| name | agent-intelligence-hub |
| description | 9 advanced agent and AI meta-skills for Claude Code: adversarial code review, agent design, workflow orchestration, context management, prompt engineering, self-evaluation, self-improvement, security auditing, and skill testing. |
| version | 1.0.0 |
| author | walva |
| license | MIT |
| tags | ["agents","prompt-engineering","self-improvement","security-auditing","orchestration"] |
| agents | ["claude-code"] |
Agent Intelligence Hub
9 meta-skills for building, evaluating, and improving AI agents and Claude workflows.
Skills
| Skill | Purpose |
|---|
| adversarial-reviewer | Adversarial code review with Saboteur, New Hire, and Security Auditor personas |
| agent-designer | Design and architect multi-agent systems |
| agent-workflow-designer | Design complex agent workflow pipelines |
| context-engine | Context management and retrieval for long-running agents |
| prompt-engineer-toolkit | Prompt optimization, A/B testing, few-shot generation |
| self-eval | Evaluate and score agent/skill performance |
| self-improving-agent | Self-modifying agent that improves its own instructions |
| skill-security-auditor | Security audit Claude skills and plugins |
| skill-tester | Automated testing framework for skills |
Usage
To load a specific skill, read its SKILL.md:
/read _AGENT_INTELLIGENCE_HUB/adversarial-reviewer/SKILL.md
/read _AGENT_INTELLIGENCE_HUB/prompt-engineer-toolkit/SKILL.md
/read _AGENT_INTELLIGENCE_HUB/self-improving-agent/SKILL.md
