Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jeremylongshore/glean-hello-world
Index documents into Glean and search them back using the Indexing and Client APIs.
Passed 21 of 22 test cases with the skill, and 12 of 22 without it.
and 11 more in the full report
9 fixed12 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
When separating read and write access for Glean API integration, which environment variable should be passed in the Authorization header specifically for client search requests?
| Checked | Without skill | With skill |
|---|---|---|
| Uses GLEAN_CLIENT_TOKEN for client search authentication. | Missed | Passed |
The instructions your model reads when the skill loads.
Index documents into Glean and search them. Two steps: set up a custom datasource with the Indexing API, then query with the Client API.
const GLEAN = `https://${process.env.GLEAN_DOMAIN}/api`;
const idxHeaders = {
'Authorization': `Bearer ${process.env.GLEAN_INDEXING_TOKEN}`,
'Content-Type': 'application/json',
};
// Create or configure a custom datasource
await fetch(`${GLEAN}/index/v1/adddatasource`, {
method: 'POST', headers: idxHeaders,
body: JSON.stringify({
name: 'my_wiki',
displayName: 'Internal Wiki',
datasourceCategory: 'PUBLISHED_CONTENT',
urlRegex: 'https://wiki.company.com/.*',
iconUrl: 'https://wiki.company.com/favicon.ico',
}),
});
// Index individual documents
await fetch(`${GLEAN}/index/v1/indexdocuments`, {
method: 'POST', headers: idxHeaders,
body: JSON.stringify({
datasource: 'my_wiki',
documents: [{
id: 'doc-001',
test cases passed, vs 12 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.