gsc-content-opportunities

gsc-content-opportunities is a skill for Claude Code from acamolese/google-search-console-mcp. It costs 62 tokens per session (538 once invoked), scanned A, original, MIT.

A workflow for turning Google Search Console data into a ranked content plan. Google Search Console is Google's service for reporting how a website performs in search results.

In plain words
What is it for?
It helps decide which pages to rewrite, strengthen, merge, or refresh by combining quick-win, click-through-rate, cannibalisation, and content-decay reports.
Why use it?
It identifies where content work may bring more search clicks, including pages with weak click-through rates, competing pages, declining traffic, or rankings just outside the first page.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the google-search-console plugin — 5 skills, 2 MCP servers shipped together

Good fit It helps decide which pages to rewrite, strengthen, merge, or refresh by combining quick-win, click-through-rate, cannibalisation, and content-decay reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/acamolese/google-search-console-mcp/gsc-content-opportunities
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 acamolese/google-search-console-mcp --skill gsc-content-opportunities
Clone the repo
git clone --depth 1 https://github.com/acamolese/google-search-console-mcp

Made for: Claude Code.

Or install google-search-console, the plugin that ships this one along with the rest of its 5 skills, 2 MCP servers.

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 gsc-content-opportunities

README.md
[![agentmods](https://agentmods.dev/badge/skills/acamolese/google-search-console-mcp/gsc-content-opportunities/github.svg)](https://agentmods.dev/skills/acamolese/google-search-console-mcp/gsc-content-opportunities)
Your own site
<a href="https://agentmods.dev/skills/acamolese/google-search-console-mcp/gsc-content-opportunities"><img src="https://agentmods.dev/badge/skills/acamolese/google-search-console-mcp/gsc-content-opportunities/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 gsc-content-opportunities

Your own site · 80×15
<a href="https://agentmods.dev/skills/acamolese/google-search-console-mcp/gsc-content-opportunities"><img src="https://agentmods.dev/badge/skills/acamolese/google-search-console-mcp/gsc-content-opportunities.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 538 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 $0.00062 $0.00538
Opus 5 $0.00031 $0.00269
Sonnet 5 $0.00012 $0.00108
Haiku 4.5 $0.00006 $0.00054

Measured 12d ago against content hash 567af7bf8b32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gsc-content-opportunities 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/gsc-content-opportunities/SKILL.md · 51 lines

What it actually says

Content opportunities

1. Gather

Run all four with period="last_3_months":

  1. gsc_quick_wins — queries close enough to the top that a push pays off
  2. gsc_ctr_gaps with entity="page" — pages that rank but are not clicked
  3. gsc_cannibalization — queries split across several pages
  4. gsc_content_decay with months=6 — pages sliding down month after month

They answer different questions and the plan needs all four. Decay in particular is invisible to any period comparison: a page that halves over six months never shows a sharp drop in any single month.

2. Sort the work into four buckets

  • Rewrite (from ctr_gaps): the ranking is already there, the snippet is not earning the click. Cheapest work on the list. Quote the current CTR against the expected one.
  • Strengthen (from quick_wins): queries just off the first page. Quote the estimated uplift, which is the clicks the query would earn at position 3.
  • Merge or re-point (from cannibalization): name the page that should win.
  • Refresh (from content_decay): quote the peak month and the last month so the decline is visible.

3. Rank and state the limits

Order the whole plan by estimated click gain, not by bucket. Then state the thresholds the tools applied — every response's meta line carries them — so the reader knows what was filtered out. On a small property the floors do most of the filtering.

Two things to be honest about:

  • The uplift figures assume the page reaches the target position. They size the opportunity; they are not a forecast.
  • themes output, where you use it, is word frequency across queries. It is a starting point for topic ideas, not evidence of demand.

4. Optional

If the user wants the plan as a document rather than a message, gsc_audit produces a self-contained HTML report covering the same ground plus the technical issues.

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 · 51 lines · 62 tokens per session scan A 567af7bf8b32

Subscribe to this mod's changes

gsc-content-opportunities is a skill published in the GitHub repository acamolese/google-search-console-mcp (8 stars, last pushed 20d ago), licensed MIT. It adds 62 tokens to every session and 538 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 2026-08-31.