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 agentmods add skills/unifapi-agent/agents/keyword-researchnpx skills add unifapi-agent/agents --skill keyword-researchgit clone --depth 1 https://github.com/unifapi-agent/agentsWrote 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/unifapi-agent/agents/keyword-research)<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>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 | $0.00113 | $0.02576 |
| Opus 5 | $0.00056 | $0.01288 |
| Sonnet 5 | $0.00023 | $0.00515 |
| Haiku 4.5 | $0.00011 | $0.00258 |
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.
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 set —
seo/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 candidate —
seo/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 baseline —
seo/keywords/for-sitelists what the target domain already ranks for, so you don't recommend what it already owns and can spot striking-distance pages. - GAP vs competitors —
seo/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/serpwithtargetset 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.
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.
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.
- 6d ago First seen · 104 lines · 113 tokens per session scan A bfff15f7b92e
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.
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…
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…
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-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…
geo-platform-optimizer
Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually.
geo-report
Generate a professional, client-facing GEO report combining all audit results into a single deliverable with scores, findings, and prioritized actions.