Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →microsoft/foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample.
Passed 16 of 19 test cases with the skill, and 8 of 19 without it.
and 8 more in the full report
10 fixed9 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
In a Python script initializing `FoundryChatClient`, the code currently hardcodes `project_endpoint='https://your-project.services.ai.azure.com'`. What exact environment variable should be read to retrieve the real project endpoint in this environment?
| Checked | Without skill | With skill |
|---|---|---|
| The response names FOUNDRY_PROJECT_ENDPOINT as the environment variable. | Missed | Passed |
The instructions your model reads when the skill loads.
Some samples (notably those under 01-get-started) hardcode the Foundry
project endpoint and model directly in the FoundryChatClient constructor
using placeholder values, for example:
client = FoundryChatClient(
project_endpoint="https://your-project.services.ai.azure.com",
model="gpt-4o",
credential=AzureCliCredential(),
)
These placeholder values are not real and the sample cannot run as written. The validation environment provides the real values through environment variables, so the sample must read them from the environment instead.
When you detect a hardcoded/placeholder project_endpoint (or model) that
is causing the sample to fail with missing or invalid setup:
project_endpoint value with a read from the
FOUNDRY_PROJECT_ENDPOINT environment variable.model value with a read from the FOUNDRY_MODEL
environment variable.import os is present at the top of the file.The corrected constructor should look like:
import os
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
These samples are intentionally written with hardcoded placeholders, so this
test cases passed, vs 8 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.