agentmods.dev

seo-gsc-drops

seo-gsc-drops is a skill for Claude Code from lionkiii/claude-seo-skills. It costs 69 tokens per session (1,054 once invoked), scanned A, original, MIT.

A Google Search Console comparison that finds searches and pages losing clicks by comparing the latest 28 days with the 28 days before them. It highlights losses greater than 50 percent as critical.

In plain words
What is it for?
Use it to find declining keywords and pages, sort losses by size, and focus SEO checks on the biggest drops.
Why use it?
It helps locate falling search traffic and rankings before the causes become harder to investigate.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Part of the claude-seo-skills plugin — 51 skills, 6 agents shipped together

not rated 20repo 3mo ago A scan 69 tokens original MIT

Good fit Use it to find declining keywords and pages, sort losses by size, and focus SEO checks on the biggest drops.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lionkiii/claude-seo-skills/seo-gsc-drops
View source ↗ lionkiii/claude-seo-skills
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add lionkiii/claude-seo-skills --skill seo-gsc-drops
Clone the repo
git clone --depth 1 https://github.com/lionkiii/claude-seo-skills

Made for: Claude Code.

Or install claude-seo-skills, the plugin that ships this one along with the rest of its 51 skills, 6 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for seo-gsc-drops

README.md
[![agentmods](https://agentmods.dev/badge/skills/lionkiii/claude-seo-skills/seo-gsc-drops/github.svg)](https://agentmods.dev/skills/lionkiii/claude-seo-skills/seo-gsc-drops)
Your own site
<a href="https://agentmods.dev/skills/lionkiii/claude-seo-skills/seo-gsc-drops"><img src="https://agentmods.dev/badge/skills/lionkiii/claude-seo-skills/seo-gsc-drops/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for seo-gsc-drops

Your own site · 80×15
<a href="https://agentmods.dev/skills/lionkiii/claude-seo-skills/seo-gsc-drops"><img src="https://agentmods.dev/badge/skills/lionkiii/claude-seo-skills/seo-gsc-drops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,054 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.01054
Opus 5 $0.00034 $0.00527
Sonnet 5 $0.00014 $0.00211
Haiku 4.5 $0.00007 $0.00105

Measured 12d ago against content hash c7b0160ea4b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

seo-gsc-drops scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/seo-gsc-drops/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GSC Drops — Ranking Drop Detection

@skills/seo/references/mcp-degradation.md @skills/seo/references/gsc-api-reference.md

Identifies pages and keywords that lost clicks between the last 28 days and the prior 28-day period. Sorts by biggest losses first. Highlights CRITICAL drops (>50% loss).

MCP Check

Before calling any GSC tool, verify the MCP is connected:

  1. Use ToolSearch with query +google-search-console
  2. If tools returned — note the actual tool name prefix, proceed to Inputs
  3. If no tools returned — display the GSC MCP error template from references/mcp-degradation.md and stop:
## Google Search Console MCP Not Available

The `/seo gsc drops` command requires the GSC MCP, which is not currently connected.

**What you can do:**
- Use `/seo technical <url>` for crawlability and indexability analysis (no live data)
- Use `/seo audit <url>` for a full static SEO audit

**To connect GSC MCP:**
- Install and configure a Google Search Console MCP server (see README for setup)
- Add it to ~/.claude/mcp.json at user scope (NOT project scope)
- Verify GSC property access before running commands (domain vs URL prefix format)
- See references/gsc-api-reference.md for property format details

Inputs

  • site: The GSC property URL. Accept both formats:
    • Domain property: sc-domain:example.com
    • URL prefix: https://example.com or https://www.example.com
    • If user provides a bare domain (no prefix), call list_sites to identify the correct property format registered in GSC.

Date Calculation

Use Bash to calculate the two comparison periods (GSC has ~3 day delay):

currentEnd=$(date -v-3d +%Y-%m-%d)
currentStart=$(date -v-31d +%Y-%m-%d)
previousEnd=$(date -v-31d +%Y-%m-%d)
previousStart=$(date -v-59d +%Y-%m-%d)
echo "Current: $currentStart to $currentEnd | Previous: $previousStart to $previousEnd"

Execution

Step 1 — Page-level comparison: Call compare_performance with:

  • siteUrl: the site property
  • currentStartDate: currentStart
  • currentEndDate: currentEnd
  • previousStartDate: previousStart
  • previousEndDate: previousEnd
  • dimension: "page"
  • limit: 500

Read the full file on GitHub · 118 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 118 lines · 69 tokens per session scan A c7b0160ea4b6

Subscribe to this mod's changes

seo-gsc-drops is a skill published in the GitHub repository lionkiii/claude-seo-skills (20 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 1,054 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metricsClaude CodeMarketing and SEOahrefsai-seoanthropicbacklinksclaude-code-skills
Related

Other skills, from other repositories

seo-images

Image SEO audit for a URL or domain. Pulls raw image inventory via Firecrawl, then audits alt-text quality, modern-format coverage (WebP / AVIF), responsive sizing (srcset / sizes), lazy-loading and LCP signals (loading, fetchpriority, decoding), CLS-safe dimensions, descriptive file names, and ImageObject JSON-LD.…

amirjahfar1/automate-seo-with-claude · 225 tokens

seo-technical-audit

Focused one-shot technical SEO audit for a domain. Crawlability, indexability, security, mobile, structured data, JS rendering — single-pass deliverable, not a diff. Distinct from seo-drift (which tracks changes over time) and from seo-page (which audits keywords/traffic for one URL, not technical health). Use when…

amirjahfar1/automate-seo-with-claude · 109 tokens

seo-api

DataForSEO API integration architect for developers. Covers the entire DataForSEO surface — DataForSEO Labs (ranked keywords, keyword ideas/suggestions/related, domain rank overview, competitors, domain/page intersection, subdomains, relevant pages, bulk keyword difficulty, bulk traffic estimation, search intent…

amirjahfar1/automate-seo-with-claude · 411 tokens

seo-ads

Paid-search competitive landscape for a domain or keyword. Reconstructs the paid footprint keyword-by-keyword from live SERP ad blocks — advertisers, ad copy patterns, who else bids on the same keywords, CPC/competition signals, SERP shopping/ad-pack visibility — and produces a competitive ads brief plus a recommended…

amirjahfar1/automate-seo-with-claude · 113 tokens

seo-backlinks-profile

Full backlink profile for a domain — referring domains, anchor text distribution, authority distribution, IP and subnet diversity, growth/decay trend, toxic-candidate flagging. Distinct from seo-backlink-gap (which is gap-vs-competitor only). Produces a profile health score and reviewable disavow candidate list (never…

amirjahfar1/automate-seo-with-claude · 116 tokens

seo-content-audit

E-E-A-T + CITE quality audit for an EXISTING piece of content. Scores Experience, Expertise, Authoritativeness, Trustworthiness, and citation-readiness for AI search; surfaces veto items that block publication; produces a publish / publish-with-fixes / no-publish verdict. Distinct from seo-content-brief (produces a…

amirjahfar1/automate-seo-with-claude · 138 tokens