self-verifying-bibliography SKILL.md skillA

self-verifying-bibliography from chgagne/claude-skills-research is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add chgagne/claude-skills-research/self-verifying-bibliography@git:20261009.3a873fd

Pins git:20261009.3a873fd in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
chgagne/claude-skills-research
Path
_evals/verifying-bibliography/self-skill/SKILL.md
Versions recorded
1
Latest version
git:20261009.3a873fd, committed Oct 9, 2026
Size
13,524 bytes
Repository stars
5
License
MIT

Check a BibTeX bibliography against the real published record. Finds fabricated or non-existent references, wrong titles, author lists, DOIs, venues, volumes, pages and years, retracted papers, and arXiv/bioRxiv preprints that have since been published. Use it when asked to check, audit, validate, fact-check, clean up or "fix" a .bib file or reference list, before submitting a paper or thesis, or whenever citations were written or edited by an LLM.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Self-verifying bibliography

You are checking whether each BibTeX entry describes a work that **really exists**, and whether its fields **match the version of record**. The most important rule:

> **Every claim or correction must come from a record fetched during this session**: an API response, a DOI landing page, DBLP, arXiv, the publisher or the proceedings site. Never "fix" a field from memory. A correction written from memory is just another possible hallucination. If you cannot find an authoritative record, say so. Do not guess.

Not finding an entry in the APIs does not prove it is fabricated. Finding a similar title does not prove the entry is correct. The script narrows down where to look. You make the final decision for each flagged entry, with evidence.

## Tools in this skill

- `scripts/bibverify.py` (Python 3, stdlib only). Run it with the path relative to this SKILL.md.
  - `check REFS.bib [--cited-in main.tex ...] [--keys k1,k2] [--out r.json] [--md r.md] [--workers 4]` checks every entry against Crossref, doi.org, arXiv, DBLP, OpenAlex, Semantic Scholar, bioRxiv and Open Library. It writes a JSON report and a Markdown report, and prints the Markdown.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add chgagne/claude-skills-research/self-verifying-bibliography@sha256:c7becc3189c13f61

The line at the top of this page pins the label git:20261009.3a873fd, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_4idfg23wky5uogv3.svg)](https://markdownregistry.com/a/art_4idfg23wky5uogv3)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 9, 2026.

versioncommittedcommitsizeaudit
git:20261009.3a873fd latest2026-10-09 3a873fd 13,524 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (13524 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

chgagne/claude-skills-research · 5 stars · license MIT · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4idfg23wky5uogv3
GET https://markdownregistry.com/api/v1/resolve?ref=chgagne/claude-skills-research/self-verifying-bibliography
GET https://markdownregistry.com/api/v1/blob/c7becc3189c13f616a2e4baa115e145ee8f4b199f35cf8b83c457bcf77fe0934

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from chgagne/claude-skills-research

self-surveying-literature SKILL.md skill
chgagne/claude-skills-research · _evals/surveying-literature/self-skill/SKILL.md · Audit a research paper draft (LaTeX sources + .bib) for related work it should cite but does not, above all close prior…
git:20261009.6f52569 · audit A · 5 stars
collaborating-on-research SKILL.md skill
chgagne/claude-skills-research · collaborating-on-research/SKILL.md · Use when working with a researcher on a long-running research project across many sessions — opening or closing a…
git:20260817.136fa75 · audit A · 5 stars
comparing-papers SKILL.md skill
chgagne/claude-skills-research · comparing-papers/SKILL.md · Use when comparing a draft against specific prior work head to head — checking whether a baseline was trained at the…
git:20260812.4c0299b · audit A · 5 stars
explaining-derivations SKILL.md skill
chgagne/claude-skills-research · explaining-derivations/SKILL.md · Use when a proof or derivation needs to be made explicit step by step — expanding a paper's algebra for a reader…
git:20260816.89dabff · audit A · 5 stars
proofreading-paper-writing SKILL.md skill
chgagne/claude-skills-research · proofreading-paper-writing/SKILL.md · Use when asked to proofread, polish, or critique the writing of an academic paper from its LaTeX sources — grammar and…
git:20261009.2091ec8 · audit A · 5 stars
reviewing-paper-sources SKILL.md skill
chgagne/claude-skills-research · reviewing-paper-sources/SKILL.md · Use when asked to review, critique, or assess an academic paper from its LaTeX sources — including pre-submission…
git:20260926.af6ea48 · audit A · 5 stars
running-cluster-experiments SKILL.md skill
chgagne/claude-skills-research · running-cluster-experiments/SKILL.md · Use when planning, budgeting, submitting or resuming a multi-job experiment campaign on a Slurm/HPC cluster — sizing…
git:20260812.12926b4 · audit A · 5 stars
surveying-literature SKILL.md skill
chgagne/claude-skills-research · surveying-literature/SKILL.md · Use when finding related work a draft may have missed, checking whether a contribution has already been published, or…
git:20261016.40659e0 · audit A · 5 stars
using-drac-clusters SKILL.md skill
chgagne/claude-skills-research · using-drac-clusters/SKILL.md · Use when working on a Digital Research Alliance of Canada (DRAC, Alliance, formerly Compute Canada) HPC cluster such as…
git:20260814.fdf4923 · audit B · 5 stars
verifying-bibliography SKILL.md skill
chgagne/claude-skills-research · verifying-bibliography/SKILL.md · Use when checking a .bib or reference list for incorrect or fabricated entries — wrong titles, invented co-authors…
git:20261009.18f8d6d · audit A · 5 stars
verifying-proofs SKILL.md skill
chgagne/claude-skills-research · verifying-proofs/SKILL.md · Use when checking the mathematics of a paper rather than its claims — verifying a theorem's proof, an algebraic…
git:20260817.78f3c11 · audit A · 5 stars

Every file in chgagne/claude-skills-research

Browse by kind, by grade A, or by owner.