Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Summary

Agent skills for building quantum computing workflows on aqora.io and beyond.

Install to Claude Code

/plugin install aqora-skills@aqora-io-skills

Run in Claude Code. Add the marketplace first with /plugin marketplace add aqora-io/skills if you haven't already.

README.md

Aqora Skills

Agent skills for building quantum computing workflows. Equip your AI coding agent to design circuits, run simulators, orchestrate quantum optimization, and pair-program inside live aqora-hosted marimo notebooks. Works with Claude Code, opencode, pi, GitHub Copilot, Cursor, Codex, and any agent that reads the Agent Skills open standard.

The repo treats the platform (aqora workspaces) and the domain (quantum computing) as two complementary axes. Platform skills know how to drive a live workspace. Domain skills know qiskit, pennylane, circuit optimization, and simulator choice. Together they cover the full loop from "sketch a circuit" to "run it on a simulator in an aqora workspace and compare results."

Available Skills

| Skill | Purpose | | :---- | :------ | | aqora-workspace | Pair-program inside a live aqora-hosted marimo workspace. List workspaces, execute code in the remote kernel, create and edit cells. The entry point for running quantum code on aqora. |

Roadmap

  • quantum: qiskit and pennylane authoring, circuit construction and transformation, simulator selection (numpy, qiskit, pennylane), gate-count and depth optimization, QAOA and VQE templates. Pairs with aqora-workspace when the agent needs to run circuits on aqora infrastructure.
  • Additional platform skills as the aqora API grows: dataset management, competition submission, and workspace search.
  • Additional domain skills for adjacent quantum tooling as the ecosystem evolves.

Installation

Claude Code

/plugin marketplace add aqora-io/skills
/plugin install aqora-skills@aqora-io-skills

Enable auto-update to stay current:

/plugin  ->  Marketplaces  ->  aqora-io-skills  ->  Enable auto-update

Any Agent Skills Compatible Tool

Works with any agent that supports the Agent Skills open standard, including opencode, pi, GitHub Copilot, Cursor, and Codex.

Install everything:

npx skills add aqora-io/skills

Install a single skill:

npx skills add aqora-io/skills --skill aqora-workspace

If you do not have npx but have uv:

uvx deno -A npm:skills add aqora-io/skills

Manual

Clone this repository and symlink individual skill directories into your agent's skills path. Common locations:

| Agent | Path | | :---- | :--- | | Claude Code | ~/.claude/skills/<skill-name> | | opencode | ~/.config/opencode/skills/<skill-name> | | pi | ~/.pi/agent/skills/<skill-name> | | GitHub Copilot | ~/.copilot/skills/<skill-name> |

Only the leaf skill directory matters. The skills/ parent is not copied.

Quick Start

After installing, log in to aqora so the skills can authenticate:

pip install aqora-cli
aqora login

Then ask your agent a workspace question, for example:

  • "list my aqora workspaces"
  • "in my portfolio-optimizer workspace, add a cell that runs QAOA on the pennylane simulator and plots the efficient frontier"
  • "open the numpy-simulator workspace and sanity-check the Hadamard gate"

The agent loads the relevant skill, targets the right workspace, and starts working. Cells appear live in the workspace UI.

Philosophy

Skills in this repo follow three rules.

1. Portable first, Claude Code second. Skills are authored to the Agent Skills open standard. Claude Code manifests sit on top as an overlay. If a piece of guidance only applies to one agent, it belongs in a reference file, not the skill body. 2. Progressive disclosure. The body of SKILL.md is short and action-oriented. Depth lives in references/*.md files the body links to. Only the body enters context on invocation. References load on demand. 3. Scripts own the machine, kernels own the state. Bundled scripts run on the user's machine and talk HTTP. Business logic lives in the remote kernel, driven through marimo._code_mode.

Development

See CONTRIBUTING.md for authoring conventions, frontmatter rules, and the validation script CI runs on every pull request.

Credits

The execute-code script pattern is adapted from marimo-team/marimo-pair. Credit to the marimo team for the design.

License

MIT. See LICENSE.

Related plugins

Browse all →