unreal-engine
Comprehensive Unreal Engine C++ and Blueprint development assistant with deep project structure understanding. Use when helping with Unreal Engine projects, including: C++ gameplay programming, Blueprint development, input system configuration (Enhanced Input), Gameplay Ability System (GAS), project structure navigation, asset discovery and referencing, plugin integration (experimental/beta), API lookups for underdocumented features, and debugging. Triggers on any Unreal Engine development question, especially when working within a .uproject directory.
What this skill does
# Unreal Engine Development Assistant
## Core Philosophy: Zero Assumptions
**CRITICAL**: Never make assumptions about the user's project. Every Unreal project is unique in structure, assets, and configuration. Always verify before suggesting code or assets.
## Pre-Flight Discovery Protocol
When a user asks for Unreal Engine help, ALWAYS execute this discovery sequence FIRST:
### 1. Locate the .uproject File
```bash
find . -maxdepth 2 -name "*.uproject" -type f
```
**If found**: Read it to extract:
- Engine version from `"EngineAssociation"` field
- Project name from filename
- Enabled plugins from `"Plugins"` array
- Module dependencies from `"Modules"` array
**Example .uproject structure**:
```json
{
"FileVersion": 3,
"EngineAssociation": "5.7", // ← Engine version
"Category": "",
"Description": "",
"Modules": [
{
"Name": "ProjectName", // ← Module name
"Type": "Runtime",
"LoadingPhase": "Default",
"AdditionalDependencies": ["Engine", "GameplayAbilities"]
}
],
"Plugins": [
{"Name": "EnhancedInput", "Enabled": true},
{"Name": "GameplayAbilities", "Enabled": true}
]
}
```
### 2. Map the Project Structure
**Standard Unreal project layout**:
```
ProjectRoot/
├── ProjectName.uproject ← Project file
├── Source/ ← C++ source code
│ ├── ProjectName/ ← Main module
│ │ ├── Public/ ← Header files (.h)
│ │ ├── Private/ ← Implementation files (.cpp)
│ │ └── ProjectName.Build.cs ← Build configuration
│ └── ProjectNameEditor/ (optional) ← Editor-only code
├── Content/ ← All assets (.uasset files)
│ ├── Blueprints/ ← Common location for BPs
│ ├── Input/ ← Input Actions & Mapping Contexts
│ ├── Characters/ ← Character assets
│ ├── UI/ ← UMG widgets
│ └── [project-specific folders]
├── Config/ ← Configuration .ini files
│ ├── DefaultEngine.ini ← Engine settings
│ ├── DefaultInput.ini ← Legacy input config
│ └── DefaultGame.ini ← Game-specific config
├── Plugins/ ← Project plugins
├── Intermediate/ ← Build artifacts (ignore)
├── Saved/ ← Logs, configs (ignore)
└── Binaries/ ← Compiled executables (ignore)
```
Execute these discovery commands:
```bash
# Find C++ classes
view Source/*/Public
view Source/*/Private
# Discover Content assets (especially Input Actions)
find Content -type f -name "*.uasset" | head -50
# For Input Actions specifically
find Content -type f -name "*IA_*" -o -name "*InputAction*"
# For Input Mapping Contexts
find Content -type f -name "*IMC_*" -o -name "*InputMappingContext*"
# Find Blueprint classes
find Content -type f -name "BP_*.uasset"
```
### 3. Understand Existing Code
**Before suggesting ANY code**:
- Read existing character/controller classes to understand patterns
- Check what components are already added
- Identify naming conventions (e.g., `IA_` prefix for Input Actions)
- Look for existing helper classes or base classes
```bash
# Example: Find character class
find Source -name "*Character.h" -o -name "*Character.cpp"
```
## Input System Handling
### Enhanced Input System (UE5+)
**NEVER assume input action names**. Always discover them first:
```bash
# Find Input Actions in Content
find Content -type f \( -name "IA_*.uasset" -o -name "*InputAction*.uasset" \)
# Find Input Mapping Contexts
find Content -type f \( -name "IMC_*.uasset" -o -name "*MappingContext*.uasset" \)
```
**Common Input Action patterns**:
- `IA_Move` or `IA_Movement` (Axis2D)
- `IA_Look` (Axis2D)
- `IA_Jump` (Boolean)
- `IA_Interact` (Boolean)
But ALWAYS verify - projects use different naming conventions.
### Binding Input Actions in C++
**Template for Enhanced Input binding**:
```cpp
#include "EnhancedInputComponent.h"
#include "EnhancedInputSubsystems.h"
#include "InputAction.h"
// In SetupPlayerInputComponent
void AMyCharacter::SetupPlayerInputComponent(UInputComponent* PlayerInputComponent)
{
Super::SetupPlayerInputComponent(PlayerInputComponent);
// Cast to Enhanced Input Component
if (UEnhancedInputComponent* EnhancedInput = Cast<UEnhancedInputComponent>(PlayerInputComponent))
{
// Bind actions - VERIFY THESE ASSET PATHS EXIST
EnhancedInput->BindAction(MoveAction, ETriggerEvent::Triggered, this, &AMyCharacter::Move);
EnhancedInput->BindAction(LookAction, ETriggerEvent::Triggered, this, &AMyCharacter::Look);
EnhancedInput->BindAction(JumpAction, ETriggerEvent::Started, this, &AMyCharacter::Jump);
}
}
```
**Header declarations**:
```cpp
UPROPERTY(EditAnywhere, BlueprintReadOnly, Category = "Input")
UInputAction* MoveAction;
UPROPERTY(EditAnywhere, BlueprintReadOnly, Category = "Input")
UInputAction* LookAction;
```
### .uasset Files and Blueprint Reading
**.uasset files** are binary and mostly unreadable in text editors, BUT:
- Some metadata is visible (asset names, paths, GUIDs)
- Property names and string values may be readable
- Useful for discovering asset references and dependencies
- **Do NOT rely on .uasset contents for implementation details**
**Better approach**: Use `find` to discover assets, then ask user to verify or describe them.
## Gameplay Ability System (GAS)
When working with GAS projects (check `.uproject` for `"GameplayAbilities"` plugin):
### Critical GAS Setup Requirements
**1. Build.cs dependencies**:
```csharp
PublicDependencyModuleNames.AddRange(new string[] {
"Core", "CoreUObject", "Engine", "InputCore",
"GameplayAbilities",
"GameplayTags",
"GameplayTasks"
});
```
**2. Ability System Component placement**:
- **For single-player or listen-server**: Can be on Character
- **For dedicated server**: Usually on PlayerState (for player-owned actors)
- **For AI/NPCs**: Can be on Character or custom actor
**3. Key GAS classes**:
- `UAbilitySystemComponent` - The core component
- `UGameplayAbility` - Base class for abilities
- `UAttributeSet` - Holds gameplay attributes (health, stamina, etc.)
- `UGameplayEffect` - Modifies attributes
- `FGameplayTag` - Tags for ability system
### Common GAS Patterns
**Granting abilities**:
```cpp
// In C++
AbilitySystemComponent->GiveAbility(
FGameplayAbilitySpec(AbilityClass, 1, INDEX_NONE, this)
);
```
**Activating abilities**:
```cpp
// By class
AbilitySystemComponent->TryActivateAbilityByClass(AbilityClass);
// By tag
FGameplayTagContainer TagContainer;
TagContainer.AddTag(FGameplayTag::RequestGameplayTag(FName("Ability.Dash")));
AbilitySystemComponent->TryActivateAbilitiesByTag(TagContainer);
```
## Plugin-Specific Guidance
### Unknown or Experimental Plugins
**When encountering unfamiliar plugins** (e.g., Mutable, MutableClothing, RelativeIKOp):
1. **Search for official documentation**:
```
web_search: "Unreal Engine [PluginName] documentation API"
web_search: "Unreal Engine [PluginName] usage examples"
```
2. **Check source code** (if accessible):
```bash
# Engine plugins location (if user has source build)
find /path/to/UE5/Engine/Plugins -name "PluginName"
```
3. **Be transparent**: "This plugin is experimental/underdocumented. Let me search for the latest information..."
## API Knowledge Gaps
**When uncertain about API usage**:
1. **Search Epic's documentation**:
```
web_search: "Unreal Engine [ClassName] API [EngineVersion]"
```
2. **Search community resources**:
```
web_search: "Unreal Engine [feature] example code C++"
```
3. **Check Epic Developer Community forums**
4. **Look for example projects** (Lyra, Valley of the Ancient, ActionRPG)
## Common Pitfalls to Avoid
### ❌ WRONG: Making Assumptions
```cpp
// DON'T assume this exists
EnhancedInput->BindAction(IA_Jump, ETriggerEvent::Started, this, &AMyCharacter::Jump);
```
### ✓ CORRECT: Discovery First
```bash
# Find what Input Actions actually exist
find Content -name "*IA_*"
# Then ask user oRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.