Seo Reporter

Audit a URL for SEO factors and generate an actionable markdown report. Use when asked to analyze, check, or audit a webpage's SEO performance. Covers title,...

Security Scan

The skill's requirements and runtime behavior are consistent with an SEO auditing tool: it performs read-only HTTP requests using curl and generates a local markdown report, and it does not request credentials or install external code.

Purpose & Capability

Name/description (SEO audit) match the declared requirements and included script: only curl is required and the script fetches the target page, robots.txt, sitemap.xml and inspects HTML for SEO signals. No unrelated binaries or credentials are requested.

Instruction Scope

SKILL.md instructs the agent to run ./audit.sh against the target URL. The script performs only HTTP GETs and local text processing (grep, sed, tr), writes temporary files in a mktemp dir, and prints findings. It does not reference other system files, credentials, or external endpoints beyond the audited site and common sitemap variants. Note: SKILL.md includes an example cd into /home/tim/... which is just illustrative and should not be followed literally on other systems.

Install Mechanism

No install spec (instruction-only plus a shipped audit.sh). No downloads or package installs are performed. Risk is limited to running the included shell script locally.

Credentials

The skill requires no environment variables or credentials. The script uses only curl and standard shell tools. There are no requests for unrelated secrets or access to config paths.

Persistence & Privilege

always is false and the skill does not request persistent system-wide changes. It writes temporary files to a temp directory and does not modify other skills or system configuration.

Assessment

This skill appears coherent and limited in scope: it performs read-only HTTP requests to the target site and generates a local report. Before running, review the full audit.sh locally to confirm no unexpected network calls or data exports (the included snippet appears to be read-only but part of the file was truncated in the review listing). Run the script in a safe environment if you're unsure (e.g., a sandbox or container). Be aware the tool will make network requests to the target domain (and common sitemap paths) so don't point it at sensitive internal endpoints. Finally, if you plan to let the agent invoke skills autonomously, remember the skill can make outbound HTTP requests when run — limit autonomous use if that is a concern.

Audit any URL for core SEO factors and get an actionable report with scores and recommendations.

When to Use

✅ USE this skill when:

• "Audit the SEO of [URL]"
• "Check [URL] for SEO issues"
• "SEO report for [URL]"
• "Analyze page SEO"
• "What SEO improvements for [URL]?"

When NOT to Use

❌ DON'T use this skill when:

• Full technical SEO crawl needed → use Screaming Frog, Ahrefs, or Semrush
• Page speed / Core Web Vitals → use PageSpeed Insights
• Backlink analysis → use Ahrefs/Moz
• Keyword research or content optimization → use dedicated SEO tools
• SSL/certificate checks → use sslscan or online checkers

Input

A single URL (must include protocol: https://).

https://example.com

Output

A markdown SEO audit report covering:

Factor	What It Checks
Title Tag	Presence, length (50-60 chars optimal), uniqueness
Meta Description	Presence, length (150-160 chars optimal), relevance
H1 Heading	Exactly one H1 present, content relevance
Heading Structure	H1→H2→H3 hierarchy, no missing levels, no multiple H1s
Canonical Tag	<link rel="canonical"> present and points to correct URL
Robots.txt	File exists, is accessible, and is not blocking important pages
Sitemap.xml	File exists, is accessible, and contains the audited URL
Open Graph Tags	OG title, description, and image present
Mobile Viewport	Viewport meta tag present
HTTPS	Page served over secure connection

Each factor gets a score (Pass / Warning / Fail) and specific recommendations if issues are found.

Usage

Run the audit

URL="https://example.com"
./audit.sh "$URL"

Inline from agent

The agent should run audit.sh with the target URL and present the output as a formatted markdown report.

cd /home/tim/.openclaw/workspace/skills/seo-reporter
./audit.sh "https://example.com"

Report Format

# 🔍 SEO Audit Report: https://example.com

**Date:** YYYY-MM-DD
**URL:** https://example.com

---

## Scores

| Factor | Score | Status |
|---|---|---|
| Title Tag | 8/10 | ⚠️ Warning |
| Meta Description | 7/10 | ⚠️ Warning |
| H1 Heading | 10/10 | ✅ Pass |
| Heading Structure | 9/10 | ✅ Pass |
| Canonical Tag | 10/10 | ✅ Pass |
| Robots.txt | 8/10 | ⚠️ Warning |
| Sitemap.xml | 10/10 | ✅ Pass |
| Open Graph Tags | 5/10 | ❌ Fail |
| Mobile Viewport | 10/10 | ✅ Pass |
| HTTPS | 10/10 | ✅ Pass |

**Overall Score: 87/100**

---

## Detailed Findings

### ✅ Passed

- ...

### ⚠️ Warnings

- ...

### ❌ Issues Found

- ...

## Recommendations

1. ...
2. ...

---

*Report generated by seo-reporter skill*

Scoring Guide

Score	Meaning
10/10	Perfect — no issues
7-9/10	Good — minor improvements possible
4-6/10	Warning — meaningful issue that should be fixed
0-3/10	Fail — critical issue

Tips

• Always validate the URL has a protocol prefix (https://) before running
• The audit is non-destructive (read-only HTTP requests)
• Run from the skill directory so relative paths to helpers work
• For comparing two pages, run the audit on both and diff the scores