tt-a1i — 12 Open-Source AI Agent Skills

tt-a1i is the author of 12 open-source AI agent skills and MCP servers spanning claude-skill, codex-skill, mcp-server, with a combined 77,336+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 58/100) and security-graded where a README exists (8 of 12) — 8 verified safe.

Top skills by tt-a1i

• archify — Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion an (76.1k★ · quality 63/100 · security: safe)
• hive — Browser-native hive-mind for CLI coding agents — Claude Code, Codex, Gemini, and OpenCode collaborate as real PTY processes via a team proto (552★ · quality 63/100 · security: safe)
• simplify-codebase — Prove and remove accidental codebase complexity without breaking behavior. (432★ · quality 64/100 · security: safe)
• matt-skills-with-to-goal — Planning → verifiable goals → fresh-session implementation for AI coding agents. Based on mattpocock/skills v1.1. (164★ · quality 65/100 · security: safe)
• tokenmeter — htop for AI Agents — monitor token usage, costs & tool calls across Claude Code and Codex in real time (29★ · quality 66/100 · security: safe)
• agmon — htop for AI Agents — monitor token usage, costs & tool calls across Claude Code and Codex in real time (18★ · quality 65/100 · security: safe)
• everos-mcp — Universal long-term memory layer for AI coding assistants, powered by EverMemOS. (16★ · quality 56/100 · security: safe)
• coding-cli-guide — Interactive deep-dive into Gemini CLI internals — 150+ illustrated pages, 50+ step-by-step animations, Mermaid diagrams, and source-level wa (5★ · quality 66/100 · security: safe)

View tt-a1i on GitHub · Explore audited agent skills