Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →garrytan/hackernews-frontpage
Scrape the Hacker News front page (titles, points, comment counts).
Passed 18 of 23 test cases with the skill, and 8 of 23 without it.
and 10 more in the full report
11 fixed9 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
When extracting front-page entries from news.ycombinator.com using the standard CLI scraper, what fixed integer value is returned in the output for the total item count?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies 30 as the total story count returned. | Passed | Passed |
| Names `count` as the top-level field storing this total. | Missed | Passed |
The instructions your model reads when the skill loads.
Scrapes the Hacker News (news.ycombinator.com) front page and returns the
top 30 stories as JSON. Each story has its rank, title, link URL, point count,
and comment count.
$ $B skill run hackernews-frontpage
{
"stories": [
{ "rank": 1, "title": "...", "url": "...", "points": 412, "comments": 87 },
...
],
"count": 30
}
https://news.ycombinator.com via the daemon.tr.athing structure) into a typed
Story record.hackernews-frontpage is the smallest interesting browser-skill: no auth,
stable HTML, deterministic output, file-fixture-friendly. Every Phase 1
component (SDK, scoped tokens, three-tier lookup, spawn lifecycle) is
exercised by $B skill run hackernews-frontpage and the bundled
script.test.ts.
When the HN HTML rotates and our selectors break, the test fails against the captured fixture before users notice. That's the point.
test cases passed, vs 8 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.