← Back to Skills Marketplace
page-filed-analyzer
by
EvalGitHub
· GitHub ↗
· v0.0.1
· MIT-0
206
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install page-filed-analyzer
Description
Analyzes form fields on a live webpage using browser automation. Use when the user provides an online URL/link and wants to count and analyze form input fiel...
Usage Guidance
This skill appears to do what it says: open a provided URL, snapshot the page, and count/classify form fields. Before using it, be aware that it examines live page content and can therefore see form structure and potentially sensitive inputs (passwords, file upload controls, or values if present in the accessibility tree). Do not run it on pages containing private data unless you control the page or have explicit consent. If you need stricter privacy, request or add safeguards (avoid capturing field values, redact snapshots, or limit analysis to public/testing pages). Finally, if a page requires authentication, the skill expects you to sign in manually first—there is no credential handling built into the skill.
Capability Analysis
Type: OpenClaw Skill
Name: page-filed-analyzer
Version: 0.0.1
The page-field-analyzer skill bundle is designed to automate the counting and categorization of form elements on a webpage. It uses standard browser automation tools (mcp__browser-use) to navigate to a URL, take snapshots, and execute a JavaScript snippet that counts various HTML input types and UI framework components (like Ant Design). The code and instructions in SKILL.md are consistent with the stated purpose and show no signs of data exfiltration, malicious execution, or prompt injection.
Capability Assessment
Purpose & Capability
Name/description match the instructions: the skill uses browser automation primitives (open page, wait, take snapshot, evaluate script) to count and classify form fields. No unrelated binaries, installs, or credentials are requested.
Instruction Scope
The SKILL.md stays on topic (navigating to a URL, taking an accessibility snapshot, optionally running a contained JS snippet to count elements). However, it will inspect live page content (accessibility tree and run arbitrary in-page JS), which can expose labels/structure and potentially sensitive content (password fields, file inputs, or other user data). The instructions do not mention masking or excluding sensitive values—consider this a privacy note rather than functional incoherence.
Install Mechanism
Instruction-only skill with no install spec or external downloads; nothing is written to disk by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested; the declared requirements are minimal and appropriate for the stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent or elevated platform privileges. It does not attempt to modify other skills or system settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install page-filed-analyzer - After installation, invoke the skill by name or use
/page-filed-analyzer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.0.1
分析表单字段
Metadata
Frequently Asked Questions
What is page-filed-analyzer?
Analyzes form fields on a live webpage using browser automation. Use when the user provides an online URL/link and wants to count and analyze form input fiel... It is an AI Agent Skill for Claude Code / OpenClaw, with 206 downloads so far.
How do I install page-filed-analyzer?
Run "/install page-filed-analyzer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is page-filed-analyzer free?
Yes, page-filed-analyzer is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does page-filed-analyzer support?
page-filed-analyzer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created page-filed-analyzer?
It is built and maintained by EvalGitHub (@evalgithub); the current version is v0.0.1.
More Skills