菜单
Run ProjectTwelve Unity batch validation and EditMode/PlayMode test suites via Unity 6000.5.1f1. Use when the user or ticket asks to run Unity tests, EditMode fixtures, batchmode validation, or verify test results from TestResults/*.xml.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Log agent sessions, consolidate project memory (dream), promote reviewed memory, and load context for new chats. Use when ending a session, improving cross-session recall, or when the user mentions agent memory, dream, log-session, or memory.md.
Wiki tickets under docs/wiki/tickets/ are the canonical task queue, each linked to a GitHub issue. Use when picking work, claiming an issue, or preparing PR references.
Recommend the next open wiki ticket to work on, ranked by phase then priority, without claiming or mutating anything. Use when the user asks "what's next", to pick the next task, or to start work without a specific ticket in hand.
Sync project-twelve with the Assets/_Licensed submodule via fetch_remotes.py, git hooks, and /fetch-remotes. Use at session start, before picking backlog work, or when the user asks to sync repos or get latest.
Use when the user asks to commit and push, publish, ship, or prepare a release commit. Guides staging only intended changes, writing a Conventional Commit, committing, and pushing to origin after verifying status and diff.
Apply Karpathy's anti-pattern checklist before/during non-trivial coding — surface assumptions, resist overcomplication, keep diffs surgical, frame work as verifiable goals. Use on ambiguous or multi-step tasks, or when the user asks for a "Karpathy pass".
| name | unity-tests |
| description | Run ProjectTwelve Unity batch validation and EditMode/PlayMode test suites via Unity 6000.5.1f1. Use when the user or ticket asks to run Unity tests, EditMode fixtures, batchmode validation, or verify test results from TestResults/*.xml. |
Editor: Unity 6000.5.1f1. Project root = repo clone. Deterministic runner:
scripts/run_unity_tests.py.
/test-and-fix asks for EditMode or PlayMode.Assets/Scripts/ or Assets/Tests/.TestResults/*.xml.python scripts/run_unity_tests.py validate
python scripts/run_unity_tests.py editmode
python scripts/run_unity_tests.py editmode --filter "SandboxNavPathfinderTests|SandboxSpawnRulesTests"
python scripts/run_unity_tests.py playmode
python scripts/run_unity_tests.py editmode --parity # also npm test tile-viz + world-viz
python scripts/run_unity_tests.py editmode --parity --parity-print-only
Requires UNITY_EDITOR (or UNITY_ROOT) in the environment or gitignored .env. The harness:
TestResults/ + Logs/-quit with -runTests on Windows (Unity 6 batchmode quirk)total/passed/failed/result and failed case names from NUnit XMLAgent terminals: set block_until_ms ≥ 600000 for full EditMode.
If the harness fails, diagnose from the printed failed names and the log path it reports
(Logs/unity-*.log). Common blockers: Editor locking the project, missing UNITY_EDITOR,
Newtonsoft asmdef refs, leftover -quit on Windows -runTests.
Do not re-derive Unity flags by hand — re-run or extend the harness.
Never verify Runtime MCP (or other managed game assemblies) by launching pwsh /
powershell that [System.Reflection.Assembly]::LoadFrom(...) Unity/Temp\bin\Debug
DLLs and invokes types via reflection.
Windows Security commonly classifies that pattern as Trojan:Win32/Steanoz.Z!MTB (false
positive on agent-generated one-liners). Quarantine does not mean the project was infected.
Use instead:
python scripts/run_unity_tests.py editmode --filter RuntimeMcpOverlayToolsTests
# or the matching *Mcp* EditMode filter for the tools under change
If Unity is unavailable, report that blocker — do not invent an offline LoadFrom harness.
AGENTS.md test vocabularydocs/wiki/quality-gates.md.agent/SKILL_COMPILATION.md