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.
npx skills add itallstartedwithaidea/agent-skills --skill keyword-researchgit clone --depth 1 https://github.com/itallstartedwithaidea/agent-skillsWrote 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.
[](https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/keyword-research)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.02087 |
| Opus 5.5 | $0.00010 | $0.00835 |
| Sonnet 5.5 | $0.00005 | $0.00417 |
| Haiku 4.5 | $0.00003 | $0.00209 |
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 1mo 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.
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"
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.
- 1mo ago First seen · 227 lines · 25 tokens per session scan A 20d7ab29288c
keyword-research is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (44 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 2,087 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
tracking-health
Preventive audit of conversion tracking across all configured ad platforms — Meta pixels + CAPI, Google Ads conversion actions, and final-URL tracking-parameter consistency on every platform — with a GA4 cross-check. Use when the user asks to check tracking, audit conversion measurement, verify pixels / tags, check…
learn
Save a marketing diagnosis insight to the pro-diagnosis knowledge base so it is applied in future operations across all platforms. Use when the user runs /learn, explicitly teaches the agent a marketing insight, corrects the agent's analysis, or asks to remember/record an operational learning for next time. Also use…
adspirer-amazon-ads
Create and manage Amazon Ads through Adspirer — Sponsored Products, Sponsored Brands, and Sponsored Display, with ASIN targeting, search-term reports, ACoS, and bid optimization. Use for anything on Amazon Advertising or Seller/Vendor Central ads.
weekly-report
A skill that creates a weekly marketing-operations summary across connected platforms. It reviews logged actions and strategy information to produce a recap.
review-stack
Stack review of one or more third-party tools (OXC, TanStack, Vite, cf, Sentry, pnpm, Claude Code...) against current official best practices, or of what a dependency bump brings (bumped): one parallel subagent per tool, verified findings, one consolidated plan in chat. USE WHEN: user runs /review-stack or explicitly…
sealeap-amazon-product-targeting
An Amazon Ads planning skill for targeting product pages and categories, including competitor, complementary, upsell, and own-product traffic.