1.3K skills · sorted by relevance
Set spending limits, token quotas, and rate limits, which restrict requests over time. Review current consumption and apply controls per API key or globally to manage AI costs across providers.
Set spending limits, token quotas, and rate limits, which restrict requests over time. Review current consumption and apply controls per API key or globally to manage AI costs across providers.
Manage OmniRoute API keys and provider authentication from the command line. Register, rotate, or revoke keys, inspect usage and expiration, set spending and model restrictions, and start or check OAuth sign-in connections.
Check OmniRoute server health, component status, and live metrics from the command line. Filter alerts or watch a refreshing dashboard to see provider status and circuit breakers, which interrupt requests when failures occur.
Inspect OmniRoute connection restrictions, usage quotas, and retry delays from the command line. Reset stuck providers and adjust failure thresholds, cooldowns, and recovery timing to manage how connections respond to errors.
Browse and search OmniRoute's AI model catalog from the command line. Filter by provider or capability, check model aliases, validate compatible models before adding them, and maintain manually registered model details.
Review AI call logs by provider, model, time range, status, and cost. Aggregate token usage, export logs, configure budgets, and inspect response times and prompt cache statistics to understand usage and performance.
Build AI agents with Cline SDK using guidance on choosing APIs, adding custom tools, saving sessions, and handling live events. References also cover model providers, scheduled runs, multi-agent coordination, and production deployment.
Prepare voiceovers, background music, sound effects, transcripts, captions, and background cutouts for HyperFrames compositions. The skill guides audio provider selection, word timing, and caption styling, with local alternatives for several audio tasks.
Refactor React components with too many true-or-false options into reusable parts. Provides guidance on component composition, shared state, and flexible interfaces, with examples of good and problematic implementations and specific guidance for React 19.
Build Claude applications using guidance for the official Anthropic SDK. Choose an integration approach, implement streaming and tool use, and follow workflows for model migration, prompt audits, evaluation, and cost optimization.
Build and optimize quantum circuits with PennyLane, including models that combine quantum circuits with PyTorch or JAX. Explore molecular energy estimation and optimization problems, validate values and gradients in simulation, and prepare tested circuits for provider plugins.
Plan systems across AWS, Azure, GCP, and OCI by comparing services and architecture patterns. Helps guide service selection, disaster recovery, migration planning, and cost decisions while considering ways to reduce dependence on a single provider.
Finds and retrieves paid financial datasets when free sources lack coverage or detail. Guides comparison of providers, success rates, prices, and required inputs, while keeping execution costs and remaining credits visible.
Connect cognee to model providers, databases, storage services, and development tools. Guides configuration of language models and embeddings, the numerical representations used for search, including the separate settings each requires.
Install Cursor as an agent backend for NanoClaw groups using its local SDK. Set up authentication and container integration so groups can use Cursor for planning, MCP tools, streaming responses, and session continuation.
Add Codex as the agent that plans tasks and coordinates tools in NanoClaw. Choose it for individual groups alongside Claude, with conversation history and session resume using a ChatGPT subscription or OpenAI API key.
Move legacy NanoClaw memory and Claude auto-memory into a shared structure used across providers. The skill separates lasting facts from standing instructions, updates indexes, records each file's outcome, and verifies recall after approval.
Maintain an application's supported language models by checking provider availability, adding models, and keeping documentation, live tests, and model-specific request settings aligned. It also checks provider model identifiers and candidates for the recommended list.
Configure Crush with Bash or JSON files to choose AI providers and models, connect external tools, set permissions, and adjust behavior. Understand how project and global settings combine when customizing your working environment.
Build automated emails for account registration, invoices, and notifications, from reusable templates to delivery service integration. Includes local previews, multilingual content, dark mode styling, and checks for delivery issues and tracking.
Guide cmux backend changes with consistent rules for Effect, a TypeScript library for structured error handling. Covers Cloud VM state, database migrations, provider integrations, and authentication and payment checks so changes follow the intended architecture.
Get help setting up, configuring, and troubleshooting Paseo using current public documentation. Identify the affected host and connection method, then use relevant diagnostics to investigate provider, version, workspace, or connectivity problems.
Publish a built website or web app and provide a shareable URL through Kortix Apps, Cloudflare, or Vercel. Check the running build, security, external service requirements, and data storage limits before deploying with the user's explicit approval.