A source-processing helper for turning PDFs, uploads, Zotero exports, or saved quotations into bibliography entries and page-specific citations. Zotero is a tool for collecting and managing references; a bibliography is the list of sources used in a paper.

Use it to import a bibliography, process a PDF or DOI, check source-board decisions, and prepare quotations for use in chapters.

It reduces manual reference entry and helps prevent invented publication details, page numbers, or quotations. It also keeps selected sources and quotations connected to the project.

How koljaschoepe/scientific-writing configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to koljaschoepe/scientific-writing. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/koljaschoepe/scientific-writing/main/.claude/skills/quellen/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/koljaschoepe/scientific-writing

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/koljaschoepe/scientific-writing/quellen/github.svg)](https://agentmods.dev/skills/koljaschoepe/scientific-writing/quellen)

Your own site

<a href="https://agentmods.dev/skills/koljaschoepe/scientific-writing/quellen"><img src="https://agentmods.dev/badge/skills/koljaschoepe/scientific-writing/quellen/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/koljaschoepe/scientific-writing/quellen"><img src="https://agentmods.dev/badge/skills/koljaschoepe/scientific-writing/quellen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,135 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.01135
Opus 5.5	$0.00010	$0.00454
Sonnet 5.5	$0.00005	$0.00227
Haiku 4.5	$0.00003	$0.00113

Measured 26d ago against content hash 741adb341992, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

quellen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 26d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/quellen/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/quellen: Quellen verarbeiten

Wichtig: Nichts erfinden (Metadaten, Seiten, Zitate). literatur.bib und .arbeit/kandidaten.json nie ganz lesen, sondern bib.mjs keys|list und kandidaten.mjs list --kurz|neu. Board nur über kandidaten.mjs set|add. Nur legale PDF-Wege. Bei technik.abo: pro höchstens 2 Auswertungen parallel. Endausgabe laut AGENTS.md.

Argument: $ARGUMENTS (DOI, PDF-Pfad oder bibkey zum Neuauswerten)

1. Arbeitsliste

A: node .claude/kit/werkzeuge/kandidaten.mjs neu (Entscheidungen seit der letzten Verarbeitung, genommene ohne bib-Eintrag, Eingang).
B: Dateien in quellen/eingang/.
C: Zotero: exportiert Better BibTeX direkt nach quellen/literatur.bib, genügt ein Abgleich (bib.mjs keys gegen das Board). Liegt ein Export anderswo: node .claude/kit/werkzeuge/bib.mjs import <datei.bib>.
D: Zitate aus dem Dashboard: Einträge in quellen/notizen/<bibkey>.md ohne paraphrase oder kapitel (das Journal nennt sie). Paraphrase in Arbeitssprache, Typ und Kapitel ergänzen, gegen das PDF gegenlesen. seite muss die gedruckte Seite sein. Steht nur seite_pdf da, die gedruckte Seite im PDF nachsehen und ergänzen.

Mehr als 8 Quellen: Interview „Alle jetzt (Empfohlen, etwa Minuten)“, „Nur Kernquellen (Stern oder Markierung kernquelle)“, „Die ersten 5“.

2. Eingang sortieren (B)

PDF: Titel, Autoren, DOI von der ersten Seite, DOI über Crossref prüfen, nach quellen/pdfs/<bibkey>.pdf verschieben, Board-Eintrag mit herkunft: upload, status: genommen.
.bib oder .ris: bib.mjs import, jeden Eintrag als genommen ins Board.
Merkblatt, Prüfungsordnung, Bewertungsbogen: keine Quelle. Per Interview klären, dann nach .arbeit/betreuung/ (Bewertungskriterien zusätzlich nach .arbeit/betreuung/bewertung.md). LaTeX-Vorlage der Arbeitsgruppe: siehe pdf-Skill, Abschnitt Format und Vorlage.
Unklar: fragen.

3. Je Quelle

bibkey: nachnameJahrErstesWort, klein, ohne Umlaute (schwaller2019molecular), Kollision mit Suffix a, b.
bib-Eintrag: node .claude/kit/werkzeuge/bib.mjs add <doi>. Ohne DOI: bib.mjs add-json <datei.json> mit korrektem Typ (@article, @book, @incollection, @online, @misc für Preprints). Chemie-Stile: Zeitschriftenkürzel in shortjournal.
PDF: Open-Access-Link aus dem Board oder Unpaywall, sonst Verlagsseite mit Uni-Login per Playwright. Geht nicht: pdf: null, Interview („Selbst besorgen und in den Eingang legen“, „Fernleihe“, „Nur Abstract nutzen“, „Quelle verwerfen“).
Auswerten: Subagent quellen-auswerter mit bibkey, PDF-Pfad, Kapitel, Notiz der Person, Kernquelle ja oder nein.
Board: kandidaten.mjs set <id> bibkey=<k> pdf=<pfad> ausgewertet=true zitate=<n>.

Read the full file on GitHub · 70 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

26d ago Changed · -10 tokens per session 741adb341992
28d ago First seen · 70 lines · 35 tokens per session scan A 28c66255ff0c

Subscribe to this mod's changes

quellen is a skill published in the GitHub repository koljaschoepe/scientific-writing (13 stars, last pushed 26d ago), licensed MIT. It adds 25 tokens to every session and 1,135 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-01.

Claude Code Documents LaTeX PDF Research academic-writing ai bachelor-thesis master-thesis

overleaf

Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.

aloth/olcli · 62 tokens

latex-rescue

Diagnose and repair LaTeX build failures in local projects or supplied logs. Make minimal source fixes, preserve scientific content and reference keys, and report actual build evidence and unresolved errors.

Calix-L/awesome-latex-skills · 41 tokens

pdf2tex

Reconstruct editable LaTeX from PDF content using page-aware extraction and visual comparison. Preserve source evidence, flag uncertain math/tables/citations, and distinguish text extraction, OCR, reconstruction, and verified compilation.

Calix-L/awesome-latex-skills · 46 tokens

fetch-paper

Fetches a legal open-access copy of a paper from its DOI or arXiv ID — resolves through Unpaywall, arXiv PDF/HTML, and the open-access ACM Digital Library. Use when the user wants to fetch, download, read, or get the PDF or full text of a specific paper. Single polite fetch, transient processing only: it never stores…

ShaishavMaisuria/research-paper-lifecycle-skills · 117 tokens

read-paper-to-notes

Read an academic-paper PDF or supplied full text and turn it into a faithful, structured Markdown deep-reading note. Use when the user provides a research paper and asks to read, explain, summarize, take notes, extract its problem, method, equations, experiments, results, limitations, or research implications, or fill…

yujie-jason-zhang/polish_skill · 116 tokens

awesome-ieee-report

Generates IEEE-format LaTeX technical reports from project requirements and codebase evidence, using academic prose, pseudocode-only explanations, BibTeX references, and IEEEtran formatting.

EnesDemir143/awesome-ieee-report · 41 tokens

scientific-writing: Skill for Claude Code