Agents365-ai — 40 Open-Source AI Agent Skills

Agents365-ai is the author of 40 open-source AI agent skills and MCP servers spanning claude-skill, agent-tool, mcp-server, codex-skill, with a combined 9,908+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 58/100) and security-graded — 19 verified safe.

Top skills by Agents365-ai

• drawio-skill — Generate draw.io diagrams from natural language — 11 presets (UML, SysML/MBSE, BPMN, network, C4…), 36 tools: codebase/CI/infra-to-diagram, (7.2k★ · quality 71/100 · security: safe)
• video-podcast-maker — Topic → 4K narrated video for coding agents. v4.0: all TTS via the ttsCN engine component (11 platforms incl. MiniMax voice clone, native wo (1.5k★ · quality 74/100 · security: safe)
• excalidraw-skill — Hand-drawn Excalidraw diagrams from natural language. 5 patterns, 8-color semantic palette, Kroki API or local CLI. PNG/SVG, multi-agent. (181★ · quality 65/100 · security: safe)
• asta-skill — Pure instruction-pack skill wrapping Ai2's Asta MCP server (Semantic Scholar). Intent-to-tool routing, safe defaults, multi-agent. (179★ · quality 72/100 · security: safe)
• mermaid-skill — Mermaid diagrams (.mmd) from natural language with validation loop. 11+ types, multi-backend (mmdc / Kroki), PNG/SVG/PDF, multi-agent. (176★ · quality 65/100 · security: safe)
• paper-fetch — DOI → PDF resolver with 7-source fallback (Unpaywall, S2, arXiv, PMC, bioRxiv, publisher, Sci-Hub). Multi-agent, zero-deps Python. (174★ · quality 74/100 · security: safe)
• tldraw-skill — Whiteboard tldraw diagrams (.tldr) from natural language with 6 presets and vision-based self-check. PNG/SVG export, multi-agent. (111★ · quality 70/100 · security: safe)
• semanticscholar-skill — Semantic Scholar API wrapper for agents — search 200M+ papers, traverse citations, find authors. Python, rate-limited, multi-agent. (65★ · quality 73/100 · security: safe)

View Agents365-ai on GitHub · Explore audited agent skills