Developer Tools & Repos Agent Skills for Windsurf (legacy)

Designs and implements professional game user interfaces using Unity's uGUI system with responsive layouts and mobile optimization.

Review an ambiguous dirty git worktree before committing.

Write Unreal C++ that conforms to Epic's coding standard — type prefixes

Unreal Engine Control Rig skill for procedural animation, IK chains, and runtime rig modifications.

REQUIRED ENTRY POINT for ALL Unreal Engine tasks.

Unreal Engine networking specialist - Masters Actor replication, GameMode/GameState architecture, server-authoritative gameplay, network…

Unreal Engine visual pipeline specialist - Masters the Material Editor, Niagara VFX, Procedural Content Generation, and the art-to-engine…

Open-world and environment specialist - Masters UE5 World Partition, Landscape, procedural foliage, HLOD, and large-scale level streaming…

Quick-reference card for unslop modes, sub-skills, and slash commands.

Updates the current branch with the base branch (merge), resolves conflicts, validates, and pushes

Amend the latest commit message to accurately reflect the current state of the changes.

Use when user wants to update requirements-dev.in with latest PyPI versions while preserving version patterns

Update a private qm fork by merging upstream qm into it and opening a sync PR.

Use when the user wants to update, pull, or sync their WebKit repository or branch.

Audit and upgrade an existing MCP implementation to current FastMCP 3 patterns while preserving behavior and verifying protocol…

Guidelines for upgrading Expo SDK versions and fixing dependency issues

Send a change to upstream qm without leaking organization-specific context.

Choose and implement the right Circle wallet type for your application.

Deploy, import, interact with, and monitor smart contracts using Circle Smart Contract Platform APIs.

Always use this skill when integrating Base UI components `@base-ui-components/react` with Material UI `@mui/material`.

Use when designing a system whose past behaviour must be recoverable as a fact — RL training substrates, multi-agent simulations…