MCP App StoreMCP App Store
from auto-empirical-research-skills1,840
Practical guide to creating secure, reproducible sandboxed code execution environments using Docker, Nix, resource limits, and security best practices for resea
Provides step-by-step guidance for setting up sandboxed execution environments for reproducible research: Dockerfiles, resource-limited subprocess execution, Nix shells, and CI integration. Emphasises security controls (network isolation, read-only mounts, non-root users) and reproducibility for multi-language research workflows.
Use when running untrusted code, building reproducible research pipelines, or integrating sandboxed executions into CI/CD. Valuable for researchers, data scientists, and platform engineers who need safe and repeatable execution environments.
Best used by ops and research-focused agents (Claude Code, Cursor, Codex CLI) and general assistant tooling that can generate container configs and CI pipelines.
Documentation-only skill providing a guide to sandboxed code execution environments for research computing. Covers Docker containers with resource limits, Python subprocess isolation, Nix reproducible environments, and CI/CD integration. No bundled scripts to run. Well-written content with practical code examples, but serves as a reference guide rather than an actionable automation skill.
Clean skill with no security concerns. Content promotes security best practices (network isolation, non-root users, resource caps). The Python code example is educational, not executable as a tool. Architecture is straightforward — single SKILL.md with no scripts or references directory. Usefulness is limited because it's a guide, not an automated tool — users would need to manually adapt the examples.
Obsidian CLI
Control and automate an Obsidian vault from the command line: read, create, search, update notes, manage tasks, and support plugin/theme development.
Database Search Skills (31)
A collection of 31 database-specific literature search skills (arXiv, PubMed, OpenAlex, IEEE, Google Scholar guides) to discover, query, and retrieve academic p
Digital Humanities Guide
Practical recipes and code for applying computational methods—text mining, topic modeling, network analysis, and spatial/archival techniques—to humanities resea
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Reverse Engineer
Provides step-by-step guidance and best practices for binary reverse engineering: static analysis, dynamic tracing, disassembly, and documentation workflows for
Sync Production Database to Development
Run a safe, scripted workflow to download production database dumps and restore them into a development environment (download-only and restore options).
Sandbox0 Integration
Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.
arxiv2md
Convert arXiv papers into clean, LLM-ready Markdown via a REST API or CLI for fast reading, summarization, and downstream processing.
CTF Write-up Generator
Generate a concise, reproducible submission-style CTF writeup with a one-path solution script, metadata, and a short checklist for fast verification.
Minimal Run & Audit (repro reporting)
Execute a README-first smoke test and produce standardized reproducibility outputs (`repro_outputs/`) and PATCHES.md — trusted reporting for repo reproduction r
Scite Database (Smart Citations)
Query Scite.ai Smart Citations by DOI to report supporting, contrasting, and mentioning citation counts and help assess a paper's reliability.