菜单
Automates systematic literature reviews using multi-agent AI workflows. Can perform title/abstract screening, full-text screening, and data abstraction.
| name | LatteReview (Systematic Review Automation) |
| description | Automates systematic literature reviews using multi-agent AI workflows. Can perform title/abstract screening, full-text screening, and data abstraction. |
| author | BioDockify AI Team (Integration of PouriaRouzrokh/LatteReview) |
| version | 1.0.0 |
This skill integrates the LatteReview framework to allow BioDockify AI to perform PhD-level systematic reviews.
from agent_zero.skills.latte_review import get_latte_review
latte = get_latte_review()
# Define Criteria
inclusion = "Studies using AI for drug discovery in oncology."
exclusion = "Review articles, non-English papers."
# Run Screening
output_csv = latte.screen_papers(
input_path="data/papers/candidates.csv", # Must have 'title' and 'abstract' columns
inclusion_criteria=inclusion,
exclusion_criteria=exclusion
)
print(f"Screening complete. Results saved to {output_csv}")
The skill uses LiteLLM under the hood. It will inherit the API keys from the BioDockify AI environment (e.g., OPENAI_API_KEY, GEMINI_API_KEY).
Recommends the best journals for an academic paper. Use this skill whenever an author wants to know where to submit their paper, asks for journal suggestions, wants to find suitable journals for their research, or asks "which journal should I submit to". Takes the paper abstract or full manuscript, gathers the author's preferences via interactive buttons, evaluates the quality and scope of the work, then produces an exhaustive ranked list of suitable journals drawn exclusively from the Scopus and WoS indexed journal database bundled with this skill. Enriches each recommendation with live metrics (IF, CiteScore, SJR, quartile) fetched from Scimago, JCR, and publisher pages. Delivers a formatted PDF report. Always trigger this skill — do not attempt journal recommendations without it.
A shared code repository for the PAN (Digital Text Forensics) research community. Includes tools for authorship attribution, profiling, and style analysis.
A shared code repository for the PAN (Digital Text Forensics) research community. Includes tools for authorship attribution, profiling, and style analysis.
Use when the user asks Agent Zero to operate the built-in Linux Desktop, XFCE apps, LibreOffice GUI apps, file manager, terminal, or visual desktop workflows.
Improves research paper quality via academic rewriting, summarization, and proofreading.
Verifies academic citations against real databases (Semantic Scholar, CrossRef, Europe PMC). Identifies fake or suspicious citations in research text.