llm-integration
A toolkit for building robust LLM integrations: API patterns, streaming, function calling, RAG pipelines, and cost-effective model routing.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
160 skills found
A toolkit for building robust LLM integrations: API patterns, streaming, function calling, RAG pipelines, and cost-effective model routing.
Multi-model LLM integration patterns for Claude, GPT, Gemini, and Ollama. Features API handling, prompt engineering, token management, and model-agnostic orchestration.
Perform advanced video analysis using Google's Gemini API: summarize content, transcribe audio, extract timestamps, clip segments, and analyze YouTube URLs or local files with support for multiple models and long contexts.
Validates and coordinates batch study guide operations, preventing errors by enforcing template compatibility, file availability, and source-only policies before agent execution.
Gemini-powered UI design review, accessibility auditing, and design system validation tool for software agents.
Implement ReasoningBank adaptive learning with AgentDB's ultra-fast vector backend. Features trajectory tracking, verdict judgment, memory distillation, and pattern recognition for self-learning autonomous agents.
Analyze AppWorld task failures to extract specific API patterns and generate actionable playbook bullets with concrete code examples.
Fetch, index, and search developer documentation from GitHub and websites to provide AI agents with accurate, grounded, and version-specific code context.
Search and reference Chromium documentation, including design docs, APIs, and development guides. Use to locate, browse, or learn about architecture, GPU, network, security, and testing concepts within the Chromium codebase.
Unified AI gateway for 100+ LLMs with OpenAI-compatible API, model fallbacks, load balancing, and enterprise-grade tools.
An all-in-one Chinese daily utility toolkit: weather, currency exchange, news, and package tracking. Zero configuration, no API keys required.
An end-to-end video processing pipeline that transforms raw recordings into transcripts, key insights, short clips, and polished articles.