basilensis
69c6af2ed5
- README project context: .spaghetti file (rejected design) → Config/DefaultGame.ini [/Script/Spaghetti.SpaghettiProjectSettings] via the editor connector's Project Settings; "setup CLI is coming" dropped (CLI is reserve) in favor of roadmap-neutral wording - SKILL.md: prerequisites now describe the ini section and the personal-account fallback (the old "Agentic Directive creates .spaghetti" mechanism never shipped); tool roster renamed to the live server's (analyze_logs, tidy_assets, five free research tools incl. project-scoped temporal ones); context/billing section updated with the 402=credits vs 403=sign-in/onboarding taxonomy - plugin.json: version 0.1.1 → 0.3.1, tracking the editor connector mcp.json unchanged — URL-only config is already correct for the first-party AS (CIMD/DCR discovery, no credentials in the manifest).
112 lines
4.7 KiB
Markdown
112 lines
4.7 KiB
Markdown
---
|
|
name: ue5-unreal
|
|
description: >
|
|
Unreal Engine 5 development assistant — log analysis, asset auditing,
|
|
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 crashes, asset cleanup, engine docs, or editor
|
|
automation.
|
|
---
|
|
|
|
# UE5 Unreal AI Workbench Tools
|
|
|
|
This skill provides access to Spaghetti's Unreal AI Workbench MCP tools.
|
|
These tools run on a remote server (`mcp.spaghetti.gg`) and require
|
|
authentication via OAuth (your client handles this automatically on first
|
|
connect — a browser window opens for sign-in at spaghetti.gg).
|
|
|
|
## Prerequisites
|
|
|
|
Project context is **optional**. If present, it lives in the project's
|
|
`Config/DefaultGame.ini` under `[/Script/Spaghetti.SpaghettiProjectSettings]`
|
|
(`TeamId`, `ProjectId`, written by the Spaghetti editor connector's Project
|
|
Settings page). If the section is absent, tools run on the user's personal
|
|
account — that is a valid state, not an error. Do not hand-edit the ini while
|
|
the editor is running (the editor owns that file); context changes go through
|
|
the connector's Project Settings.
|
|
|
|
## Available tools
|
|
|
|
### Log Analyzer (`analyze_logs`)
|
|
|
|
**When to call:** The user reports a UE5 crash, pastes an output log, or
|
|
mentions a crash dump / minidump — or wants structured findings from any UE
|
|
log file.
|
|
|
|
**What it does:** Parses the UE5 Output Log and crash dumps, identifies
|
|
root-cause nodes or C++ pointers, and returns a precise fix with context from
|
|
the proprietary UE5 bug knowledge base.
|
|
|
|
**Input:** Log text (paste the Output Log contents or the relevant section).
|
|
|
|
**Safety:** Read-only analysis. Returns a diagnosis + suggested fix; does
|
|
not modify project files.
|
|
|
|
### Asset Janitor (`tidy_assets`)
|
|
|
|
**When to call:** The user asks about asset cleanup, naming conventions, unused
|
|
assets, missing LODs, or compliance reports.
|
|
|
|
**What it does:** Finds textures without LODs, detects naming-convention
|
|
violations (`T_`, `BP_`, etc.), identifies unused/0-reference assets, and
|
|
generates compliance reports.
|
|
|
|
**Input:** Optionally specify which checks to run (naming, LODs, unused).
|
|
|
|
**Safety:** Audit is read-only. If the user wants to apply fixes, use
|
|
Tool-Maker to generate a dry-run Python script first.
|
|
|
|
### Research tools (free)
|
|
|
|
**When to call:** The user asks about UE5 engine architecture, best practices,
|
|
or how specific systems work — or wants to search their project's ingested
|
|
logs and knowledge.
|
|
|
|
- **`search_docs_code`** — semantic search over curated UE engine
|
|
documentation and source code.
|
|
- **`search_patterns`** — known engine patterns and anti-patterns (verified
|
|
node setups, Blueprint conventions).
|
|
- **`search_logs_temporal`** — the project's ingested log events over time
|
|
(requires project context).
|
|
- **`query_temporal_relations`** — temporal knowledge-graph queries over the
|
|
project's entities and their relations (requires project context).
|
|
- **`investigate_incident`** — multi-source incident investigation across the
|
|
project's logs, entities, and relations (requires project context).
|
|
|
|
**Input:** Natural-language query about UE5 or the project's knowledge base.
|
|
|
|
### Tool-Maker (`make_tool`)
|
|
|
|
**When to call:** The user wants to automate a UE5 editor task (batch-rename
|
|
assets, apply materials, configure project settings, etc.).
|
|
|
|
**What it does:** Generates a safe, production-quality Python script using
|
|
`unreal.EditorAssetLibrary` API. The script runs via the UE 5.8 Python remote
|
|
execution bridge.
|
|
|
|
**Safety — three-layer model:**
|
|
1. **API allowlist:** only approved `unreal.EditorAssetLibrary` functions.
|
|
2. **Dry run:** scripts default to simulation mode (log what would happen,
|
|
don't execute destructive ops).
|
|
3. **Human approval:** before any destructive script runs, the user sees an
|
|
Approve/Reject dialog.
|
|
|
|
**Always show the generated script to the user before executing.** If the
|
|
script modifies assets, wrap in `unreal.ScopedTransaction` for undo support.
|
|
|
|
## Safety defaults
|
|
|
|
- **Never auto-delete assets** without explicit user confirmation.
|
|
- **Prefer dry-run mode** for any script that modifies the project.
|
|
- **Use ScopedTransaction** for reversible operations (enables Ctrl+Z).
|
|
- **Read the Output Log** for errors after any automated editor operation.
|
|
|
|
## Context and billing
|
|
|
|
The `Config/DefaultGame.ini` Spaghetti section (see Prerequisites) identifies
|
|
which team and project this UE5 project belongs to; billed tools draw from
|
|
that team's wallet — the research tools are free. On `402 Payment Required`,
|
|
direct the user to top up at `spaghetti.gg/billing`. A `403` with a portal
|
|
URL means the account needs to sign in or finish onboarding — open the URL;
|
|
retrying will not help.
|