Skill Claude Code
A full-cycle guide for checking whether agent hooks, plugins, and other integrations still match the current observed behavior of Claude Code. It focuses on undocumented dependencies, evidence from recent local records, fixes, tests, documentation, and deployment.
Skill Claude Code
A Git commit helper that records repository changes using Conventional Commits, with an option to push them afterward.
Skill Claude Code
A skill for translating Korean Markdown documents into English Markdown documents while preserving their meaning and related context.
MCP server Claude CodeCodexCursor +2
MCP server "mermaid-mcp", hosted remotely at mcp.mermaid.ai, as configured in clomia/claude-automata.
Plugin Claude Code
Bundles 6 skills, 2 agents, 8 hooks · 122 tokens together
Advisor Loop — an autonomous loop for long, multi-day work: an independent advisor certifies mission completion and the anchor survives every compaction, on subscription-safe agents.
Plugin Claude Code
Bundles 2 skills, 1 agent · 126 tokens together
Repository debt elimination — heavyweight multi-agent workflows that cross-examine findings into consensus, then apply only the highest-ROI fixes: code, docs.
Plugin Claude Code
Bundles 7 skills, 1 agent · 148 tokens together
Git transaction workflow — open a branch as an integrity boundary, drive OpenSpec through the change, and squash-merge it back only when clean, with guard hooks keeping protected branches and sync intact.
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: