MCP App StoreMCP App StoreSKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
skills
Human-guided, defensive exploratory data analysis for scientific datasets: capture context first, propose one step, run disposable scripts, and keep an append-o
claude-skill-registry
Zero-context verification that every numeric claim in a paper matches raw result files; detects rounding, cherry-picking, config mismatches and scope overclaims
CTF Skills Collection
Generate a concise, reproducible submission-style CTF writeup with a one-path solution script, metadata, and a short checklist for fast verification.
skills
Guide and reference for marimo — a reactive Python notebook system that stores notebooks as pure .py files, enabling reproducible, Git-friendly workflows, app d
aiwg
Package selected subsets of a research corpus into portable archives (tar.gz/zip) including PDFs, analysis, citations and BibTeX with manifest and provenance.
sparky
CLI tools to read, edit, and execute SolveIt dialogs (notebook-like dialogs with code, note, prompt cells) and return JSON results for automation workflows.
marketplace
Execute a README-first smoke test and produce standardized reproducibility outputs (`repro_outputs/`) and PATCHES.md — trusted reporting for repo reproduction r
auto-claude-code-research-in-sleep
Zero-context auditor that verifies every numeric claim in a paper against raw result files to catch rounding, cherry-picks, and config mismatches.
vibe-research-skill
Structure and maintain research projects with bi-directional sync between code, paper.md, and developer docs to keep experiments, documentation, and academic wr
a5c-ai
Integrate agent workflows with the Open Science Framework: create projects, upload materials, manage preregistrations, and generate DOI-backed artifacts.
aiwg
Export selected subsets of a research corpus into portable archives (tar.gz or zip) including PDFs, analysis, citations, and BibTeX for sharing or reproducibili
medical-research-skills
Produce structured, actionable peer review reports for manuscripts, theses, and internal research outputs, separating major validity issues from minor polish it
auto-empirical-research-skills
Practical guide to creating secure, reproducible sandboxed code execution environments using Docker, Nix, resource limits, and security best practices for resea
nemo-platform
Turn a domain rubric and dataset into a reproducible evaluation using the NeMo Evaluator SDK; generate configs, run local evaluations, and explain scores and fa