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.
curl -O https://raw.githubusercontent.com/koljaschoepe/scientific-writing/main/.claude/skills/pdf/SKILL.mdgit clone --depth 1 https://github.com/koljaschoepe/scientific-writingWrote 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.
[](https://agentmods.dev/skills/koljaschoepe/scientific-writing/pdf)<a href="https://agentmods.dev/skills/koljaschoepe/scientific-writing/pdf"><img src="https://agentmods.dev/badge/skills/koljaschoepe/scientific-writing/pdf/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.
<a href="https://agentmods.dev/skills/koljaschoepe/scientific-writing/pdf"><img src="https://agentmods.dev/badge/skills/koljaschoepe/scientific-writing/pdf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00028 | $0.00878 |
| Opus 5.5 | $0.00011 | $0.00351 |
| Sonnet 5.5 | $0.00006 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
pdf 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pdf: Aus Markdown wird das PDF
Wichtig: Nie „kompilieren“ sagen, sondern „PDF bauen“. Nie rohe LaTeX-Logs zeigen. Format
nur über .arbeit/einstellungen.md (Abschnitte Layout, Zitieren) ändern, nie in
.claude/kit/latex/ (Kit) oder .lokal/ (generiert). Endausgabe laut AGENTS.md.
Argument: $ARGUMENTS
| Modus | Befehl | Ergebnis |
|---|---|---|
| leer | node .claude/kit/werkzeuge/pdf.mjs --json |
Arbeit.pdf, fehlende Kapitel gemeldet |
entwurf |
pdf.mjs entwurf --json |
Wasserzeichen, Platzhalter für fehlende Kapitel |
expose |
pdf.mjs expose --json |
Expose.pdf |
docx |
pdf.mjs docx --json |
Arbeit.docx, für Betreuung, die in Word kommentiert |
check |
pdf.mjs check --json |
nur prüfen, ob Pandoc und LaTeX da sind |
Im Dashboard baut „PDF aktualisieren“ den Entwurf ohne Claude. Nach jedem Bau zeigt es echte Seiten je Kapitel statt der Schätzung.
1. Werkzeuge prüfen (still)
node .claude/kit/werkzeuge/pdf.mjs check --json. fehlend leer: weiter. Für docx genügt
Pandoc. Fehlt pandoc oder latex: pdf/installieren.md lesen und befolgen.
2. Bauen
Befehl laut Tabelle. Erstes Mal kann Minuten dauern: ankündigen.
Ergebnis-JSON: ok, pdf (Pfad), seiten, fehler[] (erklaerung, quelle,
quelleZeile, meldung), warnungen[], fehlende_kapitel[], fehlende_werkzeuge[].
3. Fehler selbst reparieren
Eindeutige Fehler im Text der Person (Tippfehler in \ce{}, \qty{}, \cref{}, fehlendes
$, falscher Bildpfad) ohne Frage beheben, neu bauen, höchstens drei Runden.
Nicht eindeutig (Quelle fehlt in der bib, Abbildung fehlt): Interview mit konkreten Wegen
(„Quelle über quellen-Skill aufnehmen“, „Zitat vorerst entfernen“, „Später klären“).
Umgebung (Paket, Schrift, Biber): ein Satz, Reparatur anbieten (MiKTeX-Update,
layout.schrift leeren). Details in .lokal/build/main.log, nur gezielt lesen.
4. Abschluss
Endausgabe laut AGENTS.md: „PDF fertig: Arbeit.pdf, 48 Seiten.“ Höchstens drei Warnungen
als Stichpunkte. Seiten außerhalb von arbeit.seiten (mehr als 10 %): ausdrücklich sagen.
node .claude/kit/werkzeuge/zustand.mjs verlauf "PDF gebaut (<modus>, <seiten> Seiten)"
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · -17 lines baa999c12c28
- 28d ago First seen · 78 lines · 28 tokens per session scan A 43eb8cf08263
pdf is a skill published in the GitHub repository koljaschoepe/scientific-writing (13 stars, last pushed 26d ago), licensed MIT. It adds 28 tokens to every session and 878 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.
Other skills, from other repositories
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.
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.
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.
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…
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…
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.