agentsclimarketplace

Research agent

Skill ellmos-ai/skills/skills/research/research-agent

Forschungspipeline fuer PubMed und arXiv. Schnellrecherche und strukturierte Literatur-Reviews mit reiner Python-Standardbibliothek.From its SKILL.md

Install
npx -y skills add ellmos-ai/skills --skill research-agent

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.1 KB, 612 tokens by cl100k_base, as published. Nobody here has run it

<img src="banner.png" width="100%" alt="research-agent banner">

Research Agent

Modulare Forschungspipeline fuer wissenschaftliche Literaturrecherche. Nutzt ausschliesslich Python-Standardbibliothek (urllib, xml, json).

Architektur

ResearchAgent (Orchestrator)
  sources/          Datenquellen (PubMed, arXiv)
    base.py         Article/SearchResult Dataclasses, Source ABC
    pubmed.py       NCBI E-utilities (esearch + efetch)
    arxiv.py        arXiv Atom API
  workflows/        Recherche-Ablauefe
    quick_search.py Schnellrecherche ueber mehrere Quellen
    literature_review.py  4-Phasen Literatur-Review

Nutzung als Python-Library

from scripts.agent import ResearchAgent

agent = ResearchAgent()

# Schnellrecherche
result = agent.search("machine learning diagnostics", max_results=10)
print(result)

# Strukturierter Literatur-Review
plan = agent.create_review_plan("transformer architectures", years=3)
print(plan.total_articles, "Artikel gefunden")

# Ergebnis speichern
agent.save_result(result, "recherche_ml.md", fmt="markdown")

Nutzung als CLI

cd scripts
python -m ResearchAgent search "quantum computing" --max 20
python -m ResearchAgent review "CRISPR gene editing" --years 5

Datenquellen

QuelleAPIRate-LimitZugang
PubMedNCBI E-utilities3/s (ohne Key), 10/s (mit Key)Frei
arXivAtom REST APIKeine dokumentiertFrei

Erweiterbar: Neue Quellen implementieren Source ABC aus sources/base.py.

Erweiterung

from scripts.sources.base import Source, SearchResult

class MySource(Source):
    @property
    def name(self) -> str:
        return "my-source"

    def search(self, query, max_results=10, **kwargs):
        # API-Abfrage implementieren
        ...

    def get_article(self, article_id):
        ...

    def is_available(self) -> bool:
        return True

BACH-Hinweise

Nur relevant bei Nutzung innerhalb von BACH.

from scripts.agent import ResearchAgent
agent = ResearchAgent(use_bach=True)  # Optionale BACH-Integration

Changelog

0.1.0 (2026-03-12)

  • Migration aus MODULAR_AGENTS/ResearchAgent in Skillbibliothek
  • PubMed + arXiv Quellen
  • QuickSearch + LiteratureReview Workflows

What ships with it: 17 files

259.3 KB alongside SKILL.md, 10 of them executable

Keep looking

Skills are one crate of 326,782. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.