Total 31,015 skills
Showing 12 of 31015 skills
LLM guardrails with NeMo, Guardrails AI, and OpenAI. Input/output rails, hallucination prevention, fact-checking, toxicity detection, red-teaming patterns. Use when building LLM guardrails, safety checks, or red-team workflows.
Error pattern analysis and troubleshooting for Claude Code sessions. Use when handling errors, fixing failures, troubleshooting issues.
Comprehensive expertise in decentralized prediction markets, including Polymarket-style platforms, UMA Optimistic Oracle integration, Conditional Tokens Framework (CTF), market making, resolution mechanisms, and regulatory considerations. Use when "prediction market, Polymarket, betting market, outcome tokens, resolution oracle, UMA oracle, conditional tokens, binary market, outcome prediction, information market, " mentioned.
Database and HTTP connection pooling patterns for Python async applications. Use when configuring asyncpg pools, aiohttp sessions, or optimizing connection lifecycle in high-concurrency services.
Unit testing patterns and best practices. Use when writing isolated unit tests, implementing AAA pattern, designing test isolation, or setting coverage targets for business logic.
CQRS (Command Query Responsibility Segregation) patterns for separating read and write models. Use when optimizing read-heavy systems, implementing event sourcing, or building systems with different read/write scaling requirements.
Property-based testing with Hypothesis for discovering edge cases automatically. Use when testing invariants, finding boundary conditions, implementing stateful testing, or validating data transformations.
GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.
Design exploration with parallel agents. Use when brainstorming ideas, exploring solutions, or comparing alternatives.
Query decomposition for multi-concept retrieval. Use when handling complex queries spanning multiple topics, implementing multi-hop retrieval, or improving coverage for compound questions.
Event sourcing patterns for storing state as a sequence of events. Use when implementing event-driven architectures, CQRS, audit trails, or building systems requiring full history reconstruction.
Headless browser automation using Vercel's agent-browser CLI. 93% less context than Playwright MCP. Snapshot + refs workflow with element references. Use when automating browser tasks, web scraping, form filling, or content capture.