Audit in-text/reference parity, DOIs, claim support, and citation style.
SkillScore82Maintained
Automatic
◆Research pack
Last verified 8/8/2026
What it changes
Passed 18 of 22 test cases with the skill, and 4 of 22 without it.
Without skill18%
With skill82%
Checks it passed that the model alone missed
Uses the label DOI MISMATCH for the mismatched item.
Assigns a severity of Blocking to a DOI title mismatch.
Labels a published working paper entry with STATUS UPDATE.
and 17 more in the full report
14 fixed4 passed either way4 still failing0 broke
Pass-rate lift
+64 pp
Tokens
+65%
Agent turns
0%
Response time
-29%
Model gemini-3.6-flashMeasured 8/8/2026v118 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 14
Prompt
In a methodology section, the author writes: 'We estimate standard errors clustered at the state level following the procedure established by Cameron, Gelbach, and Miller (2011).' Which evidentiary category applies to this citation?
What was checked, without and with the skill
Checked
Without skill
With skill
Classifies a methodological justification citation as Method precedent.
Missed
Passed
Distinguishes method precedent from general background context.
Missed
Passed
case-22 · gemini-3.6-flash · 8/8/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md132 linessingle file
Citation Integrity Auditor
Heritage and scope
This is an original Open Science Skills workflow adapted for experimental social science. It remixes general citation-check and source-verification ideas from Cheng-I Wu's Academic Research Skills for Claude Code (CC BY-NC 4.0), especially the separation between citation formatting, existence checks, DOI checks, and uncertainty reporting. Do not copy ARS prose into reports; apply the workflow below.
Instructions
1. Orient before checking
Identify the inputs and constraints:
Manuscript source: LaTeX, Markdown, Word export, PDF text, or pasted prose.
Target style: default to APA 7 unless the user names a journal or style.
Scope: whole manuscript, one section, bibliography only, or DOI-only pass.
Tool availability: if web lookup, Crossref, DataCite, DOI.org, Semantic Scholar, or OpenAlex are unavailable, mark verification status as NOT CHECKED rather than guessing.
2. Build the citation inventory
Create two inventories before judging errors:
In-text inventory: every author-year, parenthetical, narrative, footnote, or numeric citation appearing in the manuscript.
Reference inventory: every bibliography entry, including entry key if present, authors, year, title, outlet, DOI/URL, publication status, and notes.
Normalize cautiously:
Treat spelling variants, diacritics, hyphenated surnames, particles (de, van, von), and organizational authors as possible matches until checked.
For multiple works by the same author-year, verify a/b/c suffixes are assigned consistently.
For BibTeX, preserve the entry key and report it with every finding.
3. Run structural checks
Report:
Cited in text but missing from references.
In references but never cited.
Author-year mismatch between in-text citation and reference entry.
Duplicate bibliography entries for the same work.
Ambiguous citations where two reference entries could satisfy one in-text citation.