keyword-research

keyword-research is a skill for Claude Code from itallstartedwithaidea/agent-skills. It costs 25 tokens per session (2,087 once invoked), scanned A, original, MIT.

A Google Ads keyword research procedure for finding, expanding, grouping, and improving search terms for advertising campaigns. A keyword is a word or phrase used to match an advertiser's ad with what someone searches for on Google.

In plain words
What is it for?
Use it to expand seed keywords, find long and competitor-related searches, group terms by intent, choose broad, phrase, or exact matching, and create negative keyword lists from search-term reports.
Why use it?
It helps advertisers cover useful searches while reducing clicks from people who are unlikely to become customers. It also addresses how closely each keyword should match a search and which unwanted searches to exclude.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex.

Part of the google-ads-skills plugin — 12 skills shipped together , and of all-skills

Good fit Use it to expand seed keywords, find long and competitor-related searches, group terms by intent, choose broad, phrase, or exact matching, and create negative keyword lists from search-term reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/itallstartedwithaidea/agent-skills/keyword-research
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 itallstartedwithaidea/agent-skills --skill keyword-research
Clone the repo
git clone --depth 1 https://github.com/itallstartedwithaidea/agent-skills

Made for: Claude Code.

Or install google-ads-skills, the plugin that ships this one along with the rest of its 12 skills.

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 keyword-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/keyword-research/github.svg)](https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/keyword-research)
Your own site
<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/keyword-research"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/keyword-research/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 keyword-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/keyword-research"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/keyword-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,087 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 $0.00025 $0.02087
Opus 5 $0.00013 $0.01043
Sonnet 5 $0.00005 $0.00417
Haiku 4.5 $0.00003 $0.00209

Measured 10d ago against content hash 20d7ab29288c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

keyword-research 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 10d 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/google-ads/keyword-research/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Keyword Research

Part of Agent Skills™ by googleadsagent.ai™

Description

The Keyword Research skill delivers a systematic approach to keyword discovery, expansion, and optimization for Google Ads campaigns. Starting from seed keywords, it builds comprehensive keyword universes through multiple expansion vectors: semantic variations, competitor keyword mining, search term report analysis, long-tail discovery, and intent-based grouping. The result is a structured keyword strategy that maximizes relevant coverage while minimizing wasted spend.

Match type selection is a critical component. The skill evaluates each keyword against conversion probability, search volume, competition intensity, and cost-per-click economics to recommend the optimal match type. Broad match keywords are paired with smart bidding strategies, phrase match captures high-intent variations, and exact match locks in proven converters. The skill continuously refines match type assignments based on search term report feedback loops.

Negative keyword management is equally important. The skill mines search term reports for irrelevant queries, builds hierarchical negative keyword lists (account-level, campaign-level, ad-group-level), and maintains shared negative keyword lists across campaigns. Proactive negative keyword discovery prevents budget waste before it occurs by identifying common irrelevant query patterns for each industry vertical.

Use When

  • User asks for "keyword research" or "keyword ideas"
  • User wants to "expand keywords" or "find new keywords"
  • User mentions "negative keywords" or "search term mining"
  • User asks about "match types" (broad, phrase, exact)
  • User wants to "reduce wasted spend" on irrelevant queries
  • User asks to "build a keyword list" or "keyword strategy"
  • User mentions "keyword grouping" or "ad group structure"
  • User wants "long-tail keywords" or "low competition keywords"
  • User asks to "analyze search terms" or "query mining"

Read the full file on GitHub · 227 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. 10d ago First seen · 227 lines · 25 tokens per session scan A 20d7ab29288c

Subscribe to this mod's changes

keyword-research is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (37 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 2,087 once invoked, about $0.0001 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.