A coding-agent skill for safer AI code editing: inspect first, patch minimally, verify honestly.
npx skills add kyejin1991/safe-code-agentA coding-agent skill for safer AI code editing: inspect first, patch minimally, verify honestly.
Source: https://github.com/kyejin1991/safe-code-agent
Discovered from GitHub repositories pushed in the last 24 hours for agent skills, Claude/Codex/Gemini workflows, MCP tooling, and adjacent AI-agent automation.
WhatsApp AI Engineer — Gemini orchestrator + Claude Code execution. Chat with an AI coding assistant via WhatsApp or web dashboard.
The operational layer for coding agents. Memory, validation, and feedback loops that compound between sessions.
可复用的 Agent skills，以及各领域奠基性文章的中文版。
SST3 Skills — Claude Code plugin marketplace. Ralph Review Trio (Haiku → Sonnet → Opus, restart-on-fail) + more packs coming.
Local-first token usage skill for Codex, Claude Code, and OpenAI-compatible logs
Open Maintainer keeps your GitHub repos ready for AI agents. It generates AGENTS.md, repo skills, review rules, and PR/issue automation from your actual codebase.