nguyenthienthanh/aura-frog
57 skills
$npx skills add nguyenthienthanh/aura-frogSkillInstalls
agent-detectorCRITICAL: MUST run for EVERY message. Detects agent, complexity, AND model automatically.angular-expertAngular 17+ gotchas and decision criteria. Covers signals vs observables, standalone patterns, and common pitfalls Claude gets wrong.api-designerDesigns RESTful APIs with endpoint naming, versioning strategies (URL path, header-based), pagination (offset and cursor), error response schemas, and OpenAPI…bugfix-quickFast bug fixes with root cause investigation + TDD. Enforces 'no fix without root cause' discipline and verification protocol.chain-of-verificationDraft → generate verification questions → answer independently via tools → revise. Catches hallucinated facts in reports and reviews.code-reviewer6-aspect structured code review (security, architecture, error handling, test gaps, type safety, simplification) with calibrated scoring and per-aspect…code-simplifierDetect and simplify overly complex code. Apply KISS principle - less is more.conflict-detectorL1-L4 conflict detection between a proposed T4 task and pending-confirm sibling tasks.deep-debuggingSystematic debugging protocol for bugs that resist quick fixes.design-expertUI/UX design expertise — component design, design system selection, responsive layout.design-tokensGenerate a cohesive color-token system from ONE OKLCH brand hue — primary/secondary/background/foreground/muted/border with semantic light + dark, emitted as a…design-vision-loopVision feedback loop for UI — render the running UI, screenshot it across viewports + dark mode, run deterministic gates then a multimodal critique against the…documentationCreate Architecture Decision Records (ADRs) and Runbooks for operational documentation.extension-detectorDetects when a new project-level skill / rule / command would reduce friction. Asks the user for confirmation before creating anything.failure-classifierClassifies execution failures into F1-F5 (transient/local-logic/local-design/story-level/architectural).flutter-expertFlutter/Dart gotchas and decision criteria. Covers Riverpod vs BLoC, widget optimization, and platform-specific pitfalls.framework-expertUnified framework expertise bundle. Lazy-loads relevant framework patterns (React, Vue, Angular, Next.js, Node.js, Python, Laravel, Go, Flutter, Godot) based…frontend-aestheticsAnti-AI-slop taste layer for UI output — distinctive typography, dominant+accent color hierarchy, and implementation-matched polish.git-workflowToken-efficient git operations with security scanning and auto-split commitsgit-worktreeAuto-create git worktrees for workflows. Isolate changes, merge on success, discard on failure.go-expertGo gotchas and decision criteria. Covers error handling patterns, concurrency pitfalls, and interface design.laravel-expertLaravel/PHP gotchas and decision criteria. Covers N+1 prevention, Eloquent traps, and migration safety.lazy-agent-loaderLoad agent definitions on-demand to reduce context usage. Only loads full agent when needed.learning-analyzerAnalyze collected learning data from Supabase to identify success patterns, failure patterns, optimization opportunities, and agent performance trends.mcp-security-auditorOn-demand audit of MCP usage. Reads .aura/security/mcp-audit.jsonl, surfaces blocked calls, rate-limit hits, suspicious input patterns.migration-helperGuide safe database and code migrations with zero-downtime strategies.monorepoDetect and navigate monorepos correctly. Use when working with repos containing multiple packages (pnpm/yarn/npm workspaces, Turborepo, Nx, Lerna).motion-designRestrained, accessible web motion — Framer Motion declarative patterns and CSS-only staggered reveals for high-impact moments, always bundle-aware and…nextjs-expertNext.js 14+ gotchas and decision criteria. Covers server/client boundary, caching strategy, and data fetching patterns Claude commonly gets wrong.nodejs-expertNode.js gotchas and decision criteria. Covers async pitfalls, Express/NestJS patterns, and common mistakes.perf-profilingSystematic performance profiling and optimization. Use when performance issues are reported or suspected. Measure first, optimize second.performance-optimizerIdentifies and resolves performance bottlenecks across frontend (Core Web Vitals, code splitting, lazy loading), backend (N+1 queries, async processing), and…permanent-memory-loaderLoads permanent_memory.md summary lines (≤120 always-loaded tokens, hard cap 200). Surfaces durable wisdom from past Epics into the current session.phase1-liteUltra-compact Phase 1 requirements output. HARD CAP: 500 tokens.plan-archivistCompresses a completed plan-tree branch into .claude/plans/archive/{NODE_ID}.summary.md. Removes the original node files (preserved by checkpoint history).plan-loaderLoads minimum hierarchical plan context (.claude/plans/) for current execution focus. Auto-invokes every session when plans exist.plan-orchestratorRoute hierarchical-planning intents to the correct backing script.plan-validatorOn-demand plan-tree validator. Runs all 8 invariants from spec §6.7 (parent existence, children integrity, no orphans, valid status, monotonic revision,…preflight-validatorOn-demand wrapper over scripts/preflight/run-all.sh. Runs Tier 1 bash linters against a file, command, or arbitrary content. Returns 0 pass / 1 warn / 2 fail.problem-solving5 techniques for different problem types. Use when stuck or facing complex challenges.project-context-loaderLoad project conventions and generate session context. Use EXPLICITLY when needed, not automatically.prompt-evaluatorEvaluate how you use Claude Code — analyze prompt patterns, feature utilization, and get improvement suggestions.python-expertPython gotchas and decision criteria. Covers async pitfalls, FastAPI/Django patterns, and type hint traps.react-expertReact gotchas and decision criteria covering stale closure bugs in useEffect, conditional rendering traps (falsy 0/empty string), state management selection…react-native-expertReact Native gotchas and decision criteria. Covers FlatList optimization, storage hierarchy, and platform-specific pitfalls.reasoning-trace-recorderAuto-invokes for every Claude turn during active T4 task execution.refactor-expertGuide safe, incremental refactoring that improves code quality without changing behavior.response-analyzerMCP Response Analyzer pattern - Write large responses to temp files, load summaries into contextrun-orchestratorExecute 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…scalable-thinkingDesign for scale while keeping implementation simple (KISS).self-consistencyGenerate N independent reasoning paths and vote on the answer.self-healing-orchestratorProposes patches for F2 (local-logic) and F3 (local-design) failures. NEVER applies without user approval.self-improveApply learned improvements to the Aura Frog plugin. Updates rules, adjusts agent routing, modifies workflow configurations, and generates knowledge base…sequential-thinkingStructured thinking process for complex analysis. Supports revision, branching, and dynamic adjustment.session-continuationManage workflow state across sessions with handoff and resume. TOON-based state persistence.stitch-designGenerate UI designs using Google Stitch AI with optimized promptstest-writerWrite tests with TDD following structured patterns. Ensures consistent AAA structure, proper coverage targets, and framework-specific conventions.