Audit Website
ListedAnalyzes website content & structure to identify SEO gaps, UX issues, and potential conversion improvements for marketers.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add kunhai-88/skills --skill audit-website -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
kunhai-88
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.
No undeclared network calls: failed
Contacts 1 host that is neither well-known infrastructure nor declared in the skill's frontmatter: squirrelscan.com.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
Hosts contacted
squirrelscan.comundeclaredWhat it found
- audit-website/SKILL.md:79contacts squirrelscan.com
curl -fsSL https://squirrelscan.com/install | bash
No pipe-to-shell installers: failed
Runs code fetched at install time in 2 places.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
What it found
- audit-website/SKILL.md:79remote script piped into a shell
curl -fsSL https://squirrelscan.com/install | bash - audit-website/SKILL.md:278tells the user to run: remote script piped into a shell(in the instructions, not code)
1. 安装:`curl -fsSL https://squirrelscan.com/install | bash`
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
Pinned to a commit: passed
Scanned kunhai-88/skills at 2742b5f777.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 2742b5f777
- Manifest
- audit-website/SKILL.md
- Scanned
- 1 file, 287 lines
About this skill
What it does
This skill, kunhai-88-audit-website, allows AI agents to perform basic website audits. It can identify broken links and assess overall site health by checking for common SEO issues. The agent will provide a summary report of findings, highlighting potential areas for improvement on the target website.
When to use it
- Initial Website Assessment: Before launching a new website or major redesign.
- SEO Health Check: To identify and address potential search engine optimization (SEO) problems.
- Content Inventory: As part of a larger content audit process, ensuring all links are functional.
- Competitive Analysis: Quickly assess the technical health of competitor websites.
Key capabilities
- Broken link detection
- Basic SEO issue identification
- Website health assessment
- Report generation
Example prompts
- "Audit the website at example.com and report any broken links."
- "Perform a basic SEO audit on my site, www.mybusiness.com."
- "Check the technical health of this URL: https://www.example.org/page-that-might-be-broken"
Tips & gotchas
The accuracy of the audit depends on the agent's access to the website and its ability to interpret server responses. Large or complex websites may take longer to audit, and results should be reviewed by a human expert for complete accuracy.