Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →notque/news-collection
Collect, filter, and freshness-qualify news items.
Passed 17 of 21 test cases with the skill, and 8 of 21 without it.
and 14 more in the full report
12 fixed6 passed either way2 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
A breaking news item about a commercial spaceflight landing has only one source available on the web. An analyst wants to mark the freshness verdict as fresh since no older articles exist. What freshness verdict is required?
| Checked | Without skill | With skill |
|---|---|---|
| Assigns a freshness verdict of unclear due to lack of a second independent confirming source. | Missed | Passed |
The instructions your model reads when the skill loads.
Gather news items on a topic, filter junk cheaply, verify freshness, and emit qualified items under an evidence contract. Pipeline-shaped: four phases, a gate between each. Content pipelines consume the JSON artifact; pair with fact-check to verify what this skill qualifies.
Goal: gather candidate items from available sources (feeds, search results, provided fixtures). Every item carries the five-fact evidence contract: title, url, outlet, author, published_at.
Rule (verbatim from the design): publish times are extracted (article
metadata), never guessed; missing timestamp → recorded as unknown, confidence
lowered and disclosed. A guessed timestamp poisons every downstream freshness
verdict; an honest "published_at": null keeps the item usable with known
uncertainty.
Record each item as one JSON object per the item schema below. Fill
evidence_notes with where each fact came from (meta tag, byline, JSON-LD,
sitemap).
Distinguish outcomes: zero items because sources were unreachable is a collection failure (report it, stop); zero items from reachable sources is a valid empty feed (deliver an empty artifact with counts of zero).
Gate: every collected item has all five fields present — value or explicit
null with a confidence downgrade and a disclosure note. Items with silent
gaps stay in COLLECT until the gap is recorded.
Goal: cheap, high-recall pass over collected items. Three verdicts:
keep / monitor_only / reject, each with a reason code (see
Coarse Filter below).
Rule (verbatim from the design): high-magnitude stories are downgraded to
test cases passed, vs 8 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.