Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This collection provides structured support for biomedical researchers navigating the transition from draft to submission. It focuses on the technical and ethical precision required for peer review, offering tools to calibrate claim strength and ensure internal consistency across complex documents.
The skills streamline the final stages of academic writing, helping authors identify placeholder data, remove LLM artifacts, and verify references to reduce moderation risks during preprint uploads.
WHO IT'S FOR
Biomedical researchers
preparing manuscripts for peer review and submission
Academic authors
responding to peer reviewer feedback and rebuttals
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Source preference: bioRxiv, medRxiv, arXiv, or all
Optional narrower sub-topic
Check the repository for this skill’s setup.
Use the preprint-surveillance-finder skill to scan <biomedical topic> over the last 14 days across <bioRxiv, medRxiv, arXiv, or all>. Give me a concise emerging-topic report with a few hot-topic clusters, quiet but notable areas, and manual search strings for verification. State whether you used live retrieval or knowledge-synthesis mode, and do not invent papers, authors, or identifiers.
Use the pca-dimensionality-reduction skill on <input_file> and write results to a new directory at <output_dir>. Use <numeric feature columns>, with <sample ID column> and <group column> if provided. Start with the default PCA settings, then briefly summarize explained variance, visible sample separation, and the strongest feature loadings.
Create a structured bibliography from a small reading folder
Uses bibliography
Input directory containing Markdown, DOCX, or TXT literature files
New empty output directory
Desired bibliography CSV path within that output directory
Check the repository for this skill’s setup.
Use the bibliography skill to process the literature files in <input_directory> and save the two required outputs in a new empty directory at <output_directory>: a consolidated summary Markdown and <output_directory>/bibliography.csv. For this first pass, use a small folder of Markdown, DOCX, or TXT files. Organize each document by title, summary, keywords, experimental methods, key conclusion, and one-sentence commentary, following the supplied CSV template.
Claude
Codex
Cursor
OpenClaw
OpenCode