Agent Skills Hub

agent-system

Implementation patterns for MERIDIAN autonomous AI agents using Claude API, including BaseAgent lifecycle, structured tool use, token budget enforcement, and cron scheduling.

Python Security Scan

Advanced Python security vulnerability scanner for Flask, Django, and FastAPI projects. Audits OWASP Top 10, dependencies, hardcoded secrets, and framework-specific flaws.

getting-started-guide

A structured guide for novelists to navigate the seven-step writing process, from constitution and specification to planning, tasking, drafting, and quality analysis.

swarm-advanced

Orchestrate complex multi-agent swarms with topologies like mesh, hierarchical, and star for research, development, and testing workflows.

ai-llm-patterns

Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.

markdown-token-optimizer

Analyzes markdown files to identify token-wasting patterns, providing actionable suggestions to optimize documentation for LLM consumption and token efficiency.

paper-reproduce

Systematic methodology for reproducing published academic papers using provided data, including sample selection, statistical verification, and automated reporting.

memory-systems

Guides agent memory system implementation, compares frameworks (Mem0, Zep, Letta, LangMem, Cognee), and designs persistence architectures for cross-session knowledge retention.

web-research

Query the Pollinations text API with web-search enabled models like Gemini and Perplexity for grounded, real-time research.

mermaid-diagram-generator

Generate, validate, and refine Mermaid diagrams including flowcharts, sequence diagrams, ERDs, and architecture maps to visualize complex software systems and workflows.

network-watcher

Audit outbound network requests and detect data exfiltration patterns in OpenClaw skills to ensure secure outbound communication.

context-cascade

A nested plugin architecture for Claude Code that optimizes context by dynamically loading playbooks, skills, and agents to save over 90% in token usage.