Borrowing it
Nothing to install: this file belongs to upgrade-ventures/upgradeseo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/upgrade-ventures/upgradeseo/main/.agents/skills/keyword-research/SKILL.mdgit clone --depth 1 https://github.com/upgrade-ventures/upgradeseoWrote 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/upgrade-ventures/upgradeseo/keyword-research)<a href="https://agentmods.dev/skills/upgrade-ventures/upgradeseo/keyword-research"><img src="https://agentmods.dev/badge/skills/upgrade-ventures/upgradeseo/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/upgrade-ventures/upgradeseo/keyword-research"><img src="https://agentmods.dev/badge/skills/upgrade-ventures/upgradeseo/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 | $0.00020 | $0.00981 |
| Opus 5 | $0.00010 | $0.00491 |
| Sonnet 5 | $0.00004 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
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 8d 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.
This is a copy
97% identical to keyword-research — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UpgradeSEO Keyword Research
Goal
Turn seed topics into a prioritized keyword opportunity set using UpgradeSEO MCP data. The output should help the user decide what to target, what to save, and what to research next.
Required inputs
projectId- One or more seed topics, products, pages, competitors, or audience problems
- Optional market/location/language
If projectId is missing, use list_projects first. If the target market/location/language is unclear and would materially affect keyword metrics, ask the user; otherwise use the MCP tool defaults.
UpgradeSEO MCP tools
research_keywords: primary discovery tool. Use 1-5 seeds per call and prefer 150 results unless the user asks for exhaustive research.get_keyword_metrics: hydrate up to 700 known keywords with volume, keyword difficulty (KD), search intent, CPC, and monthly trends in one call. Use it to score candidate or known terms — including the Search Console striking-distance queries from step 1.get_ranked_keywords: pull exact ranking keyword rows when a target domain or page is part of the research brief.get_search_console_performance: when Search Console is connected, start from the project's real first-party demand — queries already earning impressions and near-ranking ("striking distance") terms. Request a highrowLimitand filter average position 5-20 client-side, since the API sorts by clicks and can't filter by position. Then hydrate those striking-distance queries withget_keyword_metricsto attach difficulty and intent.get_serp_results: inspect SERPs for the top candidate terms, especially when intent is ambiguous.search_local_businesses,get_local_serp_results, andget_google_business_questions: use for local SEO topics when a business/location radius matters.list_saved_keywords: avoid duplicating already-saved work or use existing tags as context.save_keywords: save selected keywords only after explicit user confirmation.
Workflow
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.
- 8d ago First seen · 71 lines · 20 tokens per session scan A 5d31e59fa975
keyword-research is a skill published in the GitHub repository upgrade-ventures/upgradeseo (1 stars, last pushed 22d ago), licensed MIT. It adds 20 tokens to every session and 981 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to keyword-research, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
semrush-backlink-audit
Audit backlink profiles with the semrush CLI. Use when the user asks for backlink analysis, referring domains, authority score, anchor text, indexed linked pages, backlink competitors, link gaps, backlink history, toxic or suspicious link signals, or off-page SEO recommendations based on Semrush CLI backlink data.
semrush-batch-workflows
Create, estimate, run, and adapt semrush CLI TOML batch recipes. Use when the user needs reusable Semrush CLI workflows, competitor audit recipes, keyword opportunity recipes, backlink audit recipes, paid-search recipes, traffic summary recipes, scheduled SEO data pulls, or API-unit estimates before multi-step Semrush…
semrush-cli-setup
Install, configure, validate, and troubleshoot the semrush CLI. Use when the user needs Semrush API auth, SEMRUSHAPIKEY or SEMRUSHOAUTHTOKEN setup, output/cache/rate-limit configuration, shell completions, API balance checks, structured error handling, or a prerequisite check before running other Semrush CLI skills.
semrush-competitor-research
Analyze SEO competitors, organic keywords, top pages, subdomains, and keyword gaps with the semrush CLI. Use when the user asks for competitor research, organic competitor discovery, content gaps, domain comparison, missing or untapped keywords, page-level SEO opportunities, or a competitive SEO audit using Semrush…
semrush-keyword-research
Research, expand, score, and prioritize SEO keywords with the semrush CLI. Use when the user asks for keyword research, search volume, CPC, difficulty, related keywords, broad-match keywords, question keywords, keyword clustering inputs, SERP domains for a query, or a prioritized keyword opportunity table powered by…
semrush-local-seo
Manage and analyze local SEO data with semrush CLI v4 commands. Use when the user asks for Semrush local listings, local business location records, Google Maps or map-rank campaigns, map-rank keywords, heatmaps, local competitors, NAP/listing QA, or local SEO reporting through the Semrush CLI.