Loading...
Loading...
Found 1,993 Skills
Enter this sub-process when conducting code optimization — handle tasks where 'behavior remains unchanged, structure changes' (structure / performance / readability). Shift single-module internal optimization from 'AI random refactoring' to 'first scan to generate a checklist, confirm each item with the user, execute step-by-step according to the method library, and require manual approval for each step'. Trigger scenarios: Users mention phrases like 'optimize it / refactor / rewrite / split it / poor performance / code is too long' without any accompanying behavior changes. Do not handle new requirements (route to feature), bugs (route to issue), or cross-module architecture restructuring (route to architecture + decisions).
Select, implement, or migrate between app architecture patterns for Apple platform apps. Use when choosing between MV (Model-View with @Observable), MVVM, MVI, TCA (The Composable Architecture), Clean Architecture, VIPER, or Coordinator patterns; when evaluating architecture fit for a feature's complexity; when migrating from one pattern to another; or when reviewing whether an app's current architecture is appropriate. Scoped to Apple-platform patterns using Swift 6.3, SwiftUI, and UIKit.
Decision Coaching for Vue Component/Composable Refactoring — Users paste a piece of code or point to an SFC, and the skill first performs a diagnosis ("Fat Trunk" / "UI & IO Entanglement" / "Reactivity & Business Logic Entanglement"), then selects one from three recipes, and provides a specific sequence of extraction steps (which variable to move first, what errors the compiler will throw, how to fix them one by one, when rollback is possible). The entire process ensures behavioral equivalence through compiler green lights + step-by-step rollback, without relying on test safeguards. Trigger scenarios: Users say "This Vue component is too fat / I want to extract the logic / Split this SFC / This composable is too messy / Extract a composable / Split into humble / Pure functionalize", or point to an obviously overlong .vue / composable file and request "Refactor / Optimize / Split". Only handles Vue (Vue 2 Options, Vue 2/3 `<script setup>`, composable, pinia store). Does not handle: Adding new features (follow feature process), fixing bugs (follow issue process), cross-module architecture restructuring, backend code.
Implement end-to-end Medallion Architecture (Bronze/Silver/Gold) lakehouse patterns in Microsoft Fabric using PySpark, Delta Lake, and Fabric Pipelines. Use when the user wants to: (1) design a Bronze/Silver/Gold data lakehouse, (2) set up multi-layer workspace with lakehouses for each tier, (3) build ingestion-to-analytics pipelines with data quality enforcement, (4) optimize Spark configurations per medallion layer, (5) orchestrate Bronze-to-Silver-to-Gold flows via notebooks. Triggers: "medallion architecture", "bronze silver gold", "lakehouse layers", "e2e data pipeline", "end-to-end lakehouse", "data lakehouse pattern", "multi-layer lakehouse", "build medallion", "setup medallion".
System Audit - Proactively identify bug risks, security vulnerabilities, performance issues, maintainability debt, and architecture drift from code, and generate a batch list of findings. Triggers: Users say "review the system", "audit code", "scan for issues", "find bugs", "what can be optimized".
Research and discovery workflow for document deliverables — competitive analyses, architecture comparisons, ADR scaffolding, literature reviews, vendor evaluations. No TDD requirement. Phases: gathering → synthesizing → completed. Triggers: 'discover', 'research', 'explore topic', or /discover.
Build secure WordPress plugins with hooks, database interactions, Settings API, custom post types, and REST API. Covers Simple, OOP, and PSR-4 architecture patterns plus the Security Trinity. Includes WordPress 6.7-6.9 breaking changes. Use when creating plugins or troubleshooting SQL injection, XSS, CSRF, REST API vulnerabilities, wpdb::prepare errors, nonce edge cases, or WordPress 6.8+ bcrypt migration.
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
Design RESTful APIs following best practices for resource modeling, HTTP methods, status codes, versioning, and documentation. Use when creating new APIs, designing endpoints, or improving existing API architecture.
Create diagrams and visualizations using Mermaid.js v11 syntax. Use when generating flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, user journeys, timelines, architecture diagrams, or any of 24+ diagram types. Supports JavaScript API integration, CLI rendering to SVG/PNG/PDF, theming, configuration, and accessibility features. Essential for documentation, technical diagrams, project planning, system architecture, and visual communication.
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and structured output design.