Web search and content fetching - search the web or extract content from URLs
SkillScore86Maintained
Automatic
◆Research pack
Last verified 8/16/2026
What it changes
Passed 16 of 18 test cases with the skill, and 2 of 18 without it.
Without skill14%
With skill86%
Checks it passed that the model alone missed
Sets path to /fetch in request body.
Sets path to /search in request body.
Sets path to /fetch in request payload.
and 22 more in the full report
16 fixed3 passed either way3 still failing0 broke
Pass-rate lift
+73 pp
Tokens
+55%
Agent turns
0%
Response time
-37%
Model gemini-3.6-flashMeasured 8/16/2026v119 of 22 cases passed with skill · 18 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 15
Prompt
I want to log into my Gooseworks developer account using the command line tool. What CLI command should I execute in my terminal to initiate interactive CLI authentication?
What was checked, without and with the skill
Checked
Without skill
With skill
Recommends executing npx gooseworks login in terminal.
Missed
Passed
Does not construct a search or fetch JSON payload.
Passed
Passed
case-06 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md89 linessingle file
Linkup - Web Search & Fetch API
Setup
Read your credentials from ~/.gooseworks/credentials.json:
If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login
All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"
Search the web and fetch content from any URL.
Capabilities
Search: The /search endpoint allows you to retrieve web content
Fetch: The /fetch endpoint allows you to fetch a single webpage from a given URL
Usage
Search
The /search endpoint allows you to retrieve web content.
Parameters:
q* (string) - The natural language question for which you want to retrieve context.
depth* (string) - Defines the precision of the search. standard returns results faster; deep takes longer but yields more comprehensive results.
outputType* (string) - The type of output you want to get. Use structured for a custom-formatted response defined by structuredOutputSchema.
structuredOutputSchema (object) - Required only when outputType is structured. Provide a JSON schema (as a string) representing the desired response format. The root must be of type object.
includeSources (boolean) - Relevant only when outputType is structured. Defines whether the response should include sources. Please note that it modifies the schema of the response, see below
includeImages (boolean) - Defines whether the API should include images in its results.
fromDate (string) - The date from which the search results should be considered, in ISO 8601 format (YYYY-MM-DD). It must be before toDate, if provided, and later than 1970-01-01.
toDate (string) - The date until which the search results should be considered, in ISO 8601 format (YYYY-MM-DD). It must be later than fromDate, if provided, or than 1970-01-01.
includeDomains (string[]) - The domains you want to search on. By default, don't restrict the search. You can provide up to 100 domains.
excludeDomains (string[]) - The domains you want to exclude of the search. By default, don't restrict the search.
includeInlineCitations (boolean) - Relevant only when outputType is sourcedAnswer. Defines whether the answer should include inline citations.
maxResults (number) - The maximum number of results to return.