菜单
Step-by-step workflow for implementing a new game feature in the roguelike architecture (layer assignment → discriminated union → pure function → test → shell wiring)
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
Write cutting-edge and modern native CSS. Apply this skill whenever writing, reviewing, or refactoring CSS for components, layouts, design systems, or theming, even if the user doesn't say "modern CSS" explicitly. Covers a self-contained design-token scale (color, size, shadow, ease, type), cascade layers (@layer), @scope for component isolation (donut scopes, :scope specificity, scoping proximity), container queries, :has(), OKLCH/color-mix, native nesting, subgrid, fluid typography via clamp(), scroll-driven animations, logical properties, and concrete native replacements for SCSS mixins, maps, and variables.
Apply this skill whenever the task involves web security: writing or auditing HTTP security headers, configuring CSP, CORS, HSTS, or Permissions-Policy, sanitising untrusted HTML (Sanitizer API / DOMPurify), implementing Trusted Types to prevent DOM-XSS, setting up the Reporting API to capture CSP/COEP/deprecation violations, hardening cookies (SameSite, HttpOnly, Secure, Partitioned), implementing WebAuthn / Credential Management, using Web Crypto for client-side cryptography, or auditing code for XSS, CSRF, clickjacking, MIME-sniffing, mixed content, or cross-origin data leakage. Triggers on keywords: XSS, CSRF, CSP, CORS, HSTS, SameSite, innerHTML, eval, Trusted Types, Sanitizer, ReportingObserver, WebAuthn, cross-origin, clickjacking, Content-Security-Policy, Referrer-Policy, Permissions-Policy, subresource integrity, cookie security, secure context, same-origin, mixed content.
Patterns for invoking the GitHub CLI (gh) from agents. Covers structured output, pagination, repo targeting, search vs list, gh api fallback.
Audit and update durable architecture guidance after a cross-layer implementation, file move, package boundary change, coverage config change, or SDTE feature. Use when agent needs to reconcile AGENTS.md, package AGENTS.md files, local .agents/skills, older specs, dynamic imports, and test or coverage configuration with the architecture that was actually implemented.
Run the Spec → Design → Tasks → Execution workflow for non-trivial work — produces /specs/<feature>/{spec,design,tasks}.md, drives atomic per-task execution, and ends with a Review phase. Invoke when starting a new package, new game system, GameState shape change, or any change touching > 3 files or crossing a layer boundary.
Best practices for building scalable plain Web Components without turning custom elements into “god objects”. Provides patterns that keep Web Components modular, reusable, maintainable, and focused on UI concerns.
| name | roguelike-feature |
| description | Step-by-step workflow for implementing a new game feature in the roguelike architecture (layer assignment → discriminated union → pure function → test → shell wiring) |
Follow these steps in order. Each step must compile and pass tests before moving to the next.
Identify which layer(s) the feature touches:
packages/game/lib/state/packages/game/lib/input/packages/game/lib/render/project-render-commands.ts as RenderCommand projectionpackages/game/lib/effects/, with foreground Canvas command execution in packages/game/lib/effects/execute-render-command.tspackages/game/lib/effects/packages/game/lib/effects/ or the entry point, using log() from @bruff/utilspackages/utils/If the feature introduces new events, extend the relevant discriminated union in packages/game/lib/core/actions.ts:
type GameAction =
| { type: "MOVE_PLAYER"; direction: Direction }
| { type: "YOUR_NEW_ACTION" /* typed payload */ };
Use InputAction for normalised input, GameAction for simulation events, SystemEvent for engine-level signals, and RenderCommand for draw instructions produced by the render projection.
(state: GameState, action: YourAction) => GameStateeffects/ or any browser API.Add the new action to the pure step path (packages/game/lib/state/advance-game-state.ts) or the relevant reducer. The shell (effects/loop.ts and effects/frame-step-driver.ts) dispatches inputs and renders; it must contain no business logic itself.
For visual output, add foreground draw data in projectRenderCommands(state) and Canvas execution in executeRenderCommand(context, command). Keep animated background concerns in the shell unless the feature explicitly migrates them to commands.
If the feature affects browser tests, expose it through the existing window.__bruffTestApi surface only when __BRUFF_TEST_MODE__ and ?test=1 / data-test-mode="true" are active.
Shell diagnostics must emit through the logging event bus with log() from @bruff/utils. Do not add direct console.* calls.
pnpm run ok