nguyenthienthanh/aura-frog

design-vision-loop

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,…

原文语言：英语

design-expert

UI/UX design expertise — component design, design system selection, responsive layout. Includes auto-detection from package.json and Context7 integration for library docs.

原文语言：英语

design-tokens

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…

原文语言：英语

frontend-aesthetics

Anti-AI-slop taste layer for UI output — distinctive typography, dominant+accent color hierarchy, and implementation-matched polish. Use when building or restyling a UI/landing/component that should look designed rather than defaulted, or when the user asks…

原文语言：英语

stitch-design

Generate UI designs using Google Stitch AI with optimized prompts

原文语言：英语

run-orchestrator

Execute 5-phase TDD workflow for complex features. Use when the user invokes /run, asks to build/create/implement a feature, requests a complex multi-file change, or types 'fasttrack:'. Enforces phase gates, sprint contracts, and builder!=reviewer discipline.

原文语言：英语

motion-design

Restrained, accessible web motion — Framer Motion declarative patterns and CSS-only staggered reveals for high-impact moments, always bundle-aware and reduced-motion-safe. Use when adding animation/transitions to a UI (entrance reveals, list stagger,…

原文语言：英语

agent-detector

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.

原文语言：英语

problem-solving

5 techniques for different problem types. Use when stuck or facing complex challenges.

原文语言：英语

sequential-thinking

Structured thinking process for complex analysis. Supports revision, branching, and dynamic adjustment.

原文语言：英语

angular-expert

Angular 17+ gotchas and decision criteria. Covers signals vs observables, standalone patterns, and common pitfalls Claude gets wrong.

原文语言：英语

api-designer

Designs RESTful APIs with endpoint naming, versioning strategies (URL path, header-based), pagination (offset and cursor), error response schemas, and OpenAPI conventions. Use when the user asks about REST API design, creating endpoints, URL structure, API…

原文语言：英语

bugfix-quick

Fast bug fixes with root cause investigation + TDD. Enforces 'no fix without root cause' discipline and verification protocol. Without this skill, fixes are applied at symptoms instead of sources, and bugs return.

原文语言：英语

chain-of-verification

Draft → generate verification questions → answer independently via tools → revise. Catches hallucinated facts in reports and reviews. MANDATORY for Phase 4 security/test claims. Paper: Dhuliawala et al. 2023.

原文语言：英语

code-reviewer

6-aspect structured code review (security, architecture, error handling, test gaps, type safety, simplification) with calibrated scoring and per-aspect breakdown. Use when the user asks to review code, check a PR, review a pull request, audit changes before…

原文语言：英语

code-simplifier

Detect and simplify overly complex code. Apply KISS principle - less is more.

原文语言：英语

conflict-detector

L1-L4 conflict detection between a proposed T4 task and pending-confirm sibling tasks. L1 (file overlap) + L2 (function/region overlap) ship in v3.7.0-beta.2 as deterministic bash. L3 (semantic LLM) + L4 (architectural LLM) are stubbed for v3.7.0-rc.1.

原文语言：英语

deep-debugging

Systematic debugging protocol for bugs that resist quick fixes. Use bisection, hypothesis trees, and scientific method when a bug isn't obvious from the stack trace. Goes beyond bugfix-quick for production-grade root cause analysis.

原文语言：英语

documentation

Create Architecture Decision Records (ADRs) and Runbooks for operational documentation.

原文语言：英语

extension-detector

Detects when a new project-level skill / rule / command would reduce friction. Asks the user for confirmation before creating anything. NEVER writes plugin-level files — only `.claude/skills/`, `.claude/rules/`, `.claude/commands/` in the user's project.

原文语言：英语

failure-classifier

Classifies execution failures into F1-F5 (transient/local-logic/local-design/story-level/architectural). Outputs JSON with class, confidence, evidence, and recommended action. Deterministic rule-based classifier; no LLM call.

原文语言：英语

flutter-expert

Flutter/Dart gotchas and decision criteria. Covers Riverpod vs BLoC, widget optimization, and platform-specific pitfalls.

原文语言：英语

framework-expert

Unified framework expertise bundle. Lazy-loads relevant framework patterns (React, Vue, Angular, Next.js, Node.js, Python, Laravel, Go, Flutter, Godot) based on detected tech stack.

原文语言：英语

git-workflow

Token-efficient git operations with security scanning and auto-split commits

原文语言：英语

git-worktree

Auto-create git worktrees for workflows. Isolate changes, merge on success, discard on failure.

原文语言：英语

go-expert

Go gotchas and decision criteria. Covers error handling patterns, concurrency pitfalls, and interface design.

原文语言：英语

laravel-expert

Laravel/PHP gotchas and decision criteria. Covers N+1 prevention, Eloquent traps, and migration safety.

原文语言：英语

lazy-agent-loader

Load agent definitions on-demand to reduce context usage. Only loads full agent when needed.

原文语言：英语

learning-analyzer

Analyze collected learning data from Supabase to identify success patterns, failure patterns, optimization opportunities, and agent performance trends.

原文语言：英语

mcp-security-auditor

On-demand audit of MCP usage. Reads .aura/security/mcp-audit.jsonl, surfaces blocked calls, rate-limit hits, suspicious input patterns. Companion to mcp-call-gate hook (which produces the audit log).

原文语言：英语

migration-helper

Guide safe database and code migrations with zero-downtime strategies.

原文语言：英语

monorepo

Detect and navigate monorepos correctly. Use when working with repos containing multiple packages (pnpm/yarn/npm workspaces, Turborepo, Nx, Lerna). Ensures commands run in correct package scope, dependencies are routed properly, and cross-package changes are…

原文语言：英语

nextjs-expert

Next.js 14+ gotchas and decision criteria. Covers server/client boundary, caching strategy, and data fetching patterns Claude commonly gets wrong.

原文语言：英语

nodejs-expert

Node.js gotchas and decision criteria. Covers async pitfalls, Express/NestJS patterns, and common mistakes.

原文语言：英语

perf-profiling

Systematic performance profiling and optimization. Use when performance issues are reported or suspected. Measure first, optimize second. Applies Pareto principle — find the 20% of code causing 80% of slowness, fix that, not the rest.

原文语言：英语

performance-optimizer

Identifies and resolves performance bottlenecks across frontend (Core Web Vitals, code splitting, lazy loading), backend (N+1 queries, async processing), and database (EXPLAIN ANALYZE, indexing strategies) layers. Use when the user reports slow code, latency…

原文语言：英语

permanent-memory-loader

Loads permanent_memory.md summary lines (≤120 always-loaded tokens, hard cap 200). Surfaces durable wisdom from past Epics into the current session. Silent if .claude/memory/ does not exist.

原文语言：英语

phase1-lite

Ultra-compact Phase 1 requirements output. HARD CAP: 500 tokens.

原文语言：英语

plan-archivist

Compresses a completed plan-tree branch into .claude/plans/archive/{NODE_ID}.summary.md. Removes the original node files (preserved by checkpoint history). Reduces always-loaded surface area as features ship.

原文语言：英语

plan-loader

Loads minimum hierarchical plan context (.claude/plans/) for current execution focus. Auto-invokes every session when plans exist. Stays under 800 always-loaded tokens regardless of plan tree size.

原文语言：英语