菜单
Use for any agent working on the ue-claude-scaffold codebase. Defines where things live, how to build/test/typecheck, and what tools are available. Non-container interactive execution.
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
Use for any container agent that posts progress to the coordination server's message board. Defines the curl format, channels, message types, payload conventions, posting responsibilities, and verbosity levels.
Use when a review agent must produce structured output. Defines the BLOCKING/NOTE/Summary/Verdict template, the two-tier confidence rubric, and the JSON shadow block consumed by POST /tasks/:id/reviews. Compose with review-process and a domain skill.
Use when an agent evaluates the output of other agents or decides whether work meets the bar. Enforces rigorous quality standards — reject shortcuts, demand evidence, no rubber-stamping.
Use when an agent is the FSM arbitrator on a durable task. Defines the two triggers, the three ruling types, the POST contract, the addendum-file rules for contradiction rulings, and the 409 handling. Project-agnostic.
Tells container agents where the Unreal Engine source tree is mounted inside the container, so they can grep and read engine headers to verify API signatures and class hierarchies.
Use when an agent must review code changes. Defines the universal review sequence — identify files, read context, check against domain criteria, score, filter. Compose with a domain skill and review-output-schema.
| name | scaffold-environment |
| description | Use for any agent working on the ue-claude-scaffold codebase. Defines where things live, how to build/test/typecheck, and what tools are available. Non-container interactive execution. |
| axis | environment |
You are working on ue-claude-scaffold — a scaffold for running autonomous Claude Code agents against Unreal Engine projects.
ue-claude-scaffold/
server/ ← Fastify + TypeScript coordination server
dashboard/ ← React + Vite + Mantine monitoring SPA
container/ ← Docker entrypoint, hooks, compose config, standing instructions
agents/ ← Markdown agent definitions (YAML frontmatter + system prompt)
skills/ ← Markdown SKILL.md files (YAML frontmatter + skill content)
plans/ ← Plan documents and design analysis
issues/ ← Issue markdown files with frontmatter
scripts/ ← Utility shell scripts
launch.sh ← Launch container agent
setup.sh ← First-time setup
status.sh ← Monitor agent progress
stop.sh ← Stop running agents
server/)cd server
npm run typecheck # Type-check without emitting
npm run build # TypeScript compile to dist/
npm test # Run all tests (Node.js built-in test runner via tsx)
npm run test:coverage # Tests with c8 coverage
npx tsx --test src/routes/<file>.test.ts # Run a single test file
npm run dev # Start dev server with hot reload
dashboard/)cd dashboard
npm run build # Type-check + production build
npm run dev # Start Vite dev server
npm run preview # Preview production build
bash -n launch.sh # Validate syntax (no execution)
bash -n setup.sh
bash -n status.sh
bash -n stop.sh
.ts imports use .js extensions (import { foo } from './bar.js')server/src/schema/tables.ts, indexed by server/src/schema/index.ts. Migrations live in server/drizzle/ and apply via npm run db:migrate (which runs src/migrate.ts). PGlite for dev and tests; node-postgres for prod via DATABASE_URL.scaffold.config.json (structural, not committed) + .env (secrets, not committed). Examples provided as *.example.* files.package.json and tsconfig.json in the subtree you're working in for the authoritative test runner, scripts, and helpers — do not assume a framework.name, description, axis fields. Agents have name, description, model, color, tools fields.