🔌
Plugins
Loading...
Showing 30 of 22815 results
AI development workflow: 21 skills for brainstorming, planning, TDD, debugging, code review, security audit, safety guardrails. One plugin, adapts to your project.
Fail-closed CloakBrowser workflows through exact managed Playwright CLI and Chrome DevTools MCP transports; Webwright runtime and fallbacks are forbidden.
Сквозной дизайн-воркфлоу: Figma → код → токены → FSD → shadcn/ui → ReactBits → browser-валидация. 5 скиллов + /ry-design. Skills-only - MCP transport from rldyour-mcps.
Скиллы технического и веб-исследования + ry-explore субагент глубокого анализа (Opus 4.8 1M via opus[1m], max effort) через Context7/DeepWiki/Grep MCP. /ry-explore slash command included.
Автономный SDLC-воркфлоу: ry-init/start/newp/review/deploy/sync + 6 reviewer subagents + post-task-sync + instruction-docs-sync. Хуки SessionStart/PreToolUse/PostToolUse/Stop. Tracked AI context on main.
LSP-воркфлоу: маршрутизация, health-check, brew-first установка, Serena LSP integration. 4 skills + 2 scripts + 3 references. Покрывает Python/Rust/Dart/TS/Go/C++/Qt/YAML/Docker/HTML/CSS/Shell/JSON/TOML/Markdown.
Транспортный слой MCP - 11 серверов с зафиксированными версиями: Serena, Sequential Thinking, Chrome DevTools, Context7, DeepWiki, Grep, shadcn, Dart/Flutter, Figma, OpenAI Docs, GitHub.
macOS cmux orchestrator-режим: оркестратор-терминал делегирует worker-терминалам через cmux send/read-screen/events; роль активируется декларацией в /ry-init. Устанавливается только на macOS.
rtk token-economy core: гарантированный PreToolUse Bash hook сжимает вывод команд через rtk (Rust Token Killer) до попадания в контекст + skill token-economy + /rtk-gain. Внешний бинарь rtk (Apache-2.0), не MCP; graceful passthrough без rtk.
Quality-first инженерные правила: clean architecture (FSD/VSA/Hexagonal), implementation discipline, dependency policy + supply chain (SLSA L2), verification gates (pyright/ruff/ESLint v9), AGENTS.md/.claude/CLAUDE.md/MADR 4.0.0, /ry-rules-review.
Безопасность по OWASP Top 10 2025 при реализации + защитный Mythos-style security review через /ry-sec-review slash command.
Семантический воркфлоу через Serena MCP + .serena memory sync markers. UserPromptSubmit/PreToolUse/PostToolUse hooks only; Stop orchestration belongs to rldyour-flow.
Recursive Language Model (RLM) v3 — dual-mode execution, git-aware incremental analysis, memory persistence, token-aware processing, and multi-agent orchestration
AI agent that fully tests React Native features on simulator/emulator — navigates the app, verifies UI, walks user flows, and confirms internal state.
Research-first methodology with skills-first enforcement for Claude Code
Generate a self-contained interactive HTML Gantt chart from a markdown roadmap file — /roadmap
Organise defined feature requirements into a sequenced, release-grouped roadmap and communicate it in user-benefit terms.
Plan a strategic roadmap across prioritization, epics, stakeholders, and sequencing.
Convene an adversarial council to pressure-test an idea before you commit — five rival personas plus a Judge that returns GREEN LIGHT / RESHAPE / KILL and the cheapest 48-hour test.
Pressure-test a business idea before you build it. Convenes a 5-angle adversarial panel — The Critic (what kills this?), The Champion (the 10x upside?), The Analyst (does the logic hold?), The Investigator (what does the market say?), The Customer (would I actually pay?) — fired in parallel as independent reviewers, then a Judge synthesizes one GO / RESHAPE / KILL verdict with explicit confidence and the cheapest 48-hour test to de-risk it. Never averages the scores: a weighted synthesizer with demand/fatal-flaw/logic veto gates produces the call, backed by deterministic stdlib tools.
Connect Claude to Roblox Studio on macOS via MCP, with skills for Luau scripting, game architecture, and Studio mode guidance
Connect Claude to Roblox Studio on Windows via MCP, with skills for Luau scripting, game architecture, and Studio mode guidance
Robot Framework execution layer for analysis, authoring, review, and flake repair; full workflows also require app-exploration and test-analysis
Robotics & autonomous-systems engineering team — 3 agents (robotics-architect-lead, ros-motion-planning-engineer, perception-and-autonomy-engineer) across the three engines of a robot program: system architecture (ROS 2 computation graph & DDS, compute/sensor selection, the real-time vs non-real-time split, safety architecture, sim-to-real), the motion stack (ROS 2 nodes/topics/actions, MoveIt/Nav2 planning, kinematics, PID/MPC control, coordinate frames/TF), and perception & autonomy (sensor fusion, SLAM, EKF state estimation, localization, behavior-tree/state-machine autonomy). Ships 4 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 reference), 5 best-practices, 2 templates, 2 commands. Engineering decision-support, not functional-safety certification advice: safety-standard pointers (ISO 10218/13849), DDS/distro landscape, and sensor/compute specifics carry a retrieval date + verify-at-use; no PII. Requires ravenclaude-core@>=0.7.0.
Discover and control a humanoid on the bench, characterize its real sensor + effector envelope into a machine-readable robot descriptor (the real-to-sim calibration card), and stage a sensor-calibrated, free-base Isaac Lab RL job from that descriptor — generalizable to new humanoids. Verified on a Unitree G1 EDU.
John D. Rockefeller — Ledger A discipline, crisis as opportunity. Grounded in Chernow's Titan.