rules-optimizer
Optimize and create Claude Rules (.claude/rules/*.md) following best practices.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Optimize and create Claude Rules (.claude/rules/*.md) following best practices.
Auxiliary script management rules for Ralph agents. Use proactively when creating helper scripts in .claude/session/.
Prime context for a task — calls context_continue + context_retrieve to find relevant files before starting work. Minimizes token usage by reusing cached context and only reading what's needed.
Guide for creating Agent Skills: structure, best practices, and SKILL.md format for Claude Code, Codex, Gemini CLI, and other AI agents.
When creating or validating skills. Reference for SKILL-CREATOR and SKILL-VALIDATOR.
Self-improvement protocol for Neo4j agents. Instructs agents to report skill updates needed.
Comprehensive testing suite for GitHub agent skills and subagents. Executes 17 workflows and generates a detailed report.
Create, manage, and test reactive triggers (webhook & event-based). Triggers execute skills or routines in response to external events (GitHub push, Stripe payment, Linear issue, etc.). Use when user says 'create trigger', 'list triggers', 'novo trigger', 'webhook para', 'quando acontecer', 'trigger list', 'test trigger', or any reference to reactive event triggers.
Implement UCP Checkout over the A2A (Agent-to-Agent) binding — enable autonomous agent-to-agent commerce using Agent Cards and structured message parts. Use when building agent-to-agent commerce flows.
Detects when Claude is uncertain but presenting answers confidently. Teaches Claude to recognize and communicate uncertainty clearly instead of masking it with confident language.