Menu
SkillsMP a collecté 60 skills depuis nguyenthienthanh/aura-frog. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 60.
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,…
Langue du texte source : anglais
UI/UX design expertise — component design, design system selection, responsive layout. Includes auto-detection from package.json and Context7 integration for library docs.
Langue du texte source : anglais
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…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Generate UI designs using Google Stitch AI with optimized prompts
Langue du texte source : anglais
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.
Langue du texte source : anglais
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,…
Langue du texte source : anglais
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.
Langue du texte source : anglais
5 techniques for different problem types. Use when stuck or facing complex challenges.
Langue du texte source : anglais
Structured thinking process for complex analysis. Supports revision, branching, and dynamic adjustment.
Langue du texte source : anglais
Angular 17+ gotchas and decision criteria. Covers signals vs observables, standalone patterns, and common pitfalls Claude gets wrong.
Langue du texte source : anglais
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…
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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…
Langue du texte source : anglais
Detect and simplify overly complex code. Apply KISS principle - less is more.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Create Architecture Decision Records (ADRs) and Runbooks for operational documentation.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Flutter/Dart gotchas and decision criteria. Covers Riverpod vs BLoC, widget optimization, and platform-specific pitfalls.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Token-efficient git operations with security scanning and auto-split commits
Langue du texte source : anglais
Auto-create git worktrees for workflows. Isolate changes, merge on success, discard on failure.
Langue du texte source : anglais
Go gotchas and decision criteria. Covers error handling patterns, concurrency pitfalls, and interface design.
Langue du texte source : anglais
Laravel/PHP gotchas and decision criteria. Covers N+1 prevention, Eloquent traps, and migration safety.
Langue du texte source : anglais
Load agent definitions on-demand to reduce context usage. Only loads full agent when needed.
Langue du texte source : anglais
Analyze collected learning data from Supabase to identify success patterns, failure patterns, optimization opportunities, and agent performance trends.
Langue du texte source : anglais
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).
Langue du texte source : anglais
Guide safe database and code migrations with zero-downtime strategies.
Langue du texte source : anglais
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…
Langue du texte source : anglais
Next.js 14+ gotchas and decision criteria. Covers server/client boundary, caching strategy, and data fetching patterns Claude commonly gets wrong.
Langue du texte source : anglais
Node.js gotchas and decision criteria. Covers async pitfalls, Express/NestJS patterns, and common mistakes.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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…
Langue du texte source : anglais
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.
Langue du texte source : anglais
Ultra-compact Phase 1 requirements output. HARD CAP: 500 tokens.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais