Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/citation-assistant-skill
Claude Code skill for citation workflow via OpenAlex and CrossRef
Passed 15 of 23 test cases with the skill, and 12 of 23 without it.
and 1 more in the full report
3 fixed13 passed either way9 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
How do you install the citation assistant skill into OpenClaw from the command line?
| Checked | Without skill | With skill |
|---|---|---|
| Runs openclaw skills install citation-assistant | Missed | Passed |
The instructions your model reads when the skill loads.
Citation Assistant is a Claude Code skill that integrates OpenAlex and CrossRef APIs into the coding workflow for instant paper lookup, citation formatting, and reference management. Search for papers by title or keyword, get formatted BibTeX entries, find related works, and insert citations — all without leaving the terminal. Designed for researchers writing papers in LaTeX or Markdown.
# Add as Claude Code skill
# Copy SKILL.md to your Claude Code skills directory
# Or install via OpenClaw:
openclaw skills install citation-assistant
import requests
OA_API = "https://api.openalex.org"
def search_papers(query, limit=5):
"""Search OpenAlex for papers."""
resp = requests.get(
f"{OA_API}/works",
params={
"search": query,
"per_page": limit,
},
headers={"User-Agent": "ResearchPlugins/1.0 (https://wentor.ai)"},
)
return resp.json().get("results", [])
papers = search_papers("attention mechanism transformer")
for p in papers:
authors = [a["author"]["display_name"] for a in p.get("authorships", [])[:3]]
print(f"[{p.get('publication_year')}] {p.get('title')}")
test cases passed, vs 12 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.