mcpField
U
ue5-module-router

ue5-module-router

github.com/unrealxuAgent workflows53345 installsUpdated 9w ago
Repository

About ue5-module-router

An Agent routing skill for Unreal Engine 5 development requests. It matches explicit module names first, then uses aliases and layer context, and returns recommended skills, tools, and routing rationale.

Key features

  1. 01Exact module-name routing
  2. 02Alias and layer-context matching
  3. 03Prioritization of multiple matches
  4. 04Confidence and rationale in output
  5. 05Candidate suggestions for low confidence

Use cases

  1. 01Find a development skill for modules such as RenderCore
  2. 02Route requests spanning concerns to primary and secondary skills
  3. 03Choose a nearby capability when no module is recognized

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/unrealxu/unrealengine5-skills --skill ue5-module-router

After installing, type/ue5-module-routerin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
references/
routing-policy.md
ue5-module-routing-table-draft.deprecated.csv
ue5-module-routing-table-final.csv

Details

From the project README

Quick Start

  • Extract explicit module names from user prompt first.
  • If module is found, route by exact module mapping before keyword heuristics.
  • If module is not found, use aliases and layer context.

Workflow

  • Parse prompt for module candidates (for example RenderCore, AIModule, AssetRegistry).
  • Lookup module in ue5-module-routing-table-final.csv.
  • If multiple hits, prioritize:
    1. exact module name match
    2. Build.cs path similarity
    3. alias overlap with prompt keywords
  • Return routing payload:
    • primary_skill
    • secondary_skill
    • recommended_mcp_tools[]
    • route_confidence
    • route_reason
  • Use secondary_skill when request spans multiple concerns in one module context.

Constraints

  • Prefer deterministic routing; avoid broad guesses if exact module match exists.
  • Keep one primary target skill unless user explicitly asks cross-module analysis.
  • If module maps to ue5-architecture, answer module-boundary/design first.
  • Prefer dedicated MCP tools before execute_script.

Failure Handling

  • If no module is recognized, fallback to closest capability skill and state reason.
  • If confidence is low, provide top 2 candidates and request module confirmation.
  • Use execute_script only when dedicated MCP tools are insufficient and explain why.
  • If mapping is outdated, regenerate from ue5-architecture/scripts/generate_module_index_v2.py.

Escalation

  • Escalate for large cross-cutting refactors across many modules.
  • Escalate when requested module belongs to plugin source outside indexed scope.

Comments

Markdown supported