Systems Lab

Agent skill

google-ads-competitive-analysis-toolkit

This skill should be used when the user asks to \"analyze Auction Insights\", \"monitor competitor strategies\", \"calculate market share in Google Ads\", \"build a competitive response plan\", or mentions \"Share of Voice\", \"impression share analysis\", or \"competitor bidding\".

activeReaches the webInstructions only823 words

Filed under ABM and paid and Positioning and messaging.

From Ad-Superpowers/ad-superpowers-plugin · 120 skills · 5 · pushed 2026-09-10

What it does when it runs

This skill should be used when the user asks to \"analyze Auction Insights\", \"monitor competitor strategies\", \"calculate market share in Google Ads\", \"build a competitive response plan\", or mentions \"Share of Voice\", \"impression share analysis\", or \"competitor bidding\". Do NOT use for: keyword strategy (use keyword-strategy-planner), bid strategy selection (use bid-strategy-selector), or campaign performance diagnosis (use performance-troubleshooter).

Read from the skill and the 3 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
  • adstransparency.google.com
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about google-ads-competitive-analysis-toolkit

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/Ad-Superpowers/ad-superpowers-plugin.git /tmp/ad-superpowers-plugin
git -C /tmp/ad-superpowers-plugin sparse-checkout set "plugin/skills/google-ads-competitive-analysis-toolkit"
mkdir -p ~/.claude/skills/google-ads-competitive-analysis-toolkit
cp -R "/tmp/ad-superpowers-plugin/plugin/skills/google-ads-competitive-analysis-toolkit/." ~/.claude/skills/google-ads-competitive-analysis-toolkit/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

Or take the whole library

This repo ships a .claude-plugin manifest, so Claude Code can install all 120 skills at once. Plugin skills are invoked as /<plugin>:<skill>, so they never collide with your own.

/plugin marketplace add Ad-Superpowers/ad-superpowers-plugin
/plugin

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Reproduced in full from Ad-Superpowers/ad-superpowers-plugin/blob/9b6385d2d2d228e4dac096a1d6bc5715c04fa736/plugin/skills/google-ads-competitive-analysis-toolkit/SKILL.md, which is licensed MIT (repository). 823 words, 20 headings.

Competitive Analysis Toolkit

Complete guide for analyzing competition in Google Ads, from Auction Insights interpretation to strategic response to competitor activities.

Pull Competitive Data via MCP

Impression Share Metrics (Campaign Level)

google_ads_run_gaql(query="
  SELECT campaign.name,
         metrics.search_impression_share,
         metrics.search_budget_lost_impression_share,
         metrics.search_rank_lost_impression_share,
         metrics.search_absolute_top_impression_share,
         metrics.search_top_impression_share,
         metrics.average_cpc, metrics.cost_micros
  FROM campaign
  WHERE segments.date DURING LAST_30_DAYS
    AND campaign.status = 'ENABLED'
    AND campaign.advertising_channel_type = 'SEARCH'
  ORDER BY metrics.cost_micros DESC
  LIMIT 20
")

Interpret:

  • search_rank_lost_impression_share rising → competitors increasing bids/QS
  • search_budget_lost_impression_share rising → you are budget-capped
  • search_absolute_top_impression_share dropping → someone pushed you down

Auction Insights (Competitor Domain Data)

The auction_insight resource provides per-competitor overlap, position above, and outranking metrics via GAQL:

google_ads_run_gaql(query="
  SELECT auction_insight.display_domain,
         metrics.auction_insight_search_impression_share,
         metrics.auction_insight_search_overlap_rate,
         metrics.auction_insight_search_position_above_rate,
         metrics.auction_insight_search_outranking_share,
         metrics.auction_insight_search_top_impression_percentage,
         metrics.auction_insight_search_absolute_top_impression_percentage
  FROM auction_insight
  WHERE segments.date DURING LAST_30_DAYS
  ORDER BY metrics.auction_insight_search_impression_share DESC
  LIMIT 20
")

This returns the same data as the UI's Auction Insights report, including competitor domain names. Filter by campaign or ad group for segment-specific analysis.

Auction Insights Metrics

MetricWhat It Measures
Impression Share% of impressions you received vs total available
Overlap Rate% of your impressions where competitor also appeared
Position Above Rate% of overlapping impressions where competitor was above you
Top of Page Rate% of impressions in top positions (above organic)
Abs. Top of Page Rate% of impressions at first position
Outranking Share% of auctions where you ranked above competitor or appeared when they didn't

Outranking Share = (You higher + You appeared, they didn't) / Total eligible auctions.

Interpretation Scenarios

High Overlap, Low Outranking: Competitor targets same keywords and wins more often. Check Quality Score difference, evaluate bid strategy.

Low Overlap, High Impression Share: You dominate this segment with little direct competition. Maintain position, don't overbid.

New Competitor Appears: 40% overlap, 60% position above in first week. Monitor trends, analyze their ads manually.

Competitor IS Rising (yours dropping): Competitor investing more. Evaluate ROI of these keywords — increase bids if profitable, or shift to less competitive segments.

Competitive Benchmark Analysis

Build a benchmark table for top 5 competitors from Auction Insights data (minimum 30 days):

┌──────────────┬───────────┬─────────┬───────────┬────────────┬──────────┐
│ Competitor   │ Imp Share │ Overlap │ Pos Above │ Outranking │ Trend    │
├──────────────┼───────────┼─────────┼───────────┼────────────┼──────────┤
│ You          │ 45%       │ -       │ -         │ -          │ Baseline │
│ Competitor A │ 52%       │ 78%     │ 55%       │ 42%        │ ↑ +5%   │
│ Competitor B │ 38%       │ 65%     │ 35%       │ 58%        │ → Stable│
└──────────────┴───────────┴─────────┴───────────┴────────────┴──────────┘

Threat Score = (Overlap Rate x Position Above Rate) / 100
Example: Competitor A = (78% x 55%) / 100 = 42.9 (HIGH)

Market Share Calculation

Method 1 — Impression Share basis: Your IS = your share of eligible searches. Lost IS (Budget) + Lost IS (Rank) = room to grow.

Method 2 — Relative Share: Your IS / Sum of all known IS. Note: overlap means sum can exceed 100%.

Method 3 — Share of Voice: Your Impressions / Estimated total searches (from Keyword Planner).

Competitive Position Matrix

        HIGH IS
           │
    MARKET │  DOMINANT PLAYERS
    LEADERS│  (large budgets, strong QS — differentiate)
           │
LOW ───────┼─────────── HIGH Position Above
           │
    NICHE  │  AGGRESSIVE CHALLENGERS
    PLAYERS│  (selective but strong — monitor and learn)
           │
        LOW IS

Competitor Strategy Patterns

PatternSignalsYour Response
Aggressive Market ShareTop positions always, broad coverage, aggressive offersDon't match — focus on efficiency and niche
Cherry-PickingHigh position only on specific keywords, low IS overallTest their high-value keywords, learn from selection
Defensive/BrandDominant on brand terms, low non-brand presenceOpportunity on non-brand generics
Promotional SurgeSudden IS increase, aggressive offers, temporaryTrack timing, plan your own promotions around their baseline periods

Competitive response decision tree and tactical responses in references/decision-trees.md. Monitoring setup, weekly review checklist, and Google Ads Script in references/detailed-reference.md.

Output: Competitive Analysis Report Template

# Competitive Analysis Report

## Executive Summary
- **Period:** [Date range]
- **Market position:** [Leader/Challenger/Follower]
- **Key trend:** [Describe]
- **Action required:** [Yes/No + brief explanation]

## Top Competitors
| Competitor | Imp Share | Overlap | Position Above | Outranking | Trend |
|------------|-----------|---------|----------------|------------|-------|
| [You] | [X]% | - | - | - | Baseline |
| [Comp A] | [X]% | [X]% | [X]% | [X]% | [up/down/stable] |

## Competitor Deep Dives
### [Competitor A]
- **Strategy type:** [Aggressive/Selective/Defensive]
- **Observed tactics:** [List]
- **Ad messaging:** [Headlines, offers, USPs]
- **Threat level:** [High/Medium/Low]

## Strategic Recommendations
### Immediate (This Week)
1. [Action] - [Rationale]

### Short-term (This Month)
1. [Action] - [Rationale]

## Monitoring Plan
- **Daily:** CPC and IS changes
- **Weekly:** Auction Insights review, manual spot check
- **Monthly:** Full competitive landscape analysis

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what google-ads-competitive-analysis-toolkit does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.