OthmanAdi — 14 Open-Source AI Agent Skills
OthmanAdi is the author of 14 open-source AI agent skills and MCP servers spanning claude-skill, codex-skill, mcp-server, uncategorized, with a combined 28,116+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 58/100) and security-graded where a README exists (12 of 14) — 12 verified safe.
Top skills by OthmanAdi
- planning-with-files — Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and co (27.9k★ · quality 65/100 · security: safe)
- plandeck — The visual Kanban for long-running AI agents. Watch your agent's plan organize itself: dependencies unlock into Ready, the critical path lig (68★ · quality 61/100 · security: safe)
- planning-with-teams — Manus-style context engineering for Claude Code Agent Teams. Coordinate multiple Claude instances with shared planning files. (27★ · quality 76/100 · security: safe)
- langsmith-fetch-skill — 🔍 AI observability skill for Claude Code. Debug LangChain/LangGraph agents by fetching execution traces from LangSmith Studio directly in y (27★ · quality 74/100 · security: safe)
- loophole — Control Ableton Live from Claude and any LLM. An MCP server built on Ableton's official Extensions SDK: one .ablx, no Remote Script, no Able (20★ · quality 65/100 · security: safe)
- humanizer-semitic — AI text humanizer skills for Arabic (MSA, Egyptian, Levantine) and Hebrew — zero AI tells (9★ · quality 59/100 · security: safe)
- skill-deck — Universal coding agent skill browser — desktop overlay for Claude Code, Cursor, Copilot, Codex and 15+ AI agents (8★ · quality 68/100 · security: safe)
- plan-it — HTML-first persistent planning skill for Claude Code, Cursor, and 15 other agents. One self-contained plan.html. Survives /clear. SHA-256 at (7★ · quality 46/100 · security: safe)
View OthmanAdi on GitHub · Explore audited agent skills