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/start/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/start)<a href="https://agentmods.dev/skills/koljaschoepe/scientific-writing/start"><img src="https://agentmods.dev/badge/skills/koljaschoepe/scientific-writing/start/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/start"><img src="https://agentmods.dev/badge/skills/koljaschoepe/scientific-writing/start.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 | $0.00045 | $0.01365 |
| Opus 5.5 | $0.00018 | $0.00546 |
| Sonnet 5.5 | $0.00009 | $0.00273 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
start 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/start: Projekt einrichten
Wichtig: Jede Frage über das Rückfrage-Tool, bis zu 4 Fragen je Runde. „Später klären“
bleibt als leerer Wert stehen. Relative Daten in echte Daten umrechnen (heutiges Datum aus dem
Kontext). Nie Passwörter tippen. Werte nur in .arbeit/einstellungen.md: einzelne mit
zustand.mjs einstellung <abschnitt.schluessel> <wert>, bei der Ersteinrichtung die Datei in einem
Zug bearbeiten (nur hinter den Doppelpunkten, Kommentare bleiben). Zustand nur über
zustand.mjs. Endausgabe laut AGENTS.md.
Argument: $ARGUMENTS
Kontext laden
node .claude/kit/werkzeuge/zustand.mjs init(legt fehlende Dateien aus den Vorlagen an)..arbeit/einstellungen.mdund.arbeit/plan.mdlesen..claude/kit/leitfaeden/interview.mdbeachten.
Die Runden stehen in eigenen Dateien. Lies immer nur die Runde, die gerade dran ist:
| Runde | Datei | Inhalt |
|---|---|---|
| 1 | runden/1-arbeit.md |
Arbeitstyp, Fach, Sprache, Methodik |
| 2 | runden/2-person.md |
Name, Hochschule, Institut, E-Mail |
| 3 | runden/3-zeit.md |
Beginn, Abgabe, Betreuung, Termine, Seitenbereich |
| 4 | runden/4-thema.md |
Thema, KI-Regeln, Schreibmodus |
| 5 | runden/5-format.md |
Zitierstil, Vorlage, Verzeichnisse, Logo |
| 6 | runden/6-werkzeuge.md |
Code, Zotero, Bibliothek, Reparatur |
Schon eingerichtet
- eingerichtet: ja und kein Argument: Interview „Was möchtest du ändern?“ (header „Ändern“,
multiSelect): „Umfang, Fristen, Termine“ (Runde 3), „Arbeit, Thema, KI-Regeln“ (1 und 4),
„Format und Zitierstil“ (5), „Werkzeuge und Systemcheck“ (6). In der Beschreibung erwähnen:
Alles andere ändert sie direkt in .arbeit/einstellungen.md (Klick im Dashboard) oder sagt
es einfach. Ein Argument (/start fristen) springt direkt zur passenden Runde. Danach
speichern wie unten, nur die geänderten Werte.
Ersteinrichtung
Begrüßung (einziger Text ohne Interview): „Hallo! Ich begleite dich durch die ganze Arbeit, von der Themenfindung bis zum PDF. Ich stelle dir jetzt ein paar Fragen, meistens zum Anklicken. Das dauert etwa 10 Minuten. Wenn du etwas nicht weißt, wähl ‚Später klären‘. Nichts davon ist endgültig.“
What ships with it
6 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 · -115 lines · +11 tokens per session 9a9f28be0889
- 28d ago First seen · 207 lines · 34 tokens per session scan A c0efcdf13d59
start is a skill published in the GitHub repository koljaschoepe/scientific-writing (13 stars, last pushed 26d ago), licensed MIT. It adds 45 tokens to every session and 1,365 once invoked, about $0.0002 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
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
systems-paper-writing
Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.
coauthor-brief
Generate a co-author / collaborator handoff brief for a multi-author, multi-machine project — summarizing what changed since the last brief (git delta), the current state of each artifact (manuscript, analysis, slides), open questions, how to reproduce locally, and any restricted-data access steps. Use when user says…
triage-inbox
Triage academic email and calendar (Gmail / Google Calendar via the session's MCP) into a prioritized digest plus a referee-obligations tracker — classifying referee requests, R&R and editor correspondence, co-author threads, seminar and conference invites, and grant/admin deadlines, and proposing a human-gated action…
project-retrospective
Generates LESSONS.md files capturing institutional knowledge and failures. Use when closing out projects or investigations.