keyword-research

keyword-research is a skill for Claude Code from unifapi-agent/agents. It costs 113 tokens per session (2,576 once invoked), scanned A, original, MIT.

A research workflow for finding search terms, related topics, and competitor keyword opportunities using current search-result evidence.

In plain words
What is it for?
Use it to expand seed terms, compare competitor rankings, identify gaps, and organize keywords into topic groups.
Why use it?
It helps replace an unranked list of ideas with topics that have search demand, a clear purpose, and a reason they may be achievable.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the unifapi plugin — 47 skills, 1 MCP server shipped together

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.

agentmods
npx agentmods add skills/unifapi-agent/agents/keyword-research
Any agent
npx skills add unifapi-agent/agents --skill keyword-research
Clone the repo
git clone --depth 1 https://github.com/unifapi-agent/agents

Made for: Claude Code.

Or install unifapi, the plugin that ships this one along with the rest of its 47 skills, 1 MCP server.

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/unifapi-agent/agents/keyword-research.svg)](https://agentmods.dev/skills/unifapi-agent/agents/keyword-research)
Your own site
<a href="https://agentmods.dev/skills/unifapi-agent/agents/keyword-research"><img src="https://agentmods.dev/badge/skills/unifapi-agent/agents/keyword-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,576 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00113 $0.02576
Opus 5 $0.00056 $0.01288
Sonnet 5 $0.00023 $0.00515
Haiku 4.5 $0.00011 $0.00258

Measured 6d ago against content hash bfff15f7b92e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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/seo-agent/keyword-research/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Keyword Research

You are a keyword strategist. Your goal is to turn a seed list (or a competitor domain) into a ranked, defensible set of keyword opportunities and topic clusters — each backed by live SERP and volume evidence, not a scraped keyword dump or a black-box "difficulty" number.

This is an enhanced skill: it reads live public data through UnifAPI. Every keyword in the output carries a volume figure, an intent label, and a winnability read pulled from a real SERP, so the operator can defend the priority order instead of trusting a vendor score.

Use UnifAPI for live evidence

A scraped keyword list tells you nothing about whether you can win the query. The expansion, the metrics, and the SERP all have to come from the same live source so they're comparable. Use the unifapi skill to connect (OAuth MCP), then call the operations below, grouped by job. Pass location + language consistently across every call.

  • EXPAND the seed setseo/keywords/ideas (same-category terms from a seed), seo/keywords/related (semantically related queries), seo/keywords/suggestions (long-tail queries containing the seed), seo/keywords/autocomplete (live autocomplete). Run all four and dedupe to widen coverage beyond the obvious head terms.
  • SCORE every candidateseo/keywords/overview (volume + CPC + competition + KD + intent in one pull — the primary metrics call), seo/keywords/difficulty (isolated 0–100 top-10 chance), seo/keywords/intent (informational / navigational / commercial / transactional with probabilities), seo/keywords/history (12-mo trend → seasonality).
  • OWN-SITE baselineseo/keywords/for-site lists what the target domain already ranks for, so you don't recommend what it already owns and can spot striking-distance pages.
  • GAP vs competitorsseo/competitors/domain (find the real organic competitors first), seo/competitors/ranked-keywords (every query a competitor ranks for, with position + URL), seo/competitors/domain-intersection (queries two domains both rank for — set the target as one side to find what it's missing), seo/competitors/page-intersection (pages competing for shared queries).
  • SERP shape (winnability)seo/serp with target set to the user's domain returns the organic results, target visibility, SERP features (PAA, AI Overview, video, local pack), and current target position. This is what grounds the winnability score.

Read the full file on GitHub · 104 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 104 lines · 113 tokens per session scan A bfff15f7b92e

Subscribe to this mod's changes

keyword-research is a skill published in the GitHub repository unifapi-agent/agents (559 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 2,576 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

orangeo-ai-visibility-skill

Audit brand AI visibility readiness and prepare OranGEO-style GEO, AEO, LLM SEO, and AI search optimization action plans. Use when asked for a Claude Code skill, Codex skill, GEO skill, generative engine optimization skill, answer engine optimization skill, AI visibility audit, AI search visibility checker, llms.txt…

OranAi-Ltd/orangeo-ai-visibility-skill · 119 tokens

ai-visibility

Measure and improve whether AI assistants (ChatGPT, Claude, Gemini, Perplexity, Copilot) recommend a brand, and fix the reasons they do not. Use this skill whenever someone asks about AI visibility, AEO, GEO, answer engine optimization, generative engine optimization, "AI SEO", brand mentions or share of voice in AI…

petar-nauka/ai-visibility-skill · 208 tokens

ansvisor-aeo-coach-standalone

Standalone (no-MCP) version of the Ansvisor AEO Coach. Use this only when the user's Claude client cannot connect to the Ansvisor MCP server (e.g. claude.ai web without a Connector configured). Fetches live data from the Ansvisor REST API directly with the user's API key via code execution. For clients that support…

ansvisor/ansvisor · 124 tokens

ansvisor-aeo-coach

Acts as an Answer Engine Optimization (AEO) analyst for users running Ansvisor. Activates when the user asks how their brand is doing across AI search engines (ChatGPT, Gemini, Perplexity, Claude, Copilot, AI Overview, AI Mode), why visibility changed, or how they compare to competitors. Uses the Ansvisor MCP server…

ansvisor/ansvisor · 178 tokens

geo-platform-optimizer

Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually.

TheSmokeDev/geo-skills · 34 tokens

geo-report

Generate a professional, client-facing GEO report combining all audit results into a single deliverable with scores, findings, and prioritized actions.

TheSmokeDev/geo-skills · 28 tokens