agent-sdk
Expert skill for building and maintaining AI agents using the Claude Agent SDK, covering architecture, tool integration, MCP servers, and agentic workflows.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
212 skills found
Expert skill for building and maintaining AI agents using the Claude Agent SDK, covering architecture, tool integration, MCP servers, and agentic workflows.
A local RAG semantic memory system using Qdrant and Ollama. Ideal for recalling workspace files, notes, project decisions, and user preferences with high-relevance vector search.
Automated security auditing for project dependencies. Scans package files (npm, pip, maven, etc.) for vulnerabilities, CVEs, and license issues, offering automated fix suggestions and integration for secure deployment workflows.
Enriches vague prompts by performing codebase research and asking targeted questions to clarify user intent before execution.
Mandatory workflow skill for managing conversation state, enforcing skill discovery, and ensuring task adherence through TodoWrite checklists.
Framework for orchestrating long-running agentic tasks, evidence-based delivery, and automated QA gates following Simon Willison's iterative loop.
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.
Expert guidance and configuration standards for creating specialized OpenCode AI agents, including YAML frontmatter, tool permissions, and operational modes.
Implement an AI agent delegation architecture to keep your main context clean, reduce token costs, and isolate specialized infrastructure or API tasks.
Orchestrate multi-agent AI swarms using the ClawTeam CLI to automate parallel task execution, dependency management, and team collaboration with git worktree isolation and tmux support.
Defense-in-depth protection for Claude Code. Manage security hooks to block dangerous commands, enforce file access controls, and protect sensitive paths across global or project-specific scopes.
Automate non-interactive npm package installations by piping shell confirmations to bypass prompts.