skills/ue5-unreal/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: ue5-unreal
 description: >
-  Unreal Engine 5 development assistant — log analysis, asset auditing,
+  Unreal Engine 5 development assistant — crash analysis, asset auditing,
-  engine-docs research, and Python script generation via Spaghetti Unreal AI
+  knowledge-base search, and Python script generation via Spaghetti Unreal AI
   Workbench. Call these tools when the user is working in a UE5 project and
-  needs expert help with log errors or crashes, asset cleanup, engine docs,
+  needs expert help with crashes, asset cleanup, engine docs, or editor
-  or editor automation.
+  automation.
 ---
 
 # UE5 Unreal AI Workbench Tools
@@ -17,80 +17,73 @@ connect — a browser window opens for sign-in at spaghetti.gg).
 
 ## Prerequisites
 
-The user must have signed in at [spaghetti.gg](https://spaghetti.gg) at least
+Your UE5 project must have a `.spaghetti` file at its root containing
-once (accounts and welcome credits are created on first sign-in).
+`team_id` and `project_id`. If no `.spaghetti` exists, the first tool call
+returns an Agentic Directive instructing you to create one. Follow it.
 
-A `.spaghetti` file at the UE5 project root (`team_id`, `project_id`) is
+## Available tools (Phase 1 — MVP)
-optional — without it, calls bill the user's personal wallet and everything
-works except the two project-scoped research tools (`search_logs_temporal`,
-`investigate_incident`). If you see a "no user account exists" error, point
-the user at the portal sign-in; if you see "not a member of team", the
-`.spaghetti`/headers point at the wrong team.
 
-## Available tools
+### Crash Investigator (`spaghetti/analyze_crash`)
 
-### Log Analyzer (`spaghetti/analyze_logs`)
+**When to call:** The user reports a UE5 crash, paste an output log, or
+mentions a crash dump / minidump.
 
-**When to call:** The user reports errors or a crash in their UE5 project and
+**What it does:** Parses the UE5 Output Log and crash dumps, identifies
-has a log file (for example `Saved/Logs/<Project>.log`, or a crash log).
+root-cause nodes or C++ pointers, and returns a precise fix with context from
+the proprietary UE5 bug knowledge base.
 
-**What it does:** Full-log analysis — structured findings with severity and
+**Input:** Crash log text (paste the Output Log contents or the relevant
-evidence, crash triage naming the suspect Blueprint, and statistics. Uploads
+section).
-are session-based; large logs never flow through chat.
 
-**Input:** A local log path (`logPath`) to start a session, or pasted log
+**Safety:** Read-only analysis. Returns a diagnosis + suggested fix; does
-text (`logText`) as the fallback path.
+not modify project files.
 
-**Cost:** 5 credits per session, billed only when analysis runs — empty logs
+### Asset Janitor (`spaghetti/audit_assets`)
-or logs with no Error/Fatal entries are free. Retries never bill twice.
 
-**Safety:** Read-only analysis. Does not modify project files.
+**When to call:** The user asks about asset cleanup, naming conventions, unused
+assets, missing LODs, or compliance reports.
 
-### Asset Janitor (`spaghetti/tidy_assets`)
+**What it does:** Finds textures without LODs, detects naming-convention
+violations (`T_`, `BP_`, etc.), identifies unused/0-reference assets, and
+generates compliance reports.
 
-**When to call:** The user asks about asset cleanup, naming conventions,
+**Input:** Optionally specify which checks to run (naming, LODs, unused).
-unused assets, missing LODs, or compliance reports.
-
-**What it does:** Audits a project asset inventory — unused assets with
-reclaimable sizes, redirectors, naming-convention violations, LOD problems —
-and returns a prioritized report plus a downloadable CSV.
-
-**Input:** An inventory JSONL path. With the UE connector plugin installed,
-call its `export_asset_inventory` tool in the editor first (it writes
-`Saved/spaghetti_inventory.jsonl`); without it, a short Python-console script
-produces the same file.
-
-**Cost:** 3 credits per session, billed only when a report is produced.
 
 **Safety:** Audit is read-only. If the user wants to apply fixes, use
-Tool-Maker to generate a dry-run script first.
+Tool-Maker to generate a dry-run Python script first.
 
-### Research tools (free)
+### Smart Librarian (`spaghetti/search_kb`)
 
-- `search_docs_code` — hybrid search over curated UE engine documentation.
+**When to call:** The user asks about UE5 engine architecture, best practices,
-- `search_patterns` — recommended engine approaches vs anti-patterns for a described intent.
+or how specific systems work. Also for snippet search (verified node setups,
-- `search_logs_temporal` — time/severity/subsystem-filtered search over logs previously ingested by `analyze_logs`. Requires project context.
+Blueprint patterns).
-- `query_temporal_relations` — entity-relation traversal over ingested logs (up to 3 hops, optionally as of a point in time).
+
-- `investigate_incident` — bounded investigation combining logs, relations, docs, and patterns. Requires project context.
+**What it does:** Semantic search over two knowledge bases:
+- **Team KB:** your project's private RAG index (studio docs, past bug
+  resolutions, conventions).
+- **UE5 Engine Graph:** GraphRAG over the public UE 5.8 source for multi-hop
+  reasoning about engine architecture.
+
+**Input:** Natural-language query about UE5 or your project's knowledge base.
 
 ### Tool-Maker (`spaghetti/make_tool`)
 
 **When to call:** The user wants to automate a UE5 editor task (batch-rename
-assets, apply settings, generate reports, etc.).
+assets, apply materials, configure project settings, etc.).
 
-**What it does:** Generates an editor-automation Python script from a
+**What it does:** Generates a safe, production-quality Python script using
-natural-language description of the task.
+`unreal.EditorAssetLibrary` API. The script runs via the UE 5.8 Python remote
+execution bridge.
 
 **Safety — three-layer model:**
-1. **API allowlist:** only approved editor APIs.
+1. **API allowlist:** only approved `unreal.EditorAssetLibrary` functions.
-2. **Dry run:** delivered scripts are simulation transforms — destructive
+2. **Dry run:** scripts default to simulation mode (log what would happen,
-   operations commented out, reversible operations wrapped in
+   don't execute destructive ops).
-   `unreal.ScopedTransaction` for undo support.
+3. **Human approval:** before any destructive script runs, the user sees an
-3. **Human approval:** the user Approves/Declines via the client's approval
+   Approve/Reject dialog.
-   flow. Billed 10 credits only on approval; blocked, declined, and
-   cancelled runs are free.
 
-**Always show the generated script to the user before executing.**
+**Always show the generated script to the user before executing.** If the
+script modifies assets, wrap in `unreal.ScopedTransaction` for undo support.
 
 ## Safety defaults
 
@@ -99,9 +92,9 @@ natural-language description of the task.
 - **Use ScopedTransaction** for reversible operations (enables Ctrl+Z).
 - **Read the Output Log** for errors after any automated editor operation.
 
-## Billing
+## Context
 
-Tool calls bill the user's personal wallet, or the team wallet when team
+The `.spaghetti` file at the project root identifies which team and project
-context is set. If you see `402 Payment Required` / "Insufficient credits",
+this UE5 project belongs to. All tool calls are billed to the team's Spaghetti
-call the free `topup` tool to create a checkout link, or direct the user to
+wallet. If you see a `402 Payment Required`, direct the user to
 `spaghetti.gg/billing` to top up.