Agent skill

Google Ads Negatives

by TheMattBerman in TheMattBerman/google-ads-copilot

Recommend negative keywords for Google Ads with the right match type, scope, and caution.

MITAuto-check passedMarketing & SEO

Install Google Ads Negatives

skills CLI
$ npx skills add TheMattBerman/google-ads-copilot --skill google-ads-negatives -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install TheMattBerman/google-ads-copilot google-ads-negatives --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/TheMattBerman/google-ads-copilot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/google-ads-negatives .claude/skills/google-ads-negatives && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
google-ads-negatives
GitHub stars
238
Token cost
~2.3k tokens
SKILL.md length
952 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
MIT

At a glance

Recommend negative keywords for Google Ads with the right match type, scope, and caution.

  • Works in 12 steps: Announce mode (connected/export). → Load existing negatives from MCP query… → In connected mode, run the shared… → …
  • Tasks that involve Paid advertising
  • SKILL.md covers Data Acquisition, Process, Draft Output and Output Shape, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Google Ads Negatives is an agent skill from TheMattBerman/google-ads-copilot. Recommend negative keywords for Google Ads with the right match type, scope, and caution. Pulls live data via MCP or works with manual exports. Always produces a negative keyword draft for human review.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO, covering Paid advertising. It works with Google Ads and Model Context Protocol. The repository describes itself as: Google Ads Copilot: operator kit for audits, MCP-connected reads, export-mode analysis, and draft/apply workflows. The licence is MIT.

When your agent uses it

  • Tasks that involve Paid advertising

Example prompts

  • “/google-ads-negatives”

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

  1. Announce mode (connected/export).
  2. Load existing negatives from MCP query or workspace/ads/negatives.md.
  3. In connected mode, run the shared retrieval ladder (data/search-term-retrieval.md). Report retrieval_mode in the output header.
  4. Run the shared negative-inventory verification (data/negative-inventory.md / scripts/negative-inventory.sh) so you know whether negatives…
  5. If retrieval mode is pmax-fallback, only recommend negatives for extremely obvious junk terms. If limited, do not recommend negatives…
  6. Review query evidence and recurring waste clusters.
  7. Cross-reference against existing negatives — never recommend what's already excluded.
  8. Cross-reference against keyword_view when keyword rows are available — for each waste cluster, check which targeted keyword(s) triggered…
  9. For each waste cluster, decide: exclusion, isolation, or keyword fix?
  10. For each recommended negative
  11. Use the negative recommendation template from deliverable-templates.md.
  12. Write/update workspace memory.

What it can do on your machine

Read from SKILL.md and the folder at commit 2c253ee. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are sql).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Google Ads Negatives loads about 2.3k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 952 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from TheMattBerman/google-ads-copilot at commit 2c253ee, republished under its MIT licence (© TheMattBerman). 952 words, ~2,319 tokens.

Download SKILL.mdSave it as .claude/skills/google-ads-negatives/SKILL.md (or your agent's skills folder).
name
google-ads-negatives
description
Recommend negative keywords for Google Ads with the right match type, scope, and caution. Pulls live data via MCP or works with manual exports. Always produces a negative keyword draft for human review.

Google Ads Negatives

Read first:

  • google-ads/references/operator-thesis.md
  • google-ads/references/query-patterns.md
  • google-ads/references/negatives-playbook.md
  • google-ads/references/intent-map.md
  • google-ads/references/deliverable-templates.md
  • data/negative-inventory.md

Read workspace if available:

  • workspace/ads/account.md
  • workspace/ads/goals.md
  • workspace/ads/intent-map.md
  • workspace/ads/queries.md
  • workspace/ads/negatives.md
  • workspace/ads/learnings.md

Data Acquisition

Connected Mode (MCP available)

Pull via the search tool on google-ads-mcp:

Primary: Search terms with waste signals — last 30 days:

sql
SELECT
  search_term_view.search_term,
  search_term_view.status,
  campaign.name,
  ad_group.name,
  metrics.impressions,
  metrics.clicks,
  metrics.cost_micros,
  metrics.conversions,
  metrics.conversions_value,
  metrics.cost_per_conversion
FROM search_term_view
WHERE segments.date DURING LAST_30_DAYS
ORDER BY metrics.cost_micros DESC
LIMIT 500

Retrieval ladder — if the primary query returns no rows, follow the shared retrieval ladder in data/search-term-retrieval.md. In pmax-fallback mode, only recommend negatives for extremely obvious junk terms — do not recommend exact negatives without per-term metrics. In limited mode, do not recommend negatives at all — ask for a UI export.

Required: Existing campaign-level negatives:

sql
SELECT
  campaign.name,
  campaign_criterion.keyword.text,
  campaign_criterion.keyword.match_type,
  campaign_criterion.negative
FROM campaign_criterion
WHERE campaign_criterion.negative = TRUE
  AND campaign_criterion.type = 'KEYWORD'

Required: Negative inventory verification (all locations): Use the shared verification path in data/negative-inventory.md / scripts/negative-inventory.sh to check:

  • campaign-level negatives
  • ad-group-level negatives
  • shared negative lists
  • campaign/shared-list attachments
  • shared-list keyword members

Required: Keyword view (understand what's triggering waste):

sql
SELECT
  campaign.name,
  ad_group.name,
  ad_group_criterion.keyword.text,
  ad_group_criterion.keyword.match_type,
  ad_group_criterion.status,
  metrics.impressions,
  metrics.clicks,
  metrics.cost_micros,
  metrics.conversions
FROM keyword_view
WHERE campaign.status = 'ENABLED'
  AND ad_group.status = 'ENABLED'
  AND segments.date DURING LAST_30_DAYS
ORDER BY metrics.cost_micros DESC
LIMIT 200

Why keyword_view matters for negatives:

  • A wasteful search term may be caused by a single over-broad keyword — pausing or narrowing that keyword is sometimes better than adding a negative
  • Keyword match types reveal WHY certain search terms are matching — helps assess whether the negative or the keyword is the better fix
  • Cross-referencing keywords with search terms reveals the "blast radius" of each keyword — how many waste terms it's generating

Required: Existing shared negative keyword lists:

sql
SELECT
  shared_set.name,
  shared_set.type,
  shared_set.member_count,
  shared_set.status
FROM shared_set
WHERE shared_set.type = 'NEGATIVE_KEYWORDS'
  AND shared_set.status = 'ENABLED'

See data/gaql-recipes.md for additional queries.

Date Range Fallback

If LAST_30_DAYS returns 0 rows or <$5 total spend, fall back to LAST_90_DAYS, then all-time (no date filter). Negative keyword analysis is LESS time-sensitive than budget analysis — historical waste patterns are still actionable even if the data is older. Always state the date range used.

Export Mode (no MCP)

Ask the user for:

  • Search Terms report: last 30 days (sorted by Cost descending)
  • Current negative keyword list (campaign-level and shared lists)

See data/export-formats.md for recommended format.


Process

  1. Announce mode (connected/export).
  2. Load existing negatives from MCP query or workspace/ads/negatives.md.
  3. In connected mode, run the shared retrieval ladder (data/search-term-retrieval.md). Report retrieval_mode in the output header.
  4. Run the shared negative-inventory verification (data/negative-inventory.md / scripts/negative-inventory.sh) so you know whether negatives already exist at campaign, ad-group, or shared-list level.
  5. If retrieval mode is pmax-fallback, only recommend negatives for extremely obvious junk terms. If limited, do not recommend negatives — ask for a UI export.
  6. Review query evidence and recurring waste clusters.
  7. Cross-reference against existing negatives — never recommend what's already excluded.
  8. Cross-reference against keyword_view when keyword rows are available — for each waste cluster, check which targeted keyword(s) triggered it. If a single broad-match keyword generates most of the waste, consider recommending keyword narrowing (change to phrase/exact, or pause) alongside or instead of negatives.
  9. For each waste cluster, decide: exclusion, isolation, or keyword fix?
    • Exclusion: the traffic has no plausible path to value → negative it
    • Isolation: the traffic has potential but is in the wrong bucket → recommend structure change instead
    • Keyword fix: the triggering keyword is too broad → recommend match type change or pause
  10. For each recommended negative:
    • Choose match type (exact → phrase → broad, in order of safety)
    • Choose scope (ad group → campaign → shared list, in order of precision)
    • Assess collateral risk (what good traffic could this block?)
    • Note spend evidence (how much was wasted on this pattern?)
  11. Use the negative recommendation template from deliverable-templates.md.
  12. Write/update workspace memory.

Draft Output

Negative Keyword Draft — ALWAYS PRODUCED

This skill's primary deliverable is a negative keyword draft. Every run that identifies exclusion-worthy terms produces one.

Create using drafts/templates/negative-draft.md:

  • Write to workspace/ads/drafts/YYYY-MM-DD-[account-slug]-negatives.md
  • Include every recommended negative with all fields: keyword, match type, scope, reason, spend wasted, collateral risk, reversibility
  • Group negatives by theme (e.g., "Job-seeker exclusions," "Informational queries," "Competitor brand terms")
  • Update workspace/ads/drafts/_index.md
  • Announce: "Draft created: workspace/ads/drafts/YYYY-MM-DD-[account-slug]-negatives.md — N negatives for [scope description]"
Show full SKILL.md (347 more words)Show less
Negatives to REMOVE

The draft template now includes three sections: Add, Remove, and Narrow/Move.

When to recommend removal:

  • An existing negative is blocking traffic that matches the business's actual services (e.g., "brick" negative on a brick recycling company)
  • A broad-match negative is suppressing queries that more specific negatives would handle better
  • Business services have changed since the negative was added (e.g., company now offers junk removal but had "junk" as a negative)
  • A negative was auto-generated (common in Smart campaigns) and doesn't reflect operator intent

When to recommend narrowing:

  • A phrase-match negative is correct in concept but too aggressive in scope (e.g., "free" as phrase match blocking "free estimate" queries)
  • A campaign-level negative should be ad-group-level (or vice versa)
  • A broad-match negative should be phrase or exact

Always cross-reference existing negatives against:

  1. The business's actual services (from workspace/ads/account.md)
  2. Converting search terms (from the search terms report)
  3. The Intent Map (from workspace/ads/intent-map.md)
If isolation is the better answer

When the analysis reveals that traffic doesn't need exclusion but rather better routing:

  • Note this in the negative draft's Dependencies section
  • Create a supplementary structure draft using drafts/templates/structure-draft.md
  • Link the two drafts to each other
Always update workspace memory:
  • workspace/ads/negatives.md — updated negative list (proposed + existing)
  • workspace/ads/queries.md — waste patterns identified
  • workspace/ads/findings.md — strategic notes

Output Shape

  1. Account Status block — account name, CID, status, date range used, tracking confidence, mode
  2. Existing negatives summary (what's already excluded, any harmful ones flagged)
  3. Waste analysis (clusters, patterns, spend amounts)
  4. Exclusion vs. isolation decisions (with reasoning)
  5. Recommended negatives (summary table)
  6. Draft created (path and summary)
  7. Confidence assessment
  8. Memory updates

Rules

  • Do not negative underperformance when the real issue is structure or copy.
  • Do not recommend broad negatives casually.
  • Always note collateral risk.
  • Always say when confidence is low.
  • Exact match is safest. Phrase match is the default. Broad match negative is a last resort.
  • Campaign-level negatives are fine for focused campaigns. Shared lists are better for account-wide exclusion themes.
  • Every negative draft is a decision document, not a wish list. Each entry must be individually justified.

© TheMattBerman, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/google-ads-negatives of TheMattBerman/google-ads-copilot.

Open the folder on GitHubat commit 2c253ee

Compare with similar skills

Google Ads Negatives next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Google Ads Negatives compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Google Ads Negatives this skillTheMattBerman/google-ads-copilot238—~2.3kAutomated safety check: PassMIT
Google Ads Landing Page Auditnowork-studio/notfair-plugin3.9k—~306Automated safety check: PassMIT
Google Ads API MCP Setupgoogle/skills21k—~6.1kAutomated safety check: NotesApache-2.0
21 Audit Ads Performanceminhnv0807/ai-business-skills609—~4.6kAutomated safety check: PassMIT
Blog GoogleAgriciDaniel/claude-blog2.3k1 repos~3.3kAutomated safety check: NotesMIT
AdsCesarjoquin/Marketing-Skills2021 repos~3.5kAutomated safety check: PassMIT

Similar skills

  • Google Ads Landing Page Audit

    nowork-studio/notfair-plugin

    Scores Google Ads landing pages on five weighted dimensions and diagnoses why high-CTR ad groups convert poorly, with concrete fixes for each page.

    3.9k GitHub stars~306 tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Official

    Guides developers through downloading, configuring, and installing the official open-source Google Ads MCP Server.

    21k GitHub stars~6.1k tokensUpdated yesterday
    Marketing & SEOAuto-check: notes
  • 21 Audit Ads Performance

    minhnv0807/ai-business-skills

    Dung khi can ra soat CAU HINH tai khoan quang cao mot cach he thong — 6 khau tu account, campaign, adset, creative, landing den tracking, cham Health Score 0-100 va liet ke Quick Wins.

    609 GitHub stars~4.6k tokensUpdated 29 days ago
    Marketing & SEOAuto-check passed
  • Blog Google

    AgriciDaniel/claude-blog

    Google API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity…

    2.3k GitHub starsUsed in 1 repo~3.3k tokens
    Marketing & SEOAuto-check: notes
  • Ads

    Cesarjoquin/Marketing-Skills

    When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms.

    202 GitHub starsUsed in 1 repo~3.5k tokens
    Marketing & SEOAuto-check passed
  • Ads

    coreyhaines31/marketingskills

    When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms.

    54k GitHub starsUsed in 1 repo~7k tokens
    Marketing & SEOAuto-check passed

More from TheMattBerman/google-ads-copilot

All 16 skills in this repo
  • Google Ads

    TheMattBerman/google-ads-copilot

    Google Ads operator system for search-term analysis, intent mapping, wasted spend control, account structure decisions, tracking diagnostics, RSA generation, budget review, account planning, and…

    238 GitHub stars~4.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Google Ads Apply

    TheMattBerman/google-ads-copilot

    Execute approved draft actions in Google Ads accounts. An agent skill from TheMattBerman/google-ads-copilot.

    238 GitHub stars~2.7k tokensUpdated 4 mo ago
    Auto-check passed
  • Google Ads Audit

    TheMattBerman/google-ads-copilot

    Full Google Ads review that synthesizes tracking, search terms, intent mapping, negatives, structure, RSAs, budget decisions, and PMax context into a single operator read.

    238 GitHub stars~2.7k tokensUpdated 4 mo ago
    Auto-check passed
  • Google Ads Budget

    TheMattBerman/google-ads-copilot

    Review Google Ads budget allocation and scaling decisions based on signal quality, intent clarity, tracking confidence, and structural health.

    238 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Google Ads Connect

    TheMattBerman/google-ads-copilot

    Connected-mode onboarding, health check, and customer selection for Google Ads Copilot.

    238 GitHub stars~2.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Google Ads Daily

    TheMattBerman/google-ads-copilot

    Daily operator review for Google Ads. An agent skill from TheMattBerman/google-ads-copilot.

    238 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Google Ads Negatives

What does Google Ads Negatives do?

Recommend negative keywords for Google Ads with the right match type, scope, and caution. Google Ads Negatives is an agent skill from TheMattBerman/google-ads-copilot. Recommend negative keywords for Google Ads with the right match type, scope, and caution.

When should I use Google Ads Negatives?

Google Ads Negatives fits situations like: tasks that involve Paid advertising.

How do I install Google Ads Negatives in Claude Code?

Run `npx skills add TheMattBerman/google-ads-copilot --skill google-ads-negatives -a claude-code`. Or copy the skill folder (skills/google-ads-negatives in TheMattBerman/google-ads-copilot) into .claude/skills/google-ads-negatives in your project. Claude Code loads it when a task matches its description.

How do I install Google Ads Negatives in Codex?

Run `npx skills add TheMattBerman/google-ads-copilot --skill google-ads-negatives -a codex`. Or copy the skill folder (skills/google-ads-negatives in TheMattBerman/google-ads-copilot) into .agents/skills/google-ads-negatives in your project. Codex loads it when a task matches its description.

Can I use Google Ads Negatives in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TheMattBerman/google-ads-copilot --skill google-ads-negatives -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/google-ads-negatives, .gemini/skills/google-ads-negatives, .github/skills/google-ads-negatives and .opencode/skills/google-ads-negatives in your project.

What does Google Ads Negatives need to run?

SKILL.md names no scripts, command-line tools or credentials: Google Ads Negatives is instructions for the agent only.

Does Google Ads Negatives access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Google Ads Negatives safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Google Ads Negatives use?

Google Ads Negatives is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Google Ads Negatives use?

About 2.3k tokens (SKILL.md is roughly 9.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Google Ads Negatives?

Skills that share tags, products or a category with Google Ads Negatives: Google Ads Landing Page Audit (nowork-studio/notfair-plugin, 3.9k stars), Google Ads API MCP Setup (google/skills, 21k stars), 21 Audit Ads Performance (minhnv0807/ai-business-skills, 609 stars) and Blog Google (AgriciDaniel/claude-blog, 2.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Google Ads Negatives?

TheMattBerman (a GitHub user) maintains it in TheMattBerman/google-ads-copilot, which has 238 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on June 10, 2026.

Source: TheMattBerman/google-ads-copilot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.