A guided next-step helper for a research paper, from choosing a topic through research, outlining, writing, review, and submission. It reads the current project status and offers the next suitable action.

Use it to move through the project one phase at a time, respond to urgent tasks, adjust the plan, and approve the next step.

It prevents you from having to remember the whole workflow or skip an unfinished stage without warning. It also highlights urgent deadlines, unprocessed sources, and missed daily goals.

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/weiter/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/weiter/github.svg)](https://agentmods.dev/skills/koljaschoepe/scientific-writing/weiter)

Your own site

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

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 909 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	$0.00033	$0.00909
Opus 5.5	$0.00013	$0.00364
Sonnet 5.5	$0.00007	$0.00182
Haiku 4.5	$0.00003	$0.00091

Measured 26d ago against content hash b6d1c0968cce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

weiter 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/weiter/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.

/weiter: Der nächste Schritt

Wichtig: Nur die Ablaufdatei der aktiven Phase laden. Zustand nur über node .claude/kit/werkzeuge/zustand.mjs. Rückfragen nur per Rückfrage-Tool. Endausgabe laut AGENTS.md.

Argument: $ARGUMENTS

Kontext laden

Nicht eingerichtet (meldet der Start-Hook, sonst eingerichtet: nein oder leerer arbeit.titel in .arbeit/einstellungen.md): .claude/skills/start/SKILL.md lesen und befolgen, hier aufhören.
node .claude/kit/werkzeuge/zustand.mjs zeige (Phase, Kapitel, Seiten), .arbeit/plan.md (Meilensteine, Termine).
.claude/kit/ablauf/<phase>.md. Nur diese Datei.
Ab der Phase Gliederung: node .claude/kit/werkzeuge/zustand.mjs gliederung (Einheiten mit Dateien, Status und Abschnitten). Die Gliederung steht in den Kapiteldateien, nicht in einer eigenen Datei.

Phasen: einrichtung, thema, recherche, expose, gliederung, schreiben, pruefen, abgabe. Ein Argument (/weiter gliederung) gilt nur, wenn die vorigen Phasen erledigt sind oder die Person nach Hinweis auf die Lücke bewusst springt (Interview).

Dringendes zuerst

Höchstens drei Zeilen Lage (Phase, letzter Stand, Tage bis Abgabe). Dann per Interview anbieten, falls zutreffend:

Betreuungstermin in höchstens 3 Tagen: Vorbereitung (.claude/kit/vorlagen/betreuung.md).
Meilenstein überfällig: ehrlich sagen, neue Daten in .arbeit/plan.md vorschlagen.
Letzter Sync über 2 Tage (meldet der Start-Hook): /sync.
Unverarbeitete Quellen (node .claude/kit/werkzeuge/kandidaten.mjs neu) oder Dateien in quellen/eingang/: quellen-Skill.

Nichts davon: direkt loslegen, ohne Interview.

Ablauf

Nächsten Schritt aus der Ablaufdatei bestimmen (Tabelle „erledigt, wenn“).
In einem Satz sagen, was jetzt passiert und warum.
Schritt ausführen, Interviews an den Entscheidungspunkten.
Ergebnisse in die Dateien laut Ablaufdatei, .arbeit/tagebuch.md ergänzen, bei KI-Beitrag .arbeit/hilfsmittel.md.

Zustand:

node .claude/kit/werkzeuge/zustand.mjs verlauf "<was erledigt wurde>"
node .claude/kit/werkzeuge/zustand.mjs naechster "<ein Satz, den die Person im Dashboard versteht>"

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 · +4 lines · -19 tokens per session b6d1c0968cce
28d ago First seen · 66 lines · 52 tokens per session scan A 04c789233ec9

Subscribe to this mod's changes

weiter is a skill published in the GitHub repository koljaschoepe/scientific-writing (13 stars, last pushed 26d ago), licensed MIT. It adds 33 tokens to every session and 909 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 LaTeX Planning Project management academic-writing ai bachelor-thesis master-thesis

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.

davila7/claude-code-templates · 65 tokens

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.…

Orchestra-Research/AI-Research-SKILLs · 68 tokens

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.

Orchestra-Research/AI-Research-SKILLs · 66 tokens

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…

pedrohcgs/claude-code-my-workflow · 146 tokens

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…

pedrohcgs/claude-code-my-workflow · 132 tokens

project-retrospective

Generates LESSONS.md files capturing institutional knowledge and failures. Use when closing out projects or investigations.

jamditis/claude-skills-journalism · 26 tokens

scientific-writing: Skill for Claude Code