ZSeven-W — 14 Open-Source AI Agent Skills

ZSeven-W is the author of 14 open-source AI agent skills and MCP servers spanning mcp-server, codex-skill, agent-tool, with a combined 8,228+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 63/100) and security-graded where a README exists (13 of 14) — 13 verified safe.

Top skills by ZSeven-W

• openpencil — The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. Design-as-Code. Turn prompts int (7.1k★ · quality 70/100 · security: safe)
• dsh-ios — DeepSeek Harness (DSH) plugin: a live iOS Simulator — and a USB-connected iPhone — inside the conversation. 22 agent tools for booting, buil (303★ · quality 61/100 · security: safe)
• dsh-android — DeepSeek Harness plugin for Android — build, run, and interact with a live emulator or USB device stream inside a conversation, driven entir (172★ · quality 64/100 · security: safe)
• dsh-crew — DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with (157★ · quality 69/100 · security: safe)
• craft-skills — Research-backed, eval-driven skills for AI agents (157★ · quality 65/100 · security: safe)
• rish-app — Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH (149★ · quality 61/100 · security: safe)
• dsh-noema — Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page. (129★ · quality 73/100 · security: safe)
• openpencil-skill — LLM skill for designing with OpenPencil via the op CLI and MCP tools (62★ · quality 71/100 · security: safe)

View ZSeven-W on GitHub · Explore audited agent skills