Skill UI

This skill provides an end-to-end wizard for creating a Dataverse Mobile Offline Profile, enabling Power Apps to function in an offline environment. It meticulously designs per-table row scopes, manages relationships, and defines column synchronization frequency through a multi-gate approval flow. It creates necessary Dataverse entities and configures the full app-level offline metadata, ensuring seamless offline data access for native mobile clients (iOS/Android).

This is an internal, deterministic consent gate used in the meta-short-drama workflow. It normalizes user-provided draft review comments and post-revision confirmation replies. Its primary function is to enforce a secure, bounded decision process, requiring explicit approval at every stage before any external image or video generation is authorized, thus preventing ambiguous inputs from proceeding.

Create, triage, and approve GitHub issues from repository evidence. Draft issue bodies using YAML issue forms, search duplicates, and follow repository policy. Handles bug reports, feature requests, and issue approval workflows with strict validation rules.

This skill enforces strict communication protocols for AI agents interacting in shared channels with external parties. It ensures agents speak only when explicitly addressed, prevents internal context leakage, and routes sensitive content to draft-only approval. Ideal for group chats, DMs, and business partnerships where privacy and security are critical.

Defines an operator approval contract for agent-drafted outbound messages: hashed draft filing, epoch-keyed decisions, approval snapshots, durable delivery claims and receipts, plus a pre-draft baseline gate. Use when a human must approve, reject, or steer each send before it leaves.

Configure a PreToolUse security gate for Google Antigravity CLI (agy) enabling safe unattended execution with layered policy controls including hard deny, fast allow, LLM classifier fallback, and single-use token approvals, avoiding dangerous permission bypass.

This skill structures a highly controlled, bounded development life cycle for AI agents. It mandates a structured three-phase workflow: Planning (Spec), Implementation (Build), and Verification (Review). It is essential for building complex features from scratch, especially when dealing with ambiguous requirements, high risk, or needing explicit human approval gates to ensure the resulting code meets all defined specifications.

Researches uncertain questions through user-approved web search or ChatGPT consultation, then presents sourced options and waits for explicit approval before writing code. Redacts sensitive data and never shares context, files, or browser state without consent.

Official Beatra AI agent package for paid text-to-video, image-to-video generation, and video editing/extension services. Produces short AI video clips on hosted Beatra service with first/last-frame interpolation and reference-guided generation capabilities. Requires explicit user approval and accepts paid processing on third-party hosted infrastructure.

Configure CircleCI 2.1 workflows, orbs, executors, caching, workspaces and parallelism for building, testing and deploying applications. Covers approvals, scheduled runs, branch filtering and secrets contexts.

Runs the Hermes Agent CLI in one-shot mode (hermes -z) to delegate bounded local coding tasks from Code Mate. Covers availability checks, timeouts, exit codes, authentication limits and YOLO tool-approval safety constraints.

Use DeepAPI for supported web scraping, research, and email workflows. Requires explicit credentials and user approval before executing commands or remote actions.