VerifyGuard is an automated pre-check utility that scans Markdown files for formatting issues, broken links, security leaks, and unfinished placeholders before publishing.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install verifyguard
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 verifyguard 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 VerifyGuard?
VerifyGuard is a powerful and lightweight command-line validation tool designed to ensure your AI-generated and human-written documents are flawless before publication or deployment. Inspired by the independent verification agent pattern seen in Claude Code, VerifyGuard represents an entirely original Python-based implementation that acts as an automated safety guard for technical writers, developers, and content creators using Openclaw Skills.
By executing automated scans across multiple quality and security checkpoints, VerifyGuard helps prevent embarrassing mistakes such as publishing broken hyperlinks, leaking sensitive access tokens, or uploading incomplete articles with placeholders like TODO or FIXME. It operates locally using Python and standard libraries, making it fast, safe, and highly portable for integration into automated publishing pipelines.
VerifyGuard Use Cases
- Content Publishing Safeguard: Automatically verify draft files for formatting errors and incomplete work-in-progress markers before pushing to live blogs.
- Link Integrity Auditing: Validate all hyperlinked external resources in your Markdown files to guarantee no dead URLs are served to readers.
- Secret Leakage Prevention: Run a quick scanner against local files to detect API keys, proprietary tokens, passwords, and private IP leaks before committing to git.
- CI/CD Quality Gate: Integrate the CLI script into continuous integration workflows to enforce quality gates on incoming technical documentation submissions.
How VerifyGuard Works
- Target Identification: The user specifies a target Markdown document or directory path using the VerifyGuard command interface.
- Security & Secrets Scan: The system parses the target file for potential security vulnerabilities including exposed API tokens, database passwords, and internal host IP configurations.
- Syntax & Completeness Parse: VerifyGuard reads the structural outline of the content, searching for unresolved content markers (such as TODO, FIXME) and truncated syntax segments.
- Link Accessibility Check: The tool extracts all web links in the document and attempts asynchronous or sequential HTTP status inquiries to verify active connectivity.
- Report Generation: The verification workflow compiles the findings into an actionable CLI summary, categorizing items by severity (CRITICAL, ERROR, WARNING) to let users know if the file is safe to publish.
VerifyGuard Setup
Requirements
VerifyGuard operates with a Python environment and requires Python 3.x installed on your target system.
Usage Commands
You can interact with VerifyGuard using Python commands directly from your terminal. Replace {{SKILL_DIR}} with the absolute path to your cloned skill directory:
# Check Markdown document syntax and general structure
python3 {{SKILL_DIR}}/scripts/verify.py check path/to/article.md
# Validate all external URL links embedded inside the document
python3 {{SKILL_DIR}}/scripts/verify.py links path/to/article.md
# Scan the document for sensitive credentials and private configurations
python3 {{SKILL_DIR}}/scripts/verify.py secrets path/to/article.md
# Run all validation checks (security, formatting, completeness, and links) in a single workflow
python3 {{SKILL_DIR}}/scripts/verify.py all path/to/article.md
VerifyGuard Data Schema & Taxonomy
VerifyGuard organizes its validation patterns and metadata structure around the following scanning dimensions:
| Severity Level | Check Dimension | Description & Verification Target |
|---|---|---|
| CRITICAL | Security (安全) | Scans for active passwords, API secret tokens, authentication keys, and internal IP address exposures |
| ERROR | Completeness (完整) | Searches for unfinished tasks flags (e.g., TODO, FIXME) and structural content truncation errors |
| WARNING | Links (链接) | Confirms correct URL structures, schema validation, and remote destination web server accessibility |
| WARNING | Format (格式) | Ensures proper Markdown grammar formatting, parsing blocks, and safe encoding compliance |
VerifyGuard Advanced Features
- Granular Sub-module Checks: Run tailored checks (e.g., exclusively auditing external links or checking for security leaks) instead of waiting on complete file processing.
- Independent Execution Model: Inspired by Claude Code VerificationAgent workflows but implemented natively in pure Python, eliminating the need for expensive third-party model orchestration.
- Automated Workflow Integration: Designed to output standardized system codes, enabling developers using Openclaw Skills to seamlessly plug the tool into Git hooks or pre-commit processes.
- Deterministic Parsing Logic: Ensures fast and resource-efficient checks using localized regular expressions and fast HTTP requests, protecting confidential code bases from cloud leakage.
SKILL.md
Loading
Related Openclaw Skills
OpenClaw SkillForge
An automated utility designed to convert manual, multi-step conversation workflows into standardized, reusable Openclaw Skills and script templates.
CodeByteLens
An open-source code intelligence tool that empowers AI agents to perform static code analysis, symbol indexing, and call graph analysis without a bulky LSP server.
mcpglue
A standardized Model Context Protocol (MCP) bridge that lets AI agents dynamically interface with custom servers, APIs, and file systems.
Google Flow Video Automation
An automation tool that leverages Chrome CDP to programmatically generate, optimize, and download AI videos on Google Flow.
DeepThink
DeepThink is a structured multi-stage reasoning skill for AI agents that enforces systematic analysis, strategic planning, and rigorous execution validation before taking action.
Contract Review
A conversational AI guide that simplifies complex contracts, translates legalese into plain English, and identifies hidden risks before you sign.
Featured*
