citation-check

Name: citation-check
Author: scdenney

34stars0forks

How to install citation-check?

scdenney/open-science-skills/citation-check

$npx -y skills add scdenney/open-science-skills --skill citation-check

Installs into the current project.

Summary

Audit citation existence and fabrication risk, in-text/reference parity, DOIs, claim support, and style.

Files · 1

View on GitHub

SKILL.md

1	# Citation Integrity Auditor
2
3	## Heritage and scope
4
5	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.
6
7	## Instructions
8
9	### 1. Orient before checking
10
11	Identify the inputs and constraints:
12
13	- Manuscript source: LaTeX, Markdown, Word export, PDF text, or pasted prose.
14	- Bibliography source: `.bib`, CSL JSON, Zotero export, reference section, footnotes, or mixed.
15	- Target style: default to APA 7 unless the user names a journal or style.
16	- Scope: whole manuscript, one section, bibliography only, or DOI-only pass.
17	- Tool availability: if web lookup, Crossref, DataCite, DOI.org, Semantic Scholar, or OpenAlex are unavailable, mark verification status as `NOT CHECKED` rather than guessing.
18	- For LaTeX/BibTeX, drive the audit off the keys actually `\cite`d in the manuscript (follow `\input`/`\include`), not every entry in a master `.bib`. Only cited keys reach the printed reference list, which is what readers and critics actually check.
19	- Note the bibliography style. Many common styles (`apalike`, `plain`, `unsrt`) do not render the `doi` field, so a wrong or dead DOI is invisible in the compiled PDF and ranks as source-hygiene unless the style prints it. Author, year, title, volume, issue, and pages do render — prioritize those for any artifact that is already public.
20
21	### 2. Build the citation inventory
22
23	Create two inventories before judging errors:
24
25	- In-text inventory: every author-year, parenthetical, narrative, footnote, or numeric citation appearing in the manuscript.
26	- Reference inventory: every bibliography entry, including entry key if present, authors, year, title, outlet, DOI/URL, publication status, and notes.
27
28	Normalize cautiously:
29
30	- Treat spelling variants, diacritics, hyphenated surnames, particles (`de`, `van`, `von`), and organizational authors as possible matches until checked.
31	- For multiple works by the same author-year, verify `a/b/c` suffixes are assigned consistently.
32	- For BibTeX, preserve the entry key and report it with every finding.
33
34	### 3. Run structural checks
35
36	Report:
37
38	- Cited in text but missing from references.
39	- In references but never cited.
40	- Author-year mismatch between in-text citation and reference entry.
41	- Duplicate bibliography entries for the same work.
42	- Ambiguous citations where two reference entries could satisfy one in-text citation.
43	- Broken cross-references caused by LaTeX/BibTeX key drift.
44
45	Do not "fix" ambiguous cases silently. List the likely match and the evidence.
46
47	### 4. Verify source existence and identifiers
48
49	This is the highest-stakes check: confirm each cited work actually exists and that its identifier points to that work. Hallucinated citations — a real author with a plausible but nonexistent title, or a DOI that resolves to a different paper — are the failure mode that ends careers. Use programmatic indexes first; they are near-deterministic and resist hallucination.
50
51	Concrete lookups (via web fetch):
52
53	- Crossref bibliographic search: `https://api.crossref.org/works?rows=5&query.bibliographic=<URL-encoded "title first-author year">`. Compare returned title/authors/year/DOI. Append `&mailto=<email>` for the polite pool. On HTTP 429, fall back to OpenAlex.
54	- DOI resolution: `https://api.crossref.org/works/<doi>` (or `https://doi.org/<doi>`). Confirm the resolved title and authors match this entry. A DOI that resolves to a different real work is the single most common LLM-fabrication signature — never treat "DOI resolves" as "DOI correct."
55	- OpenAlex: `https://api.openalex.org/works?search=<URL-encoded title>` or `?filter=doi:<doi>`. Independent index; use when Crossref is rate-limited or for abstracts.
56	- Exact-title test: search the title in quotation marks. Zero hits anywhere is a strong fabrication signal.
57	- Author-corpus cross-check (catches the "fabricated title grafted onto a real author" pattern): query the real author's works (`...query.author=<name>`) and confirm the cited title appears in their corpus. A real author + nonexistent title + invented co-authors/venue is the classic hallucination.
58
59	Tiered fallback by source type:
60
61	- Journal articles → Crossref / OpenAlex / DOI resolution.
62	- Books and chapters → publisher page, WorldCat, Google Books, OpenAlex. Book DOIs are spotty and frequently 404 even for real books; a dead book DOI is usually source-hygiene, not a missing source.
63	- Datasets and official statistics → the issuing archive (ISSP, V-Dem, ANES, KGSS, national election studies, government statistical catalogues). Verif

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

citation-check

34stars0forks

View on GitHub

How to install citation-check?

scdenney/open-science-skills/citation-check

$npx -y skills add scdenney/open-science-skills --skill citation-check

Installs into the current project.

Summary

Audit citation existence and fabrication risk, in-text/reference parity, DOIs, claim support, and style.

Files · 1

View on GitHub

SKILL.md

1	# Citation Integrity Auditor
2
3	## Heritage and scope
4
5	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.
6
7	## Instructions
8
9	### 1. Orient before checking
10
11	Identify the inputs and constraints:
12
13	- Manuscript source: LaTeX, Markdown, Word export, PDF text, or pasted prose.
14	- Bibliography source: `.bib`, CSL JSON, Zotero export, reference section, footnotes, or mixed.
15	- Target style: default to APA 7 unless the user names a journal or style.
16	- Scope: whole manuscript, one section, bibliography only, or DOI-only pass.
17	- Tool availability: if web lookup, Crossref, DataCite, DOI.org, Semantic Scholar, or OpenAlex are unavailable, mark verification status as `NOT CHECKED` rather than guessing.
18	- For LaTeX/BibTeX, drive the audit off the keys actually `\cite`d in the manuscript (follow `\input`/`\include`), not every entry in a master `.bib`. Only cited keys reach the printed reference list, which is what readers and critics actually check.
19	- Note the bibliography style. Many common styles (`apalike`, `plain`, `unsrt`) do not render the `doi` field, so a wrong or dead DOI is invisible in the compiled PDF and ranks as source-hygiene unless the style prints it. Author, year, title, volume, issue, and pages do render — prioritize those for any artifact that is already public.
20
21	### 2. Build the citation inventory
22
23	Create two inventories before judging errors:
24
25	- In-text inventory: every author-year, parenthetical, narrative, footnote, or numeric citation appearing in the manuscript.
26	- Reference inventory: every bibliography entry, including entry key if present, authors, year, title, outlet, DOI/URL, publication status, and notes.
27
28	Normalize cautiously:
29
30	- Treat spelling variants, diacritics, hyphenated surnames, particles (`de`, `van`, `von`), and organizational authors as possible matches until checked.
31	- For multiple works by the same author-year, verify `a/b/c` suffixes are assigned consistently.
32	- For BibTeX, preserve the entry key and report it with every finding.
33
34	### 3. Run structural checks
35
36	Report:
37
38	- Cited in text but missing from references.
39	- In references but never cited.
40	- Author-year mismatch between in-text citation and reference entry.
41	- Duplicate bibliography entries for the same work.
42	- Ambiguous citations where two reference entries could satisfy one in-text citation.
43	- Broken cross-references caused by LaTeX/BibTeX key drift.
44
45	Do not "fix" ambiguous cases silently. List the likely match and the evidence.
46
47	### 4. Verify source existence and identifiers
48
49	This is the highest-stakes check: confirm each cited work actually exists and that its identifier points to that work. Hallucinated citations — a real author with a plausible but nonexistent title, or a DOI that resolves to a different paper — are the failure mode that ends careers. Use programmatic indexes first; they are near-deterministic and resist hallucination.
50
51	Concrete lookups (via web fetch):
52
53	- Crossref bibliographic search: `https://api.crossref.org/works?rows=5&query.bibliographic=<URL-encoded "title first-author year">`. Compare returned title/authors/year/DOI. Append `&mailto=<email>` for the polite pool. On HTTP 429, fall back to OpenAlex.
54	- DOI resolution: `https://api.crossref.org/works/<doi>` (or `https://doi.org/<doi>`). Confirm the resolved title and authors match this entry. A DOI that resolves to a different real work is the single most common LLM-fabrication signature — never treat "DOI resolves" as "DOI correct."
55	- OpenAlex: `https://api.openalex.org/works?search=<URL-encoded title>` or `?filter=doi:<doi>`. Independent index; use when Crossref is rate-limited or for abstracts.
56	- Exact-title test: search the title in quotation marks. Zero hits anywhere is a strong fabrication signal.
57	- Author-corpus cross-check (catches the "fabricated title grafted onto a real author" pattern): query the real author's works (`...query.author=<name>`) and confirm the cited title appears in their corpus. A real author + nonexistent title + invented co-authors/venue is the classic hallucination.
58
59	Tiered fallback by source type:
60
61	- Journal articles → Crossref / OpenAlex / DOI resolution.
62	- Books and chapters → publisher page, WorldCat, Google Books, OpenAlex. Book DOIs are spotty and frequently 404 even for real books; a dead book DOI is usually source-hygiene, not a missing source.
63	- Datasets and official statistics → the issuing archive (ISSP, V-Dem, ANES, KGSS, national election studies, government statistical catalogues). Verif

People who liked this also viewed

6 picks

Type