verify-citation

Solid

Confirm a paper actually exists (arXiv / Semantic Scholar / OpenAlex) before citing it. Use before writing any new citation.

AI & Automation 52 stars 4 forks Updated 1 weeks ago MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
57
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# /verify-citation Verify that a paper exists before writing it as a citation. Inspired by the citation-verification patterns in [flonat/claude-research](https://github.com/flonat/claude-research) and [Imbad0202/academic-research-skills](https://github.com/Imbad0202/academic-research-skills). ## When to use Run `/verify-citation` before writing any new citation into a `.tex`, `.bib`, or `.md` file. If the user asks you to "add a reference to X", run this skill first — do not write the citation until verification passes. ## Usage ``` /verify-citation "Author, Title, Year" /verify-citation "the paper we discussed about spectral geometry" /verify-citation (no argument — verify all citations in the last assistant turn) ``` ## Steps **Step 1 — Extract the citation.** If an argument is given, use it. Otherwise, extract every paper reference from the last assistant turn (titles, author–year pairs, DOIs, arXiv IDs). **Step 2 — Search.** For each citation, search at least two of: - arXiv: `https://arxiv.org/search/?searchtype=all&query=<title+author>` - Semantic Scholar: `https://api.semanticscholar.org/graph/v1/paper/search?query=<title>` - OpenAlex: `https://api.openalex.org/works?search=<title>` Use `WebSearch` or `WebFetch` to run the searches. **Step 3 — Report verdict.** | Result | Action | |--------|--------| | Found on 2+ sources, title and authors match | **VERIFIED** — write the citation | | Found on 1 source, minor title variation | **LIKELY** — note the discre...

Details

Author
Mexregkan
Repository
Mexregkan/claude-for-researchers
Created
3 months ago
Last Updated
1 weeks ago
Language
Shell
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category