Retrieve Google Ads keyword suggestions from seed keywords through Frevana.
Purpose
This skill is for expanding seed keywords into related Google Ads keyword ideas.
Inputs:
keywords- optional location, language, search partners, historical date range, sorting, adult-keyword inclusion, and tag fields
Output:
- validated response JSON with Google Ads keyword suggestion data
This skill validates that the response is JSON and returns it unchanged. Do not rewrite or reshape the returned data unless the user explicitly asks for a transformation.
What This Skill Needs
- user-provided seed
keywords - optional location, language, date, sorting, search partners, adult-keyword, and tag values
FREVANA_TOKENin the environment variables, or an explicit--tokenoverride for the current runcurlbashpython3
Execution Order
Use this flow so the request stays simple and reliable:
- Confirm the user has provided one or more seed keywords.
- If the user does not provide
search_partners, default tofalse. In the user-facing response, explicitly say that this default was used when relevant. - If the user does not provide
include_adult_keywords, default tofalse. - Prefer the script over ad hoc
curlcommands. - Let the script read
FREVANA_TOKENfirst. - In interactive shell usage, if
FREVANA_TOKENis missing, the script may prompt for it. - In non-interactive or agent workflows, fail fast if the token is missing and tell the user to set
FREVANA_TOKENor pass--tokenexplicitly. - Return the validated response JSON, or summarize the strongest keyword ideas if the user does not need the full payload.
- The script saves the JSON response to
./out/by default.
Commands
Basic keyword suggestions
bash <skill-path>/scripts/search_google_ads_keywords_for_keywords.sh \
--keywords "phone,cellphone"
With location and language
bash <skill-path>/scripts/search_google_ads_keywords_for_keywords.sh \
--keywords "wireless earbuds,gaming headset" \
--location-code 2840 \
--language-code en
Include search partners
bash <skill-path>/scripts/search_google_ads_keywords_for_keywords.sh \
--keywords "phone,cellphone" \
--search-partners true
Save response JSON to a specific file
bash <skill-path>/scripts/search_google_ads_keywords_for_keywords.sh \
--keywords "phone,cellphone" \
--output ./out/google-ads-keywords-for-keywords-result.json
Fixed Request Shape
The script sends this payload shape:
{
"keywords": [
"phone",
"cellphone"
],
"location_code": 2840,
"language_code": "en",
"search_partners": false,
"include_adult_keywords": false
}
Default values when not provided:
search_partners:falseinclude_adult_keywords:false
Do not pass unsupported fields. Do not pass API keys, output paths, or request metadata in the payload; Frevana handles server-side details.
Response Shape
The API returns JSON. This skill validates the response as JSON and returns it unchanged.
Output
- Success: the script validates that the response body is JSON and prints it to stdout
- Default file path:
./out/google-ads-keywords-for-keywords-<UTC timestamp>-<pid>.json - With
--output: the same JSON is written to the specified file path instead - Failure: the script prints the response body or parsing error and exits non-zero
Notes
- Require
--keywords --keywordsmust be a comma-separated list. Trim whitespace and preserve the user-supplied phrases--keywordsaccepts up to 20 seed keywords--search-partnersacceptstrue,false,1,0,yes,no,on, oroff--include-adult-keywordsacceptstrue,false,1,0,yes,no,on, oroff- If the user does not specify
search_partners, default tofalse - If the user does not specify
include_adult_keywords, default tofalse --sort-byacceptsrelevance,search_volume,competition_index,low_top_of_page_bid, orhigh_top_of_page_bid- Use only one of
--location-name,--location-code, or--location-coordinate - Use only one of
--language-nameor--language-code - If
curlis missing, stop and tell the user to installcurl - If
python3is missing, stop and tell the user to installpython3 - Do not echo the Bearer token back to the user
- Summarize the highest-volume keyword ideas and notable CPC or competition gaps when the user is doing keyword research
Example Prompts
Chinese
- "Use phone and cellphone to look up Google Ads keyword suggestions"
- "Look up keywords related to phone"
- "Help me look up keywords related to the keyword wireless earbuds"
- "Call the Google Ads keywords for keywords API, and save the raw JSON to a file"
- "Help me expand the Google Ads keywords for wireless earbuds, region United States, language English"
English
- "Get Google Ads keyword ideas for phone and cellphone"
- "Call the Google Ads keywords for keywords API and save the raw JSON"
- "Expand wireless earbuds into Google Ads keyword suggestions for the US in English"