Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-preprint-depositiongit clone --depth 1 https://github.com/AlterLab-IEU/AlterLab-Academic-SkillsWrote 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/alterlab-ieu/alterlab-academic-skills/alterlab-preprint-deposition)<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab-academic-skills/alterlab-preprint-deposition"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab-academic-skills/alterlab-preprint-deposition/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/alterlab-ieu/alterlab-academic-skills/alterlab-preprint-deposition"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab-academic-skills/alterlab-preprint-deposition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00271 | $0.03192 |
| Opus 5 | $0.00135 | $0.01596 |
| Sonnet 5 | $0.00054 | $0.00638 |
| Haiku 4.5 | $0.00027 | $0.00319 |
Grade A, and why
alterlab-preprint-deposition scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
All scripts are stdlib-first (use `requests` if present, else `urllib`), run in a How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preprint Deposition — Pick a Server, Prepare the Submission, Link the Published Version
The write/deposit side of preprinting. Given a finished manuscript, this skill turns "I want to post a preprint" into a concrete, server-specific plan: which server fits the field, what metadata and category to enter, which license to choose (and what it commits you to), how versioning and the preprint DOI work, whether the target journal even allows a preprint, and how to link the preprint to the article once it is published.
It is deliberately the deposit-side complement to the read-side connectors
alterlab-arxiv and alterlab-biorxiv (which search and fetch preprints) and
to alterlab-open-science (which chooses data repositories and writes DMPs).
This skill does not reimplement their search/metadata code — it calls them.
Quick Start
I finished a CS paper — how do I post it to arXiv? Which category and license?
Should this biology manuscript go on bioRxiv or medRxiv?
Does Elsevier's journal X allow me to post a preprint before submission?
My preprint just got accepted — how do I link the published DOI to the arXiv version?
What license should I pick on arXiv if I might publish in a closed journal later?
→ Identify the field → route to a server (see the matrix) → assemble metadata → choose a license → run the journal-policy check before posting → after acceptance, link the published DOI back to the preprint.
When to Use This Skill
Use this skill when the user wants to act on a preprint — post it, choose where, prepare its metadata/license, or reconcile it with a journal or a published version. Core jobs:
- Server selection — match field + manuscript type to arXiv, bioRxiv,
medRxiv, SSRN, or OSF Preprints. See
references/server_selection.md. - Submission metadata — title, authors + ORCID, abstract, **arXiv primary
- cross-list categories** or bioRxiv/medRxiv subject collection, funding,
declarations. See
references/submission_metadata.md.
- cross-list categories** or bioRxiv/medRxiv subject collection, funding,
declarations. See
- License choice — pick from each server's actual license set and explain
the downstream commitment (e.g. CC BY is irrevocable; a later journal may
object to a permissive preprint license). See
references/licensing.md. - Versioning & DOI — arXiv versions (v1, v2, …) are immutable and permanent; a withdrawal is a new version with a tombstone, never a deletion; bioRxiv/medRxiv assign a DOI on posting and accept revisions.
- Journal preprint policy — query the Sherpa Romeo v2 API for the
target journal's prearchiving (preprint) policy before posting. See
references/journal_policy.md. - Post-publication linking — connect the preprint to the published article
(publisher field on the server; the keyless
api.biorxiv.org/pubs/endpoint surfaces bioRxiv→journal links).
What ships with it
8 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.
- evals/evals.json 6.6 KB
- references/journal_policy.md 2.8 KB
- references/licensing.md 3.5 KB
- references/server_selection.md 4.5 KB
- references/submission_metadata.md 3.0 KB
- scripts/journal_policy.py 6.1 KB runs code
- scripts/preprint_link_check.py 4.8 KB runs code
- scripts/server_recommender.py 6.2 KB runs code
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.
- 6d ago First seen · 208 lines · 271 tokens per session scan A 6715b840bec3
alterlab-preprint-deposition is a skill published in the GitHub repository AlterLab-IEU/AlterLab-Academic-Skills (66 stars, last pushed 7d ago), licensed MIT. It adds 271 tokens to every session and 3,192 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
academic-slides
Create Beamer-inspired academic HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build slides for a conference talk, lecture, seminar, or thesis defense. Supports theorem environments, KaTeX equations, algorithm pseudocode, and citations. Helps academics discover their…
ob-hrm-scale-adaptor
A guide for adapting organisational behaviour and human-resources survey scales across languages and cultures. It covers permission checks, translation and back-translation, expert review, participant interviews, and tests of whether groups interpret the scale comparably.
r-spss-syntax-architect
A guide for turning research hypotheses into repeatable R or SPSS code for statistical analysis. It covers panel data, where the same companies or other units are observed over time, as well as interaction effects, curves, and mediation.
phd-milestone-tracker
A tracker for planning and monitoring the academic milestones of working business doctoral students.
q1-journal-reviewer
A simulated anonymous review by a demanding business-research journal referee. It examines a complete paper for contribution, causal reasoning, robustness checks, mechanisms, and the difference between statistical and real-world importance.
tej-data-scout
A research-planning guide that checks whether a proposed study can use data from a database such as TEJ, Taiwan’s financial and economic data service. It breaks the topic into variables, finds likely data sections, checks coverage and frequency, and notes gaps that still need confirmation.