materials, outputs, human verification steps, and final reliance. Helps legal teams reconstruct workflows for supervision review and later defense without inventing facts or prejudging privilege.

Build a production-ready behavior tree runtime with Blackboard, action/condition leaves, and composites. Implement Utility AI using response curves and action evaluators. Create hybrid agents combining both for complex NPC decision-making beyond simple FSMs. Suitable for game development and AI system architecture.

Guide the configuration, connection, validation, and repair of Claude Desktop and MCP servers using Desktop Commander. Inspect and fix mcp.json and configuration files, troubleshoot connection issues, verify model/API keys, and cover local AI gateways like OpenClaw and Hermes.

Turn interpretive-ambiguity audits of legal texts into polished deliverables: multi-page websites, single-page interactive sites, Word documents, PowerPoint decks, or LaTeX/PDF. Handles structured stress-test output, semi-structured reports, or raw prose, and renders consistent scenario-based legal analysis presentations.

Adversarial stress-test for legal texts (contract, statute, regulation, or judicial opinion) that finds ambiguous seams and turns each into a concrete dispute scenario with both sides' arguments, likely outcome, and a fix. Ideal for pressure-testing, red-teaming, auditing, or identifying loopholes and drafting problems in legal documents.

This skill provides a CLI-based workflow for Android APK reverse engineering. It covers APK unpacking, Java decompilation, smali modification, repackaging, Frida dynamic hooking, and optional native .so analysis. It leverages local tools such as jadx, apktool, frida, adb, ida-reverse, and radare2. Useful for analyzing login, signature, security, root detection, or certificate verification logic in Android apps, always in an authorized context.