Ext Ops Panel
Open dashboard
Comparison

sciagent-skills vs Arquestra — Scientific Computing Orchestration

sciagent-skills is a plugin bundle for AI coding tools published by jaechang-hits. Marketplaces we read that list it: 2 (Claude Code: claude-plugins-community, Community GitHub marketplaces). Arquestra — Scientific Computing Orchestration is an MCP server published by Apertura-AI. Marketplaces we read that list it: 2 (Official MCP Registry, Claude Code: claude-plugins-community). As of our marketplace pass on 2026-11-08. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplacesciagent-skillsArquestra — Scientific Computing Orchestration
Claude Code: claude-plugins-community Listed
Version: 1.0.0
Forks (GitHub): 46
Stars (GitHub): 386
Not marked · First seen
Listed
Version: 0.2.0
Forks (GitHub): 0
Stars (GitHub): 0
Not marked · First seen
Official MCP Registry Not listed Listed
Version: 0.2.0
Forks (GitHub): 0
Stars (GitHub): 0
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

sciagent-skills vs Arquestra — Scientific Computing Orchestration
Factsciagent-skillsArquestra — Scientific Computing Orchestration
Marketplaces that list it22
Stars (GitHub) (differs)386 (better)0 (worse)
Forks (GitHub) (differs)46 (better)0 (worse)
Last releaseNot publishedNot published
Where it runs (differs)Installs as a plugin bundleRemote server (api.apertura-ai.de/mcp/orchestration)
Transport (differs)Not statedStreamable HTTP
Tools it declaresNot publishedNot published
Environment variables it asks forNot publishedNot published
Parts of the bundle (differs)1391
Licence (differs)CC-BY-4.0Proprietary
Repository (differs)github.com/jaechang-hits/sciagent-skillsgithub.com/apertura-ai/arquestra-claude-plugin
Changes in the last 7 days00
First seen2026-10-112026-10-11
Endpoint at the last check (differs)no remote endpoint we checkStatus out of date: no HTTP response at the last check 2 days ago

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

sciagent-skills

In its own words, on Claude Code: claude-plugins-community:

197 ready-to-use life sciences skills that turn Claude into a domain expert for genomics, proteomics, drug discovery, biostatistics, scientific computing, and scientific writing. Each skill provides runnable code examples, key parameters with defaults, and troubleshooting guides for tools like Scanpy, RDKit, BioPython, PyMC, AutoDock Vina, and 190+ more. Scored 92.0% on BixBench-Verified-50 benchmark (+26.7%p over base Claude). Skills are auto-discovered — just describe your task and Claude finds the relevant skill.

Arquestra — Scientific Computing Orchestration

In its own words, on Official MCP Registry:

AI orchestration for computational chemistry and HPC workflows.

How to run each

sciagent-skills As a Claude Code plugin

Claude Code
/plugin marketplace add anthropics/claude-plugins-community
/plugin install sciagent-skills@claude-community

Arquestra — Scientific Computing Orchestration As a Claude Code plugin

Claude Code
/plugin marketplace add anthropics/claude-plugins-community
/plugin install arquestra@claude-community

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Only Arquestra — Scientific Computing Orchestration has a remote endpoint we check. How we check endpoints

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

Neither one's marketplaces publish the settings it asks for.

What it can do: sciagent-skills · What it can do: Arquestra — Scientific Computing Orchestration · Compare two other plugins

Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built