mcpField
U
ue5-auto-assistant

ue5-auto-assistant

github.com/unrealxuAgent workflows53347 installsUpdated 9w ago
Repository

About ue5-auto-assistant

ue5-auto-assistant routes UE5.6–UE5.8 requests to focused skills based on intent or module names. It is for users seeking the right workflow for Blueprint, C++, UI, performance, debugging, and other UE5 tasks.

Key features

  1. 01Intent-based UE5 request routing
  2. 02Routes across Blueprint, C++, UI, and other domains
  3. 03Optional module-level routing
  4. 04Returns primary and secondary skills
  5. 05Provides recommended MCP tools and routing rationale

Use cases

  1. 01Finding a skill for a UE5 task without knowing skill names
  2. 02Routing requests that span multiple UE5 domains
  3. 03Selecting tools for a specific UE5 workflow

MCP support

It recommends MCP tools for each request category and includes them in its routing payload.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/unrealxu/unrealengine5-skills --skill ue5-auto-assistant

After installing, type/ue5-auto-assistantin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
references/
beginner-smoke-prompts.md
mcp-skill-mapping.md
natural-language-triggers.md

Details

From the project README

Quick Start

  • Treat this as the default entry for UE5.6-UE5.8 requests.
  • Parse user intent first without requiring module names.
  • Route to ue5-module-router when module-level precision is needed.

Workflow

  • Detect request type: Blueprint, C++, UI, save/load, networking, world interaction, PCG/procedural generation, debugging, performance, packaging.
  • If module names appear, delegate routing to ue5-module-router.
  • If module names do not appear, route by intent:
    • Blueprint -> ue5-blueprint-workflow
    • C++ gameplay -> ue5-cpp-gameplay
    • UI/UMG/Slate -> ue5-ui-umg-slate
    • save/load/replication -> ue5-save-load-replication
    • pickup/spawner/world interaction -> ue5-world-interaction
    • PCG/procedural building/shape grammar -> ue5-pcg-building
    • perf/packaging -> ue5-performance-packaging
    • debugging/validation -> ue5-debug-validation
    • architecture/refactor -> ue5-architecture
  • Return one primary skill and optional secondary skill for cross-domain requests.
  • Return routing payload fields:
    • primary_skill
    • secondary_skill
    • recommended_mcp_tools[]
    • route_confidence
    • route_reason

Natural Language To Skill And Tools

  • Blueprint requests:
    • target skill: ue5-blueprint-workflow
    • recommended tools: blueprint_feature_build, blueprint_modify, blueprint_query
  • C++ gameplay/system requests:
    • target skill: ue5-cpp-gameplay
    • recommended tools: blueprint_query, asset_search, get_output_log
  • UI/UMG/Slate requests:
    • target skill: ue5-ui-umg-slate
    • recommended tools: blueprint_query, blueprint_modify, capture_viewport
  • Save/load/replication requests:
    • target skill: ue5-save-load-replication
    • recommended tools: character_data, blueprint_query, get_output_log
  • World interaction/pickup/spawner requests:
    • target skill: ue5-world-interaction
    • recommended tools: spawn_actor, get_level_actors, set_property, move_actor
  • PCG/procedural building requests:
    • target skill: ue5-pcg-building
    • recommended tools: asset_search, blueprint_query, get_output_log, capture_viewport
  • Performance/packaging requests:
    • target skill: ue5-performance-packaging
    • recommended tools: run_console_command, get_output_log, capture_viewport, open_level
  • Debug/validation requests:
    • target skill: ue5-debug-validation
    • recommended tools: get_output_log, asset_search, blueprint_query, task_list
  • Architecture/module-boundary requests:
    • target skill: ue5-architecture
    • recommended tools: asset_search, asset_dependencies, asset_referencers

Constraints

  • Do not require users to know skill names.
  • Prefer deterministic routing with explicit reason.
  • Keep fallback behavior explicit when confidence is low.
  • Prefer dedicated MCP tools before execute_script.

Failure Handling

  • If intent is ambiguous, return top 2 route candidates and ask one short clarification.
  • If request spans many systems, split into staged route steps.
  • Clarification template:
    • Quick check: do you want A(<candidate_1>) or B(<candidate_2>)?
    • ask once, then continue.

Escalation

  • Escalate when query depends on plugin/engine source outside indexed scope.
  • Escalate when org-level coding standards are required but not available in repo.

Comments

Markdown supported