agentleFS
kastriasanikastriasani/google-ads-skills/skills/google-ads-competitor-intel/SKILL.md

google-ads-competitor-intel

Skill1 starsChanged 5 months agoMITView on GitHub

Competitor conquesting and a client-ready paid-search battlecard for Google Ads. Builds a win, tie, and loss matrix vs each competitor, derives USP headlines and which competitors to attack or avoid, generates conquesting keyword sets (competitor alternative, competitor vs brand, tools like competitor, switch from competitor, competitor pricing) with match types and an RSA angle per cluster, and flags trademark and policy caution on naming competitors in ad text. Use when the user wants to research competitors for paid search, build a battlecard, conquest a competitor, bid on competitor terms, create alternative or vs keywords, find their USP against rivals, or read auction insights. Trigger phrases include competitor intel, conquesting, competitor keywords, battlecard, competitor alternative ads, and how do we compare on Google Ads.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run google-ads-keyword-research for the core (non-conquest) plan and google-ads-research for the broader market picture.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Google Ads Competitor Intel

Turn competitor research into two paid-search assets: a win/tie/loss battlecard that tells you which competitors to attack and which USP headlines to lead with, and a set of conquesting keyword clusters with match types, RSA angles, and trademark guidance. The point is to capture switchers and comparison shoppers profitably, not to pay to send buyers to a page where you lose the comparison.

When to use

  • The user wants to conquest a competitor, bid on competitor terms, or build alternative/vs keyword sets.
  • The user needs a client-ready paid-search battlecard or wants to know their USP against named rivals.
  • The user is reading Auction Insights and wants to decide where to push, hold, or pull back against competitors.

Run google-ads-keyword-research for the core (non-conquest) plan and google-ads-research for the broader market picture; this skill owns the competitor-facing slice.

Workflow

  1. Build the win/loss battlecard. Capture your offer's capabilities vs each competitor as JSON (offer, onboarding, support, capability, security), then: python3 scripts/competitor_gap_matrix.py --input matrix.json --markdown It computes per-competitor win rates and outputs three decision lists: advantages (your USP headlines for RSAs and conquest copy), gaps (claims to avoid in ad text), and parity (win on price/proof/offer instead). It flags which competitors to attack (you win clearly) and which to avoid. --demo runs on sample data; --json for pipelines.
  2. Decide who to conquest from the matrix. Attack competitors where your win rate is 60%+, be selective at 40-60%, and avoid conquesting any competitor you trail; sending comparison shoppers to a losing page wastes budget. See references/conquesting-playbook.md.
  3. Generate conquesting keyword sets: python3 scripts/conquest_keyword_builder.py --brand FlowDesk --competitors "Asana, Monday" For each competitor it builds five clusters -- alternative, vs, tools-like, switch, and pricing -- each with suggested match types, an RSA angle, and a per-cluster trademark caution. --demo and --json supported.
  4. Apply the trademark and policy rules. Bidding on a competitor trademark as a keyword is generally allowed; using it in ad text is restricted and can be disapproved or complained against. Default to keeping the competitor name in the keyword and landing page, and keep ad text about your own brand and benefits unless rights are confirmed.
  5. Pair every conquest cluster with a matching landing page (alternative, vs, migration) and lead with a USP headline from step 1 plus a risk-reversal offer. Generic homepages tank Quality Score and conversion on conquest traffic.
  6. Measure with Auction Insights. Use overlap rate to find your real rivals, position-above-rate and outranking share to see if conquesting is working, and separate budget-limited from rank-limited impression-share loss before changing bids. See references/auction-insights.md.

Inputs and data sources

Both scripts run standalone, stdlib only.

  • competitor_gap_matrix.py: a JSON matrix of your status vs each competitor per feature/offer dimension.
  • conquest_keyword_builder.py: your brand and a list of competitor names.

Optional sources sharpen the work:

  • Google Ads Auction Insights: real overlap, impression share, and outranking data to prioritize and validate conquesting.
  • Web search: competitor pricing, positioning, reviews, and release notes to fill the matrix and find switching pains.
  • Google Ads Keyword Planner: volume and competition on conquest terms.
  • Google Sheets / BigQuery: store the matrix and conquest plan.

Outputs

  • A paid-search battlecard: per-competitor win/tie/loss, win rate, conquest action (attack/selective/avoid), a feature matrix, USP headlines, and claims to avoid (markdown or JSON).
  • Conquesting keyword sets per competitor (five clusters each) with match types, RSA angles, and trademark cautions.

References

  • conquesting-playbook.md: the four conquesting page/keyword formats, which competitors to attack vs avoid, copy rules, and trademark/policy guidance.
  • auction-insights.md: how to read impression share, lost IS (rank vs budget), overlap rate, position-above-rate, and outranking share, and the action each implies.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.