From code-analysis-unreal
UE5 post-hook for code-analysis:analyze-file. Appends qualitative audit (macros, GC safety, null safety, Blueprint boundary, performance) to mirror, then triggers tick-audit and replication-audit skills based on graph context.
How this skill is triggered — by the user, by Claude, or both
Slash command
/code-analysis-unreal:after-analyze-filesonnetThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Post-hook invoked after `code-analysis:analyze-file` completes when the UE5 strategy is active. Runs **after** `code-analysis-cpp:after-analyze-file` per the hook's ORDERING directive.
Post-hook invoked after code-analysis:analyze-file completes when the UE5 strategy is active. Runs after code-analysis-cpp:after-analyze-file per the hook's ORDERING directive.
Append a ## UE5 Qualitative Audit section with:
TObjectPtr<> or UPROPERTY()-tracked). Dangling UObject references.Use graph_context.callers to verify:
Tick() really runs every frame (who ticks this actor? is it ticking?) — if yes, trigger code-analysis-unreal:tick-audit for this file.Replicated / RPC usage: if ReplicatedUsing handlers exist, trigger code-analysis-unreal:replication-audit.After the qualitative audit:
code-analysis-unreal:tick-audit for this file.Replicated, ReplicatedUsing, or any method has Server/Client/NetMulticast specifier, invoke code-analysis-unreal:replication-audit.Append to mirror. Do not overwrite.
npx claudepluginhub juyeongyi/jylee_claude_marketplace --plugin code-analysis-unrealGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.
Dispatches multiple subagents concurrently for independent tasks without shared state. Use when facing 2+ unrelated failures or subsystems that can be investigated in parallel.