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/approve/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/approve)<a href="https://agentmods.dev/skills/koljaschoepe/scientific-writing/approve"><img src="https://agentmods.dev/badge/skills/koljaschoepe/scientific-writing/approve/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/approve"><img src="https://agentmods.dev/badge/skills/koljaschoepe/scientific-writing/approve.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 | $0.00041 | $0.00900 |
| Opus 5 | $0.00020 | $0.00450 |
| Sonnet 5 | $0.00008 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
approve 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 11d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase freigeben
Verschiebt Ergebnisse von draft/ nach final/ und aktualisiert den Fortschritt.
Ablauf
1. Aktuelle Phase ermitteln
Lies output/progress.json für die aktuelle Phase.
2. Draft-Dateien identifizieren
Mit Parameter (z.B. /approve 2.3):
- Suche nur die Datei(en) für Kapitel 2.3 im aktuellen draft/-Ordner
- Ermöglicht selektive Freigabe einzelner Kapitel
Ohne Parameter (/approve):
- Suche ALLE Dateien im aktuellen draft/-Ordner
Prüfe den entsprechenden draft/-Ordner:
| Phase | Draft-Ordner |
|---|---|
| 1 | output/phase-01-brainstorming/draft/ |
| 2 | output/phase-02-outline/draft/ |
| 3 | output/phase-03-citations/draft/ |
| 4 | output/phase-04-plans/draft/ |
| 5 | output/phase-05-writing/draft/ |
| 6 | output/phase-06-review/draft/ |
Falls draft/ leer: "Es gibt nichts zum Freigeben. Nutze /next um den nächsten Schritt zu starten."
3. Dateien anzeigen
Zeige die Dateien die freigegeben werden:
Folgende Dateien werden freigegeben (draft -> final):
[Dateiname 1]
[Dateiname 2]
...
Möchtest du alle freigeben?
Bei Einzelkapitel (/approve 2.3):
Folgende Datei wird freigegeben (draft -> final):
[Dateiname]
Freigeben?
4. Freigabe durchführen
Bei Bestätigung:
- Verschiebe (kopiere) die Dateien von draft/ nach final/
- Lösche die Dateien aus draft/
5. Fortschritt aktualisieren
Prüfe config.yaml -> quellen.workflow für übersprungene Phasen.
Aktualisiere output/progress.json:
- Für Phase 1-3 und 7: Phase als abgeschlossen markieren, nächste Phase setzen
- Sonderfall Phase 2 bei
quellen.workflow: "keine": Nächste Phase ist 4 (nicht 3). Phase 3 wird automatisch als abgeschlossen markiert und übersprungen.
- Sonderfall Phase 2 bei
- Für Phase 4-6 (iterativ): Prüfe ob ALLE Kapitel abgeschlossen sind
- Falls ja: Phase als abgeschlossen markieren, nächste Phase setzen
- Falls nein: Phase beibehalten, nächstes Kapitel empfehlen
Interleaved-Modus (Phase 4/5):
- Nach Freigabe eines Plans (Phase 4): Empfehle /next um das Kapitel zu schreiben
- Nach Freigabe eines Kapiteltexts (Phase 5): Empfehle /next um das nächste Kapitel zu planen
- Falls alle Kapitel geplant UND geschrieben: Phase 4 und 5 als abgeschlossen markieren
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.
- 11d ago First seen · 112 lines · 41 tokens per session scan A f4e98e4565ad
approve is a skill published in the GitHub repository koljaschoepe/scientific-writing (11 stars, last pushed 24d ago), licensed MIT. It adds 41 tokens to every session and 900 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
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.
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…
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.
editorial-workflow
Manages newsroom editorial workflows. Use when tracking assignments, managing deadlines, or coordinating editorial calendars.