ue5-auto-assistant
starsforks
How to install ue5-auto-assistant?
teixasalone/unrealengine5-skills/ue5-auto-assistant
$npx -y skills add teixasalone/UnrealEngine5-Skills --skill ue5-auto-assistantUE5.6/UE5.7 automatic assistant entry for beginners. Use when users ask Unreal questions without naming a specific skill. Auto-route to the most precise UE5 skill and recommend dedicated MCP tools.
SKILL.md
| 1 | # Quick Start |
| 2 | - Treat this as the default entry for UE5.6/UE5.7 requests. |
| 3 | - Parse user intent first without requiring module names. |
| 4 | - Route to `ue5-module-router` when module-level precision is needed. |
| 5 | |
| 6 | # Workflow |
| 7 | - Detect request type: Blueprint, C++, UI, save/load, networking, world interaction, debugging, performance, packaging. |
| 8 | - If module names appear, delegate routing to `ue5-module-router`. |
| 9 | - If module names do not appear, route by intent: |
| 10 | - Blueprint -> `ue5-blueprint-workflow` |
| 11 | - C++ gameplay -> `ue5-cpp-gameplay` |
| 12 | - UI/UMG/Slate -> `ue5-ui-umg-slate` |
| 13 | - save/load/replication -> `ue5-save-load-replication` |
| 14 | - pickup/spawner/world interaction -> `ue5-world-interaction` |
| 15 | - perf/packaging -> `ue5-performance-packaging` |
| 16 | - debugging/validation -> `ue5-debug-validation` |
| 17 | - architecture/refactor -> `ue5-architecture` |
| 18 | - Return one primary skill and optional secondary skill for cross-domain requests. |
| 19 | - Return routing payload fields: |
| 20 | - `primary_skill` |
| 21 | - `secondary_skill` |
| 22 | - `recommended_mcp_tools[]` |
| 23 | - `route_confidence` |
| 24 | - `route_reason` |
| 25 | |
| 26 | # Natural Language To Skill And Tools |
| 27 | - Blueprint requests: |
| 28 | - target skill: `ue5-blueprint-workflow` |
| 29 | - recommended tools: `blueprint_feature_build`, `blueprint_modify`, `blueprint_query` |
| 30 | - C++ gameplay/system requests: |
| 31 | - target skill: `ue5-cpp-gameplay` |
| 32 | - recommended tools: `blueprint_query`, `asset_search`, `get_output_log` |
| 33 | - UI/UMG/Slate requests: |
| 34 | - target skill: `ue5-ui-umg-slate` |
| 35 | - recommended tools: `blueprint_query`, `blueprint_modify`, `capture_viewport` |
| 36 | - Save/load/replication requests: |
| 37 | - target skill: `ue5-save-load-replication` |
| 38 | - recommended tools: `character_data`, `blueprint_query`, `get_output_log` |
| 39 | - World interaction/pickup/spawner requests: |
| 40 | - target skill: `ue5-world-interaction` |
| 41 | - recommended tools: `spawn_actor`, `get_level_actors`, `set_property`, `move_actor` |
| 42 | - Performance/packaging requests: |
| 43 | - target skill: `ue5-performance-packaging` |
| 44 | - recommended tools: `run_console_command`, `get_output_log`, `capture_viewport`, `open_level` |
| 45 | - Debug/validation requests: |
| 46 | - target skill: `ue5-debug-validation` |
| 47 | - recommended tools: `get_output_log`, `asset_search`, `blueprint_query`, `task_list` |
| 48 | - Architecture/module-boundary requests: |
| 49 | - target skill: `ue5-architecture` |
| 50 | - recommended tools: `asset_search`, `asset_dependencies`, `asset_referencers` |
| 51 | |
| 52 | # Constraints |
| 53 | - Do not require users to know skill names. |
| 54 | - Prefer deterministic routing with explicit reason. |
| 55 | - Keep fallback behavior explicit when confidence is low. |
| 56 | - Prefer dedicated MCP tools before `execute_script`. |
| 57 | |
| 58 | # Failure Handling |
| 59 | - If intent is ambiguous, return top 2 route candidates and ask one short clarification. |
| 60 | - If request spans many systems, split into staged route steps. |
| 61 | - Clarification template: |
| 62 | - `Quick check: do you want A(<candidate_1>) or B(<candidate_2>)?` |
| 63 | - ask once, then continue. |
| 64 | |
| 65 | # Escalation |
| 66 | - Escalate when query depends on plugin/engine source outside indexed scope. |
| 67 | - Escalate when org-level coding standards are required but not available in repo. |
People who liked this also viewed
6 picksType
- hyperframes-cliUse the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, SkillsJul 2026
- request-refactor-planSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- analyze-projectRigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrSkillsMay 2026
- explore-codeRigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated braSkillsMay 2026
- ubiquitous-languageSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- scaffold-exercisesSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
