Plugin Claude Code
Bundles 2 skills, 5 commands, 1 MCP server · 240 tokens together
Drive a local Ryu Core node from Claude Code: local models, agents, workflows, RAG Spaces, and any MCP server Ryu has registered, all behind one bundled MCP bridge.
Skill Claude CodeCodex
Build or migrate a Ryu Companion app with the fixed Ryu App UI v1 vocabulary. Use when an app needs buttons, forms, lists, detail panes, dashboards, empty states, or any visual polish shared with other Ryu apps.
Skill Claude CodeCodex
Author a new agent skill in the SKILL.md format used by this collection, so the Ryu skill ecosystem is self-extending. Covers the directory layout, the YAML frontmatter schema (name and description), writing skimmable instructional content, cross-referencing other skills, and validating the result. Use when adding a…
Skill Claude CodeCodex
Create and configure an agent on a Ryu node via Core's /api/agents REST surface. Covers listing, reading, creating, updating, and deleting agents, the full record schema (system prompt, engine, model, tools, skills allowlist, orchestrator and agent-creation toggles), and inspecting an agent's reachable tools. Use when…
Skill Claude CodeCodex
Search, download, and serve a local GGUF model on a Ryu node via Core's models and engines REST surface. Covers catalog search and device-fit, installing a specific quantization, activating a model, and listing engines (the engine is derived from the model format). Use when a user wants to get a local model running on…
Skill Claude CodeCodex
Drive a Ryu node through the apps/mcp MCP server. Covers configuring the stdio server with RYUCOREURL, the tools/list handshake, and every Ryu tool (ask Ryu, list/activate models, list agents and teams, run workflows, bridge to registered MCP servers, search RAG Spaces and skills). Use when an agent should operate a…
Skill Claude CodeCodex
Create, render, inspect, and transform PDF documents with a Ryu-owned React-first pdfcn/Takumi/Forme path plus reliable pypdf and pdf-lib workflows. Use when a user asks for PDF generation, editing, extraction, merging, forms, OCR, or visual verification.
Skill Claude Code
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
Skill Claude Code
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
Skill Claude Code
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via create-skill + unslop, optionally pulling fresh evidence from recent transcripts.
Skill Claude Code
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust.
Skill Claude Code
Restate the last message in plain human language, with no jargon.
Skill Claude Code
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
Skill Claude Code
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no…
Skill Claude Code
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.
Skill Claude Code
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
Skill Claude Code
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
Skill Claude Code
Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.
Skill Claude Code
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
Skill Claude Code
The Principles section below grounds every trigger. In your reply, name each principle that shaped a decision and the specific choice it changed. Cite only principles whose leaf SKILL.md you read this session.
Skill Claude Code
Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then question the premise instead of writing another fix that assumes it.
Skill Claude Code
Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.
Skill Claude Code
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
Skill Claude Code
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: