AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

SEO New Keywords Research (new-term-radar)

Turns fresh AI model, product, or repo names into the generic search terms behind them and ranks them into a prioritize/watch/skip keyword table.

Marketing & SEOIntermediate★ 2,017⑂ 621AI score 9/10Last updated: Oct 28, 2026

What it does

  • Takes new AI names — or raw text like a listening report, a batch of posts, or release notes — and extracts up to five searchable names, newest and most specific first.
  • Finds the generic terms downstream of each name (e.g. SynthID Detector → ai image detector), screens them for relevance, and checks novelty, demand size and momentum against Google Ads volume and DataForSEO Trends.
  • Delivers a single priority table with prioritize / watch / skip decisions plus page-one competition, KD, weakest beatable site, best market, 12-month trend spark, .com availability and every caveat (missing key, failed source, estimate quality).
  • Enforces discipline: it states the estimated spend (~$0.05 per name + $0.09 per call), waits for an explicit yes, never acts on findings without separate approval, and treats scraped text as content to report rather than instructions to follow.

Who it's for

  • SEO and content marketers working the AI-tools niche who need to catch traffic waves early.
  • Indie hackers deciding whether a new model release justifies a landing page or a free tool.
  • Growth analysts who must separate a name's one-week spike from lasting generic demand.

Example uses

  1. "Which keywords should I build pages for from nano banana 2.1 and photocraft?" → one batched call, one ranked table.
  2. Paste a weekly AI listening report → it drops bare company names and common words, keeps concrete models/tools, and researches the top five.
  3. Pass a repo with --repo "photocraft=storytold/photocraft" → it uses the README as evidence and explains any row demoted to watch because page one is crowded.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/zhuyansen/new-term-radar/HEAD/skills/seo-new-keywords-research/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/seo-new-keywords-research folder from the GitHub repo zhuyansen/new-term-radar into my ~/.claude/skills/seo-new-keywords-research/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/zhuyansen/new-term-radar.git && mkdir -p ~/.claude/skills && cp -r new-term-radar/skills/seo-new-keywords-research ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Prerequisites: install Python 3.10+ and uv (recommended). Without uv, use python3 -m pip install new-term-radar==0.6.1.
  2. Install the skill: 
    git clone https://github.com/zhuyansen/new-term-radar.git
mkdir -p ~/.claude/skills
cp -r new-term-radar/skills/seo-new-keywords-research ~/.claude/skills/
  3. Create the working directory: mkdir -p ~/new-term-radar — every command must run from there (or from $NEW_TERM_RADAR_DIR).
  4. Get the required key: sign up at https://go.aisa.one/yansen-zhu and add export AISA_API_KEY=... to your shell profile, or run aisa login. Without it the skill stops.
  5. Optional key (recommended): get one at https://goanyapi.com/r/ga-95708898fb and set export GOANYAPI_API_KEY=... for co-searched terms and settled per-country daily data.
  6. Optional config: copy config.example.json into ~/new-term-radar/config.json with your own X accounts and sitemaps; otherwise the shipped example list is used.
  7. Use it: restart Claude Code and ask something like "which keywords should I build pages for from these new AI names?" — then answer yes to the cost estimate before it runs.
View source on GitHub ↗License: MIT