citation-audit SKILL.md skillA

citation-audit from seandavi/scriptorium is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add seandavi/scriptorium/citation-audit@git:20261020.38cee40

Pins git:20261020.38cee40 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
seandavi/scriptorium
Path
skills/citation-audit/SKILL.md
Versions recorded
9
Latest version
git:20261020.38cee40, committed Oct 20, 2026
First version recorded
May 20, 2026
Size
18,505 bytes
Repository stars
3
License
MIT

Audit existing citations in a manuscript for claim-support alignment, primary-vs-review mismatch, causal overreach, and unsupported assertions, and check that each reference's identifier resolves to the work the reference describes. Reports findings as structured markdown. Does NOT add or invent citations.

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

# Citation audit

You are running scriptorium's **citation-audit** skill. Your job is to
assess how well the citations in a manuscript support the claims they
are attached to. You are a **critique** skill, not a generation skill.

## Critical constraints — read before doing anything else

1. **Never add or invent citations.** Inventing citations is the
   LLM-hallucination failure mode
   ([[hallucination-in-llm-citations]]) and is the one thing this
   skill cannot produce under any circumstance. This is the fixed
   accuracy guard `no-parametric-citations`.
2. **Do not suggest citations by default.** Not even as a "you
   might also cite…" recommendation. The closest you come is
   flagging a claim as **unsupported** so the author can decide what
   to do: choosing what to cite is the author's call
   ([[declared-work-scope]]). This is the scope guard
   `citation-recommendations`, which the author can override (see
   **Guards and overrides** below).
3. **Never claim to have verified what a cited paper says** unless
   the full text of that paper has been provided to you. If only the
   bibliography entry is available (title, authors, year), say so —
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add seandavi/scriptorium/citation-audit@sha256:2c0bc125772b7a38

The line at the top of this page pins the label git:20261020.38cee40, 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_6jzozkvbmrtfjo6r.svg)](https://markdownregistry.com/a/art_6jzozkvbmrtfjo6r)

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

Versions

The registry has recorded 9 versions of this file, between May 20, 2026 and Oct 20, 2026, about one every 19 days.

versioncommittedcommitsizeaudit
git:20261020.38cee40 latest2026-10-20 38cee40 18,505 BA view · diff
git:20261020.b0259fe2026-10-20 b0259fe 18,415 BA view · diff
git:20261020.95ace9f2026-10-20 95ace9f 15,564 BA view · diff
git:20261020.b9b22312026-10-20 b9b2231 15,326 BA view · diff
git:20260520.9f1de682026-05-20 9f1de68 11,532 BA view · diff
git:20260520.2f3d92e2026-05-20 2f3d92e 11,531 BA view · diff
git:20260520.9ff8a7f2026-05-20 9ff8a7f 11,482 BA view · diff
git:20260520.341eff22026-05-20 341eff2 8,871 BA view · diff
git:20260520.b22f6852026-05-20 b22f685 8,802 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 (18505 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

seandavi/scriptorium · 3 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6jzozkvbmrtfjo6r
GET https://markdownregistry.com/api/v1/resolve?ref=seandavi/scriptorium/citation-audit
GET https://markdownregistry.com/api/v1/blob/2c0bc125772b7a38f14449cef14d56a66cd1749b674f332ad7a6a3c980abb0d0

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 seandavi/scriptorium

DESIGN.md DESIGN.md file
seandavi/scriptorium · DESIGN.md
git:20261020.0e1d1ae · audit A · 3 stars
argumentative-flow SKILL.md skill
seandavi/scriptorium · skills/argumentative-flow/SKILL.md · Improve a manuscript section's logical and argumentative coherence while preserving every citation, statistic, and…
git:20261020.24e2628 · audit A · 3 stars
author-contribution-audit SKILL.md skill
seandavi/scriptorium · skills/author-contribution-audit/SKILL.md · Audit the manuscript's Author Contributions section against ICMJE's four authorship criteria and CRediT's 14…
git:20261020.1f8453b · audit A · 3 stars
compression SKILL.md skill
seandavi/scriptorium · skills/compression/SKILL.md · Propose page-limit-driven length reductions on a manuscript section while preserving every citation, every declared…
git:20261020.24e2628 · audit A · 3 stars
desk-rejection-risk SKILL.md skill
seandavi/scriptorium · skills/desk-rejection-risk/SKILL.md · Author-side pre-submission audit that flags triggers likely to result in desk rejection before peer review —…
git:20261020.03cf3ff · audit A · 3 stars
explain SKILL.md skill
seandavi/scriptorium · skills/explain/SKILL.md · Explain scriptorium itself, a named skill, or a named MANUSCRIPT_STATE field. With no argument, gives a whole-system…
git:20261020.3814215 · audit A · 3 stars
figure-text-alignment SKILL.md skill
seandavi/scriptorium · skills/figure-text-alignment/SKILL.md · Audit text-only alignment between figure captions and the body-text sentences that reference them. For every figure…
git:20261020.04bed6a · audit A · 3 stars
gap-finder SKILL.md skill
seandavi/scriptorium · skills/gap-finder/SKILL.md · Identify gaps in existing draft prose — claims under-supported, premises missing, related work not engaged with…
git:20261020.38cee40 · audit A · 3 stars
init SKILL.md skill
seandavi/scriptorium · skills/init/SKILL.md · Conversationally bootstrap MANUSCRIPT_STATE.yaml for a new or existing manuscript directory. Infers what it can from…
git:20261020.8819780 · audit A · 3 stars
outlier-sentence-detector SKILL.md skill
seandavi/scriptorium · skills/outlier-sentence-detector/SKILL.md · Flag sentences that are statistical outliers in the manuscript along three narrow dimensions — length, syntactic…
git:20261020.6122fb3 · audit A · 3 stars
reporting-guideline-compliance SKILL.md skill
seandavi/scriptorium · skills/reporting-guideline-compliance/SKILL.md · Run an EQUATOR Network reporting-guideline checklist (CONSORT, SPIRIT, STROBE, PRISMA, ARRIVE, STARD, TRIPOD/TRIPOD+AI…
git:20261020.04bed6a · audit A · 3 stars
reporting-guideline-fit SKILL.md skill
seandavi/scriptorium · skills/reporting-guideline-fit/SKILL.md · Read the manuscript's methods section (and abstract/title for context) and infer which EQUATOR Network reporting…
git:20261020.4794680 · audit A · 3 stars

Every file in seandavi/scriptorium

Other files named citation-audit

citation-audit SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/citation-audit/SKILL.md · Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a…
git:20261019.8fdc2d5 · audit A · 17,793 stars
citation-audit SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/skills-codex/citation-audit/SKILL.md · Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a…
git:20260906.0472e53 · audit A · 17,793 stars
citation-audit SKILL.md skill
mathews-tom/armory · skills/citation-audit/SKILL.md · Verify that every citation in a manuscript is real, correctly attributed, and accurately described. Detects ghost…
v1.0.0 · audit A · 334 stars

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