OneCite
Verifies references against live academic APIs and emits clean, complete BibTeX.
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 14, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 18, 2026 · 4c17bdd
Ran two real DOIs through it live: got back correct, fully-formed BibTeX (author, journal, volume, pages, abstract, DOI, URL) pulled from actual metadata APIs, not memorized text -- but the doctor/benchmark/templates commands the SKILL.md leans on only exist in an editable repo-checkout install, not the current PyPI release.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 9/10
- Docs & honesty 5/5
What OneCite does
Resolves DOIs, arXiv/PMID IDs, GitHub and Zenodo URLs, or existing BibTeX against academic metadata APIs and writes verified BibTeX, refusing to fabricate missing fields. Triggers on requests to clean, validate, or audit a reference list or citation file. Full functionality (benchmark/doctor/template subcommands) needs an editable install from a local repo checkout, not just `pip install onecite` from PyPI.
How to install OneCite
git clone https://github.com/HzaCode/OneCite
cd OneCite
mkdir -p ~/.claude/skills
cp -r skills/onecite ~/.claude/skills/onecite
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger OneCite
-
/oneciteVerifies references against live academic APIs and emits clean, complete BibTeX.
It also activates on plain-language prompts like these:
-
Verify these DOIs and give me clean BibTeX entries for my references -
Check my citation list against academic APIs and fix any broken entries -
I have a messy bibliography, can you validate it and fill in missing fields
Frequently asked questions
- Is the OneCite skill free?
- Yes. The skill itself is free from HzaCode/OneCite. SkillProof publishes the install command and an independent test verdict at no cost.
- Does OneCite work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Works with setup. Ran two real DOIs through it live: got back correct, fully-formed BibTeX (author, journal, volume, pages, abstract, DOI, URL) pulled from actual metadata APIs, not memorized text -- but the doctor/benchmark/templates commands the SKILL.md leans on only exist in an editable repo-checkout install, not the current PyPI release.
- What is the OneCite SkillProof Score?
- 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
- How do I install OneCite?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use OneCite with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.