An automated auditing tool that identifies unreviewed AI-generated code patterns and produces a scored quality report card.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install cacheforge-vibe-check
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install cacheforge-vibe-check using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is vibe-check?
vibe-check is a technical auditing tool designed to combat vibe coding—the practice of accepting AI-generated code without rigorous human review. As a robust addition to your library of Openclaw Skills, it scans source code for specific patterns that indicate lazy or insecure development habits, providing developers with a clear, scored report card (A-F) and actionable fix suggestions. It helps maintain high engineering standards by identifying issues that standard linters might miss, such as poor naming quality or missing edge case handling.
This skill is particularly valuable for teams integrating LLMs into their workflow, ensuring that the speed of AI generation does not compromise the long-term health of the codebase. By integrating seamlessly into your existing development environment, vibe-check acts as a quality gate for your Python, TypeScript, and JavaScript projects.
vibe-check Use Cases
- Performing a comprehensive quality audit on a specific file or an entire directory.
- Scanning staged Git changes to ensure new code meets quality standards before commit.
- Reviewing the technical debt and code quality of the last several commits in a branch.
- Generating professional, screenshot-ready report cards for code reviews or team transparency.
How vibe-check Works
- The user initiates the process by requesting a audit through a trigger phrase like vibe check.
- The skill identifies the target for analysis, which can be a file, directory, or a range of Git commits.
- A dedicated analysis engine scans the target code using either LLM-powered insights or a heuristic fallback mechanism.
- Code is evaluated against eight weighted categories: Error Handling, Input Validation, Duplication, Dead Code, Magic Values, Test Coverage, Naming Quality, and Security.
- The system generates a Markdown report containing a letter grade, numerical score, and specific findings with line-by-line fix suggestions.
vibe-check Setup
To get started with this entry in your Openclaw Skills collection, ensure your environment variables are correctly set for the script path. You can run the audit directly from your terminal:
# Audit a specific directory
bash "$SKILL_DIR/scripts/vibe-check.sh" src/
# Audit with automated fix suggestions
bash "$SKILL_DIR/scripts/vibe-check.sh" --fix .
# Audit changes in the last 3 commits
bash "$SKILL_DIR/scripts/vibe-check.sh" --diff HEAD~3
vibe-check Data Schema & Taxonomy
The analysis results are organized into a structured Markdown format for easy reading and integration into documentation:
| Data Component | Format | Description |
|---|---|---|
| Vibe Score | Grade (A-F) | An overall assessment of code quality and AI-human review balance |
| Category Breakdown | Table | Scores for Error Handling, Security, Naming, etc. |
| Findings | List | Detailed descriptions of detected coding sins with file locations |
| Unified Diff | Code Block | Suggested patches to resolve identified issues when --fix is used |
| README Badge | Markdown Link | A shield badge generated to display the current vibe score |
vibe-check Advanced Features
- Discord v2 Delivery Mode: Provides optimized, interactive summaries for team communication platforms, including quick-action buttons for top findings and fixes.
- Git Diff Engine: Focuses analysis specifically on recently changed lines, saving time during incremental development cycles.
- Heuristic Fallback: Ensures the tool remains functional even without active LLM API keys by using pattern-matching logic.
- Automated Fix Suggestions: Generates ready-to-apply diffs for common issues like hardcoded secrets or missing try/catch blocks.
SKILL.md
Loading
Related Openclaw Skills
CacheForge Stats
A terminal-based dashboard for monitoring CacheForge LLM usage, token savings, and performance metrics.
CacheForge Setup
A streamlined onboarding tool to register, configure, and integrate CacheForge as an LLM proxy for AI agents.
CacheForge Ops
A comprehensive operational toolkit for managing CacheForge account billing, credits, and upstream provider configurations.
Agentic DevOps
A production-ready DevOps toolkit for Docker management, process monitoring, and deep log analysis.
CacheForge
CacheForge is a token optimization gateway that streamlines onboarding and operations for OpenAI-compatible agent workflows.
Context Engineer
A powerful context window optimizer designed to analyze, audit, and compress AI agent token utilization.
Featured*
