Research agent
Forschungspipeline fuer PubMed und arXiv. Schnellrecherche und strukturierte Literatur-Reviews mit reiner Python-Standardbibliothek.From its SKILL.md
npx -y skills add ellmos-ai/skills --skill research-agentAssembled 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
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
| Quelle | API | Rate-Limit | Zugang |
|---|---|---|---|
| PubMed | NCBI E-utilities | 3/s (ohne Key), 10/s (mit Key) | Frei |
| arXiv | Atom REST API | Keine dokumentiert | Frei |
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
scripts/
- agent.pyruns10.5 KB
- __init__.pyruns276 B
- __main__.pyruns83 B
- sources/arxiv.pyruns5.3 KB
- sources/base.pyruns4.0 KB
- sources/__init__.pyruns248 B
- sources/pubmed.pyruns7.8 KB
- workflows/__init__.pyruns301 B
- workflows/literature_review.pyruns7.8 KB
- workflows/quick_search.pyruns3.8 KB
- banner.png199.7 KB
- SKILL.en.md3.0 KB
- SKILL.es.md3.2 KB
- SKILL.fr.md3.2 KB
- SKILL.ja.md3.3 KB
- SKILL.ru.md3.8 KB
- SKILL.zh.md3.0 KB