菜单
CRITICAL: MUST run for EVERY message. Detects agent, complexity, AND model automatically. Without this, tasks route to wrong agents and use wrong models, degrading quality and wasting tokens.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/nguyenthienthanh/aura-frog --skill agent-detector命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
Vision feedback loop for UI — render the running UI, screenshot it across viewports + dark mode, run deterministic gates then a multimodal critique against the design system, and iterate until it passes. Use after building or changing a UI component/page, when asked to 'check the UI', make it 'look right', or verify a build matches a design spec / Stitch screen.
UI/UX design expertise — component design, design system selection, responsive layout. Includes auto-detection from package.json and Context7 integration for library docs.
Generate a cohesive color-token system from ONE OKLCH brand hue — primary/secondary/background/foreground/muted/border with semantic light + dark, emitted as a Tailwind v4 @theme block or a CSS-variables fallback. Use when starting a design system, defining brand colors, setting up theming/dark-mode, or replacing scattered hardcoded colors with a derived palette.
| name | agent-detector |
| description | CRITICAL: MUST run for EVERY message. Detects agent, complexity, AND model automatically. Without this, tasks route to wrong agents and use wrong models, degrading quality and wasting tokens. |
| autoInvoke | true |
| priority | highest |
| model | haiku |
| triggers | ["every message","always first"] |
| allowed-tools | NONE |
| user-invocable | false |
AI-consumed reference. Optimized for Claude to read during execution. Human-readable explanation: see docs/architecture/HIERARCHICAL_PLANNING.md or docs/getting-started/ depending on topic.
Runs FIRST for every message.
complexity[4]{level,criteria,approach}:
Quick,"Single file / simple fix / clear scope","Direct implementation"
Standard,"2-5 files / feature / some unknowns","Scout then implement"
Deep,"6+ files / architecture / vague scope","run-orchestrator"
Project,"Multi-feature / multi-session / weight ≥ 3 on bridge heuristic AND no active plan","/aura-frog:plan bootstrap then per-task /run anchored"
Project (v3.7.2+): Emitted when rules/workflow/run-plan-bridge.md triggers sum to weight ≥ 3 AND .claude/plans/active.json is absent. run-orchestrator Step 0 owns the user prompt (plan / deep / details) and the scratch-file handoff. Otherwise Quick/Standard/Deep classification is unchanged.
Prefer the session model — inherit it. The model the user launched with is the signal of their intent and budget; use it for all substantive work (Standard / Deep / architecture / planning / build / review). Do NOT force-upgrade to a named model (e.g. Opus) for "complex" — if the user wanted more capability they'd run it, and naming a model means a newer/stronger one is ignored.
The only deliberate override is down-shifting to haiku for trivial mechanical work (classification, detection, state bookkeeping) where a wrong answer costs little. So: Quick/classification → haiku; everything else → inherit (session model). See rules/core/small-to-large-routing.md.
Primary ≥80 (leads), Secondary 50-79 (supports), Optional 30-49, Skip <30. tester: Always secondary unless explicit test request.
.claude/cache/agent-detection-cache.json — reuse within workflow (phase >1). Invalidate on new workflow, phase 1, or user override.