Skill Claude CodeCodex
Re-inject Synapse A2A initial instructions after context has been cleared. Use this skill when the agent has lost its identity, A2A communication protocol, or configuration after /clear or context reset, when synapse send/reply commands stop working, or when the agent no longer recognizes its SYNAPSEAGENTID. Triggered…
Skill Claude CodeCodex
Guide architectural design decisions for software systems. Use this skill when designing new systems, evaluating architecture trade-offs, or creating technical design documents. Helps produce clear, well-structured design artifacts including component diagrams, data flow, and decision records.
Skill Claude CodeCodex
Guide for decomposing large tasks into a structured plan with dependency chains, managing priorities, and distributing work across agents. Outputs plan cards or delegation messages as the team contract; TodoList for personal micro-steps.
Skill Claude CodeCodex
Guide for Test-First (Test-Driven) Development. Focuses on writing tests before implementation, ensuring comprehensive coverage and clear requirements. Covers test design, edge cases, and the Arrange-Act-Assert structure.
Skill Claude CodeCodex
Web accessibility and interface standards guide. Covers WCAG compliance, semantic HTML, keyboard navigation, screen readers, forms, touch targets, and internationalization. Use when building, reviewing, or auditing web interfaces for accessibility and UX quality.
Agent Claude Code
Use this agent when you need to create or enhance README.md files, documentation, or technical documents that require high-quality visual explanations including diagrams, images, and Mermaid notation. This agent excels at transforming complex technical content into clear, visually-rich documentation that is easy to…
Agent Claude Code
Use this agent when working with Google's Agent-to-Agent (A2A) protocol implementation, designing multi-agent communication systems, troubleshooting A2A message routing, or implementing inter-agent coordination patterns. This includes tasks like sending messages between agents, monitoring agent status, handling…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: