← ClaudeAtlas

raxollisted

Raxol terminal framework for TUI apps and AI agents in Elixir (v2.6, 15-package monorepo). TRIGGER when: code imports Raxol modules (Raxol.Agent, Raxol.Core, Raxol.MCP, Raxol.LiveView, Raxol.Workflow, Raxol.Headless), mix.exs lists :raxol / :raxol_agent / :raxol_core / :raxol_mcp as a dependency, user asks about building TUI apps or AI agents with Raxol, agent memory/self-improvement, the workflow engine, or Raxol headless/MCP tools. DO NOT TRIGGER when: general Elixir patterns (use droo-stack skill), Claude API / Anthropic SDK usage (use claude-api skill), agentic commerce / payments / ACP job sessions (use raxol-payments skill), the Symphony coding-agent orchestrator (use raxol-symphony skill), or other TUI frameworks (Scenic, Termbox, etc.).
DROOdotFOO/agent-skills · ★ 1 · AI & Automation · score 75
Install: claude install-skill DROOdotFOO/agent-skills
# Raxol Skill Elixir TEA framework for terminal UIs + AI agent orchestration. The same TEA model runs in the terminal, browser (LiveView), SSH, and as MCP tools/resources. OTP provides supervision, crash isolation, and hot reload. Raxol v2.6 is a 15-package monorepo (Elixir 1.20 / OTP 29). The packages this skill covers: - `raxol_core` -- TEA runtime, buffer/rendering, events, directives, telemetry - `raxol` -- umbrella + terminal surface (termbox2 NIF + IO fallback) - `raxol_agent` -- agent framework: TEA/Process agents, turn driver, memory, self-improving skills, backends, harnesses, teams - `raxol_mcp` -- MCP server/client: tool auto-derivation, focus lens, resources - `raxol_liveview` -- Phoenix LiveView bridge (buffer -> HTML, a11y) - `raxol_plugin`, `raxol_sensor` -- plugin SDK, sensor fusion Payments/ACP (`raxol_payments`, `raxol_acp`) and the Symphony orchestrator (`raxol_symphony`) have their own skills -- see below. ## What You Get - TEA agent and Process agent patterns with lifecycle examples - Turn driver + memory stack + self-improving skills (v2.6) - Workflow engine: graph DSL, checkpointing, human-in-the-loop, saga rollback - AI backends (HTTP, Mock, native ClaudeCode/Cursor, OpenRouter) + harness selection - MCP server (auto-derive tools from the widget tree) and MCP client - LiveView surface (buffer -> HTML, themes, accessibility) - Multi-agent orchestration (teams, cockpit, message protocol) - Headless sessions and agent testing patterns (unit, integ