#437437th of 455 in Skills, plugins and prompts
antivibe
Claude Code skill that explains or audits existing code as learning guides
- Stars
- 1.1k
- License
- MIT
- Last commit
- Jul 2026
- Language
- Shell
596 on 22 Apr 20261,134 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
AntiVibe is a Claude Code skill, built from shell scripts and markdown agent definitions, that turns any file, directory or recent git diff into a deep-dive markdown guide covering what the code does, why, and alternatives. A senior mode routes to an auditor agent for architectural trade-offs. Depth is set per level (junior, mid, senior), with compact or full output and a skip list of known concepts.
Who it is for: Claude Code users who want to understand or audit code, not just accept it
Strengths
- Works on any file or directory; no git history or AI authorship required
- Configurable level, output mode and known-concepts skip list in SKILL.md
- Separate explainer and auditor subagents for learning versus architectural review
- Optional Stop and SubagentStop hooks generate deep dives automatically
Weaknesses
- Built for Claude Code; no other coding agent is mentioned
- Manual install: clone and copy into ~/.claude/skills, no installer
- No tagged release, so versioning is unclear
- No tests or accuracy checks described; guide quality depends on the model
What it needs
- no GPU
- Needs Claude Code
- Models: Claude
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |