VVM (Vibe Virtual Machine) provides a concise language and conventions for writing agentic programs where the LLM acts as the runtime. It includes tooling and commands to compile, validate, run, inspect runs, and generate VVM programs from natural language. Typical flows include writing .vvm files, compiling for syntax checks, executing programs that spawn subagents, and inspecting run state.
Use this skill when you have a .vvm program or want to author agent workflows in VVM; when running the CLI commands like /vvm-boot, /vvm-compile, /vvm-run, /vvm-run-inspect, /vvm-registry-inspect, or /vvm-generate; or when asking about VVM syntax, semantics, patterns, or memory modes.
Inference: general-purpose LLM-based agent runtimes (Copilot/Codex-like, Claude Code, Gemini/CLI harnesses) that can host the VVM execution model are appropriate; the skill assumes LLM-driven execution and agent call semantics.
This skill has not been reviewed by our automated audit pipeline yet.
