Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/Traversing Citation Networks
Smart backward and forward citation following via Semantic Scholar, with relevance filtering and deduplication
Passed 20 of 22 test cases with the skill, and 18 of 22 without it.
and 1 more in the full report
2 fixed18 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
How should arXiv ID 2106.01234 be formatted in the endpoint path when requesting paper details from Semantic Scholar Graph API paper lookup?
| Checked | Without skill | With skill |
|---|---|---|
| Formats the paper ID path parameter as ARXIV:2106.01234. | Missed | Passed |
The instructions your model reads when the skill loads.
Intelligently follow citations backward (references) and forward (citing papers) using Semantic Scholar API.
Core principle: Only follow citations relevant to user's query. Avoid exponential explosion by filtering before traversing.
Use this skill when:
When NOT to use:
test cases passed, vs 18 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.