VVM (Vibe Virtual Machine)

Trust Score 92/100

from vvm61

A small domain-specific language and runtime for writing agentic programs (.vvm) where the LLM is the execution runtime; provides compile, run, and inspection c

triggers:vvm.vvm/vvm-run/vvm-compile/vvm-bootvvm-generatevvm run

GitHub SKILL.md

What it does

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.

When to use it

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.

What's included

Scripts: none detected in the skill directory, but several documentation files (spec.md, vvm.md, patterns.md, antipatterns.md, memory-spec.md) provide runnable guidance.
References: design and language spec files are present (spec.md, vvm.md).
Instructions: the SKILL.md contains activation triggers, quick reference snippets (agent definition, calls, memory usage), example patterns, and CLI command descriptions for boot/compile/run/inspect/generate.

Compatible agents

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.

Audit Summary

VVM is a domain-specific language for writing agentic programs where the LLM acts as the runtime. No bundled scripts to test — the skill is purely a documentation/reference SKILL.md with 37 code examples covering the full language surface. The SKILL.md is well-structured with clear activation triggers, a documentation index for progressive disclosure, and comprehensive quick reference. Purely static analysis — no security concerns as there are no scripts or executable content.

Watch Out

No runtime/CLI tool provided — the LLM itself is the runtime, so actual execution depends entirely on the agent interpreting the DSL
References external docs (spec.md, vvm.md, patterns.md, etc.) that must be available in the skill directory for full functionality

Notes

Documentation-only skill with no scripts. Very thorough language reference. The DSL concept is creative — agent calls are syntactically distinct with @agent notation, and semantic predicates with ?`...` syntax are novel. No security issues whatsoever.

Information

Repository: vvm
Stars: 61
Installs: 0

Trust Score

Overall92

Security98

Code Quality88

Architecture82

Usefulness55

Related Skills

ds-fix — data-science mid-analysis fixer

Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Kickbox Automation (Composio / Rube MCP)

Automate Kickbox workflows via the Composio Kickbox toolkit on a Rube MCP server: discover tools, manage connections, and execute schema-compliant tool calls.

Tmux Bridge

Give an agent controlled access to a local tmux terminal bridge so it can run shell commands, capture output, and manage sessions on the user's machine.

SourceSage CLI

Generate concise, LLM-friendly repository summaries (Markdown) using the SourceSage CLI — supports lite mode, language switching, and targeted repo analysis.

Nit (Nitter CLI)

Terminal client to browse tweets, view profiles, and search posts via Nitter instances without opening a browser.

hn — Hacker News CLI

Terminal-based Hacker News client with a CLI and optional interactive TUI for browsing top/new/best/ask/show/jobs stories, viewing threads with nested comments,

Back to Skills