ai-switching-models
Switch AI providers or models without breaking things. Use when you want to switch from OpenAI to Anthropic, try a cheaper model, stop depending on one vendor, compare models side-by-side, a model upd…
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Switch AI providers or models without breaking things. Use when you want to switch from OpenAI to Anthropic, try a cheaper model, stop depending on one vendor, compare models side-by-side, a model upd…
Thin HTTP layer controllers. Controllers contain zero domain logic, only HTTP concerns. Use when working with controllers, HTTP layer, web vs API patterns, or when user mentions controllers, routes, H…
Microsoft Excel API integration with managed OAuth. Read and write Excel workbooks, worksheets, ranges, tables, and charts stored in OneDrive. Use this skill when users want to read or modify Excel sp…
QoderWork Work Partner onboarding. Trigger when the user first launches QoderWork, wants to set up their work system, or says things like "help me organize my work", "initialize", "get to know me", "s…
Product planning and design workflow for creating UI components, data models, and implementation handoffs. Use when starting a new product, defining features, designing screens, or preparing export pa…
[WHAT] Character design and illustration assistant for AI product mascots, orb avatars, and animated companions. [HOW] Generates text-to-image prompts, character reference sheets, animation state matr…
Hierarchical root cause investigation technique that maps all necessary and sufficient conditions leading to an adverse event using tree-structured logic
Express uncertainty as a plausible range instead of false precision - quantify how confident you are in estimates to avoid overconfidence in decisions
See exactly what your AI did on a specific request. Use when you need to debug a wrong answer, trace a specific AI request, profile slow AI pipelines, find which step failed, inspect LM calls, view to…
Service providers, bootstrapping, and application configuration. Use when working with service providers, app configuration, bootstrapping, or when user mentions service providers, AppServiceProvider,…
Gate 1: Business requirements document - defines WHAT/WHY before HOW. Creates PRD with problem definition, user stories, success metrics.
Guidance for implementing tensor parallelism in PyTorch, including ColumnParallelLinear and RowParallelLinear layers. This skill should be used when implementing distributed tensor parallel operations…
Design and implement a custom search strategy for the timetravel research library. Invoke with /workflow tt-strategy-create.
Create flexible boundaries for projects - not rules or requirements, but bumpers that guide without constraining. Use when starting projects, when feeling overwhelmed by possibilities, or when needing…
Identify maximum sustainable load, population size, or growth limits constrained by available resources to prevent overshoot and collapse - apply capacity planning, scalability analysis, and bottlenec…
Systematic decision-making process for choosing optimal data structure based on problem requirements, performance constraints, and operational characteristics
Speak text aloud using high-quality AI voice synthesis (Kokoro TTS on Apple Silicon). Use when user asks to vocalize, narrate, or speak text out loud. Supports concurrent audio generation for multiple…
Complete Supabase platform documentation. Use when working with Supabase - covers authentication (email, OAuth, magic links, phone, SSO), database (PostgreSQL, RLS, migrations), storage (file uploads,…
Complete 10-gate pre-dev workflow for large features (>=2 days). Orchestrates topology discovery, research, PRD, feature map, design validation, TRD, API design, data model, dependency map, task break…
Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually
[WHAT] Reverse-engineer any SaaS product into feature inventory + architecture spec + gap map [HOW] Multi-source extraction → AI enhancement → synthesis against Lev/AgentPing capabilities [WHEN] "reve…
Align predicted probabilities with actual outcomes - train yourself so things you say are 70% likely actually happen 70% of the time
Before removing something, understand why it was put there in the first place—reforms without understanding cause unintended consequences
Manage algorithms, relationships, and responsibilities between objects using eleven behavioral patterns from the Gang of Four