AgentDB Learning Plugins
Create and train custom reinforcement learning plugins for autonomous agents using 9 core algorithms including Decision Transformer and Actor-Critic for self-optimizing behavior.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
2077 skills found
Create and train custom reinforcement learning plugins for autonomous agents using 9 core algorithms including Decision Transformer and Actor-Critic for self-optimizing behavior.
Add an agent-agnostic visual feedback toolbar to your Next.js project to annotate UI elements and sync feedback with AI coding agents.
A zero-config local CLI tool for debugging AI agent execution. Inspect snapshots, LLM calls, and context engine data in development environments.
A persistent memory system for AI agents to store, recall, and manage codebase knowledge, architectural decisions, and research findings across sessions.
Guidance for designing autonomous agents for Claude Code, covering system prompts, triggering conditions, frontmatter configuration, and agent development best practices.
Manage isolated, containerized PostgreSQL environments for integration testing, optimized for concurrent local development and worktree workflows.
Create and configure custom AiderDesk agent profiles by defining tool groups, approval rules, subagent settings, and model providers to streamline your development workflow.
Build, test, and integrate custom tools with Elastic Agent Builder and connect your IDE to Agent Builder MCP for AI-driven development.
Design and build AI agents for any domain. Master agentic patterns, loop-based orchestration, and tool use to enable autonomous behavior in business, research, and creative workflows.
Advanced browser automation for research, web interaction, and data extraction within secure container environments.
AFL++ fuzzer orchestration for multi-core fuzzing of C/C++ projects with support for diverse mutation strategies, mature tooling, and scalable bug discovery.
Implement production-grade LLM-as-a-judge pipelines for model evaluation, including pairwise comparison, direct scoring, bias mitigation, and rubric generation.