Loading...
Loading...
Found 20 Skills
Self-improving agent architecture using ChromaDB for continuous learning, self-evaluation, and improvement storage. Agents maintain separate memory collections for learned patterns, performance metrics, and self-assessments without modifying their static .md configuration.
Interactive guide to repository workflow system: agents, skills, routing, and execution patterns. Use when user asks how the system works, what commands are available, or how to use brainstorm/plan/execute phases. Use for "how does this work", "what can you do", "explain workflow", "help me understand", or "show me the process". Do NOT use for actually executing workflows (use workflow-orchestrator) or debugging (use systematic-debugging).
Design domain-specific agent teams, define specialized agents, and generate the skills they use. Use when you need to decompose a complex project into coordinated multi-agent teams, choose the right architecture pattern (pipeline, fan-out/fan-in, expert pool, producer-reviewer, supervisor, hierarchical delegation), generate .claude/agents/ and .claude/skills/ files, or validate and iterate on generated harnesses. Triggers on: harness, build a harness, design agent team, agent team architecture, multi-agent skill generation, set up harness, harness engineering, domain agent team, harness for this project.
Use when a single agent demonstrably cannot handle the task and multi-agent coordination is justified.
Universal text artifact optimizer using GEPA's optimize_anything API for code, prompts, agent architectures, configs, and more
Quality review skill for verifying complex changes against criteria. Use for multi-file changes, new features, or before important commits. Skip for trivial fixes and quick iterations.
Use when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails.
Audit, score, and improve any project's Claude Code configuration. Analyzes CLAUDE.md, skills, agents, hooks, MCP servers, and settings. Trigger: /refine, /refine audit, /refine quick