keyword-research-workflow

keyword-research-workflow is a skill for Claude Code, Codex from smythmyke/jackpotkeywords-mcp-server. It costs 85 tokens per session (1,120 once invoked), scanned A, original, MIT.

A workflow for researching search terms for a product or website using Google Ads Keyword Planner data. It can also guide SEO reviews and checks of whether AI assistants recommend a site.

In plain words
What is it for?
Use it for SEO keyword ideas, Google Ads planning, low-competition keyword research, SEO audits, keyword clusters, or AI-visibility checks.
Why use it?
It turns a plain-language product description or URL into prioritized search opportunities, so users do not need to invent seed keywords first. Different report levels provide different amounts of competitive and grouping analysis.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it for SEO keyword ideas, Google Ads planning, low-competition keyword research, SEO audits, keyword clusters, or AI-visibility checks.

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

Made for: Claude Code, Codex.

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-workflow

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/smythmyke/jackpotkeywords-mcp-server/keyword-research-workflow"><img src="https://agentmods.dev/badge/skills/smythmyke/jackpotkeywords-mcp-server/keyword-research-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,120 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 $0.00085 $0.01120
Opus 5 $0.00043 $0.00560
Sonnet 5 $0.00017 $0.00224
Haiku 4.5 $0.00009 $0.00112

Measured 10d ago against content hash 88581c2b9524, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

keyword-research-workflow 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/keyword-research-workflow/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Keyword Research Workflow

Guide for using the JackpotKeywords MCP connector to turn a plain-English product description — or just a URL — into a prioritized keyword strategy backed by real Google Ads Keyword Planner data. JackpotKeywords starts from what the product does (no seed keywords needed), scores every keyword 0–100, and also offers SEO audits and AI-visibility (AEO) scans.

When to use this skill

Trigger when the user mentions any of: "keyword research", "what keywords should I target", "SEO keywords for my product/site", "Google Ads keywords", "keyword ideas", "low-competition keywords", "audit my site's SEO", "does ChatGPT/AI recommend my site", or describes a product and asks how people would search for it.

Core workflow (description → strategy)

  1. Choose the research tier.

    • jackpotkeywords_recommend — the standard report. Free, but limited to one per account per month; check jackpotkeywords_usage_status if unsure whether the allowance is spent.
    • jackpotkeywords_recommend_deep ($0.30) — everything in the standard report PLUS competitor discovery, keyword clusters, and per-category aggregates. Prefer this when the user wants the competitive picture or a content/campaign plan, not just a keyword list.
    • Input: a plain-English description and/or the product url (at least one). Pass location for local businesses and budget (daily USD) for ad planning — both improve scoring.
  2. Poll for the report. Research tools return a job_id immediately; the pipeline takes 1–3 minutes. Call jackpotkeywords_get_report with that id, waiting ~30 seconds between polls. Don't hammer it — two or three patient polls beat ten rapid ones. Failed jobs refund automatically.

  3. Interpret the data for the user.

    • Jackpot Score (0–100): composite of search volume, CPC, competition, trend, autocomplete depth, and AI relevance to this product. 75+ is a strong target.
    • $0.00 CPC means Google returned no advertiser bid data — promising but unproven, NOT free clicks. Say so when recommending those keywords.
    • Intent labels: commercial/transactional → ads + product pages; informational → blog/how-to content; navigational competitor terms → comparison pages only.
    • Clusters (deep report): each cluster is one content target — recommend one page per cluster, not one page per keyword. keywordCount is the true cluster size (the keyword list shown is a sample).
    • Competitors (deep report): use competitor-brand and alternative keywords for comparison/alternative pages; warn that bidding on brand terms means fighting an established player.

Read the full file on GitHub · 88 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 · 88 lines · 85 tokens per session scan A 88581c2b9524

Subscribe to this mod's changes

keyword-research-workflow is a skill published in the GitHub repository smythmyke/jackpotkeywords-mcp-server (0 stars, last pushed 3mo ago), licensed MIT. It adds 85 tokens to every session and 1,120 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens