Maintainer of this skill?
by Innei
流儀 — a skills collection for coding agents and the artifacts workbench they design in: live artboards, commentable documents, HTML test benches, TDD builds
# Add to your Claude Code skills
git clone https://github.com/Innei/ryugiGuides for using ai agents skills like ryugi.
See how ryugi compares with popular alternatives.
ryugi is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Innei. 流儀 — a skills collection for coding agents and the artifacts workbench they design in: live artboards, commentable documents, HTML test benches, TDD builds. It has 317 GitHub stars.
ryugi's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/Innei/ryugi" and add it to your Claude Code skills directory (see the Installation section above).
ryugi is primarily written in Shell. It is open-source under Innei on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh ryugi against similar tools.
No comments yet. Be the first to share your thoughts!
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
/plugin marketplace add Innei/ryugi
/plugin install ryugi@ryugi-dev
Then send Let's make a react todo list. Ryugi starts brainstorming before any code, draws the
options instead of describing them, and builds what you approve under TDD.
Artboard. Every option side by side, drawn live while you watch. Two of them are chosen here;
Submit sends the round back with the brief. Comment on any pixel and answer in the terminal
(q1 → b).
Skills — the agent's development workflow: brainstorm, spec, TDD, debug, verify, worktrees.
Artifacts workbench — the surface they work on: an artboard for choosing between options,
documents to comment on, live HTML pages to tune, and a library across every project. It is not
limited to mockups or to brainstorming; architecture, reviews, proposals, test benches and
verification share the same canvas. The skills use it, and npx ryugi-artifacts opens it without
an agent.
flowchart LR
I[Idea] --> B[Brainstorm] --> A[Artifacts] --> S[Spec] --> T[Build · TDD] --> V[Verify] --> L[Land]
Skills fire on their own; there is nothing to invoke. After you sign off, the agent slices the spec into tasks, proves each one red-green, keeps a ledger of judgment calls across compaction, gets one fresh review of the branch, and reports how to land it. How it works →
Diagrams, charts, code, tables. A design document, a review, a proposal, a walkthrough of a flow: comment on a sentence, edit in place; your edits and the agent's merge live.
One surface, one dimension: a component, a type scale, a background, a motion. A one-page test bench with sliders that keep their values when the agent rewrites the page.
Built work next to the approved design, in the same canvas. Pass a group, or reject it and say what is off; it comes back fixed.
npx ryugi-artifacts
Local first, no subscription, no agent session needed. One server serves every project on the
machine: recent work across all of them, ⌘K to jump, artifact links that survive a restart and a
new release. publish shares one to Ryugi Cloud.
| Harness | Command |
|---|---|
| Antigravity | agy plugin install https://github.com/Innei/ryugi |
| Codex, Cursor | Add this repo as a local plugin source (detail) |
| Devin CLI | devin plugins install Innei/ryugi |
| Factory Droid | droid plugin marketplace add https://github.com/Innei/ryugi then droid plugin install ryugi@ryugi |
| Gemini CLI | gemini extensions install https://github.com/Innei/ryugi |
| Kimi Code | /plugins install https://github.com/Innei/ryugi |
| OpenCode | .opencode/INSTALL.md |
| Pi | pi install git:github.com/Innei/ryugi |
| Qwen Code | qwen extensions install Innei/ryugi |
| Hermes Agent | hermes plugins install Innei/ryugi --enable |
| Muse | muse plugins install ./ then muse plugins approve ryugi |
Updates and caveats: docs/install.md.
Fork of Superpowers v7.0.0 by Jesse Vincent and Prime Radiant (UPSTREAM.md). Issues and PRs welcome; AGENTS.md has the rules.
Skills, harness integrations and docs: MIT — LICENSE.
The artifacts application, published to npm as ryugi-artifacts, is proprietary (npm license: UNLICENSED) and not part of this repository. Releases up to 1.51.2 were published under AGPL-3.0-only.