- Home
- Skills
- Marketing & SEO
- Citation Freshness Audit: dateModified + Sitemap
Works with the AI Agents you already use
Citation Freshness Audit: dateModified + Sitemap
Unlike content-decay (GSC traffic) or schema type audits — checks visible Updated dates, JSON-LD dateModified, and sitemap lastmod for AI-citation freshness.
$7
Citation Freshness Audit: dateModified + Sitemap
Example session with this skill installed
Run a freshness audit on the harbor-docs/ directory using sitemap-harbor.xml. Output a Markdown report for Harbor Tools. Today is 2026-10-16.
- Read your context and instructions
- Compiled the citation freshness audit
- Generated the document
I have completed the freshness audit for the harbor-docs/ directory. The audit analyzed 5 HTML files against the provided sitemap.
Freshness Audit Report: Harbor Tools
| Source File | URL | Status | Best Date | Sitemap Lastmod | Notes |
|---|---|---|---|---|---|
index.html | / | FRESH | 2026-10-10 | 2026-10-10 | Matches across HTML and Sitemap. |
setup.html | /setup | SITEMAP_MISMATCH | 2026-09-15 | 2026-10-12 | Sitemap claims newer update than HTML. |
api.html | /api | STALE | 2026-05-20 | 2026-05-20 | Date is >90 days old. |
guide.html | /guide | MISSING_DATE | N/A | 2026-10-01 | No visible or JSON-LD dates found. |
config.html | /config | WARN | 2026-08-30 | 2026-08-30 | Date is between 31-90 days old. |
Summary:
pages=5 | FRESH=1 | STALE=1 | MISSING=1 | MISMATCH=1 | WARN=1
Next steps
- Update visible dates and
dateModifiedschema insetup.htmlto match the sitemap's October 12th timestamp. - Add
dateModifiedJSON-LD toguide.htmlto resolve the missing date signal. - Refresh the content in
api.htmlto move the status from STALE to FRESH for better AI citation potential.
index.html
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Differentiation (read this first)
Unlike content-decay / content refresh packs (which triage GSC traffic drops) or schema type/required-prop audits (JSON-LD eligibility), this pack audits citation freshness signals: visible Updated dates, JSON-LD dateModified/datePublished, and sitemap lastmod consistency. It never invents dates to force FRESH and never claims AI-citation lift.
Sample output (offline dry-run on the included Harborline Tools HTML — 2026-10-16)
pages=4 | FRESH=1 | STALE=1 | MISSING=1 | MISMATCH=1
| URL | Status | Best date | Notes |
|---|---|---|---|
| /guides/choose-dock-cleats | FRESH | 2026-10-12 | Visible + JSON-LD + sitemap aligned (4d ago) |
| /compare/anchor-clamp-pro-vs-standard | STALE | 2025-11-03 | 347 days since last update |
| /faq/dock-hardware | MISSING_DATE | — | No page dates; sitemap entry missing lastmod |
| /pricing/anchor-clamp-pro | SITEMAP_MISMATCH | 2026-10-10 | Page Oct 10 vs sitemap lastmod Jun 1 |
The problem
Research shows AI answers heavily cite recently updated pages — but teams refresh copy without stamping dateModified, leave sitemap lastmod stale, or publish with no visible Updated date. Schema audits and GSC decay tools do not catch that gap.
What it does
- Extracts visible update signals (
<time datetime>, "Updated …" text,article:modified_time/og:updated_time) - Extracts JSON-LD
dateModified/datePublished(including@graph) - Parses sitemap
lastmodand matches to page URLs (canonical / og:url) - Flags FRESH (≤30d) / WARN (31–90d) / STALE (>90d) / MISSING_DATE / SITEMAP_MISMATCH
- Writes CSV + Markdown; stdout one-liner for agents/CI
- Offline-first, stdlib Python only — no paid APIs
Why this beats prompting it yourself Same classification rules every run. Offline works unplugged. Never invents dates. CSV your agent can diff in CI after a refresh wave.
Use cases
- Pre-flight before pitching pages for AI Overview / ChatGPT citation readiness
- Post-refresh verification that dates and sitemap lastmod actually moved
- Agency deliverable: "citation freshness audit" in one pass
Example session
"Audit these pages for citation freshness — dateModified vs sitemap lastmod." →
pages=4 | FRESH=1 | STALE=1 | MISSING=1 | MISMATCH=1→ Fix checklist: add dates on FAQ; align pricing sitemap lastmod; refresh the Nov 2025 comparison
Trust Works in Claude Code, Cursor and Codex · tested on the included Harborline sample · Oct 2026 · v1.0.0 · stdlib Python only · no citation guarantees · questions answered within 24h · Cygnix Labs
Pairs with: Schema Markup / Rich Results Audit · Content Refresh Audit · llms.txt + AI Crawler Access · SEO Meta Tags Generator.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed with 2 warnings 8 days ago
Requires