claude-scientific-skills

there are two ways to consume this library.

1. the civilized way (search & browse)

go to the [static site](https://microck.github.io/ordinary-claude-skills/#/).

i have indexed everything with search and categories. it is much easier than digging through folders.

2. the developer way (raw files)

clone the repo to map these skills into your own mcp servers or agents.

1. clone the repo

```bash

git clone https://github.com/Microck/ordinary-claude-skills.git

cd ordinary-claude-skills

```

1. choose your weapon

* for claude.ai: go to your profile, hit custom skills, and upload the specific folder for the skill you want.

* for api/devs: point your mcp client or system prompt config to the relevant skill directory.

1. verify

ask claude can you use the [skill name] skill now? if it says yes, you are gucci.

• [overview](#overview)
• [features](#features)
• [skill catalog](#skill-catalog)
• [configuration](#configuration)
• [how-to examples](#how-to-examples)
• [troubleshooting](#troubleshooting)
• [dependencies](#dependencies)
• [license & credits](#license--credits)

skills are basically fancy prompt packages and scripts that teach claude how to do specific things without you having to explain the context every single time. they load lazily (only when needed), which saves context window space and keeps claude from getting confused by instructions it doesn't need yet.

this repo aggregates hundreds of skills from anthropic, composiohq, k-dense-ai, and random internet geniuses.

• non-curated selection: i dumped everything in here. if it doesnt work i probably havent noticed. just let me know and i may or may not fix it.
• categorized: everything is sorted so you don't have to doomscroll to find the python tools.
• standardized: i tried to keep the folder structures somewhat consistent.
• local first: designed to be cloned locally so you aren't dependent on a third party url staying up forever.

i used to list all 600+ skills here, but it made the readme scroll for eternity.

[view the full inventory on the documentation site →](https://microck.github.io/ordinary-claude-skills/#/)

categories include:

• science & academia (protein folding, astronomy, lab automation)
• software engineering (api design, debugging, testing)
• infrastructure (kubernetes, docker, terraform)
• data & ai (vector dbs, llm evaluation, rag)
• business (marketing, finance, legal)
• creative (writing, art, philosophy)
• web3 (solidity, smart contracts, defi)

getting this to work depends on your environment. here is the recommended way to set things up if you are using mcp or a local client.

file st