All authors
Claude Skills by nexuslinkproductions
github.com/nexuslinkproductions1,031 skills11 installs2,544 views
- Visual PlanTurn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.Votes: 0GitHub stars: 2
- Viz LabBuild best-in-class, real-data-grounded visualizations of YURI's own systems — energy/ΔU surfaces, quantum Q-spheres, circuitry graphs (2D edge-bundling + 3D die), telemetry cockpits, embedding atlases. Use when the task is to visualize, depict, render, or make interactive any YURI math / quantum / graph / telemetry data, build a 3D / WebGL / three.js / react-three-fiber or D3 visualization, turn a flat view into 3D, or prototype a viz before wiring it into the app. Triggers: visualize, viz, ...Votes: 0GitHub stars: 2
- Write A SkillCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.Votes: 0GitHub stars: 2
- Writing PlansUse when you have a spec or requirements for a multi-step task, before touching codeVotes: 0GitHub stars: 2
- Writing SkillsUse when creating new skills, editing existing skills, or verifying skills work before deploymentVotes: 0GitHub stars: 2
- Yuri Code IntelligenceUnified code quality intelligence layer that diagnoses code smells (Long Method, Feature Envy, design pattern issues), prescribes targeted Fowler refactoring techniques, and reviews code for security, performance, and clarity. Use when user says 'review this code', 'refactor this', 'what's wrong with this method', 'code smells', or 'clean this up'.Votes: 0GitHub stars: 2
- Yuri Sales IntelligenceUnified sales and outreach skill generating cold outreach openers, social selling sequences, objection rebuttals, and ad creative for any paid platform — multi-persona aware, adapting tone and offer frame to buyer type. Use when user says 'write a cold email', 'outreach sequence', 'objection handling', 'ad copy', or 'sales pitch'.Votes: 0GitHub stars: 2
- Yuri Shura6-perspective adversarial review for high-stakes turns (architecture decisions, refactor planning, deployment review) — fans out architect, adversary (7-vector attack), maintainer, ops, product, and security perspectives in parallel, then consolidates. Use when user says 'review this decision', '/shura', 'adversarial review', 'what could go wrong', 'architecture review', or 'deployment review'.Votes: 0GitHub stars: 2
- Zoom OutTell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.Votes: 0GitHub stars: 2
- Deepseek OffloadOffload task to DeepSeek or other neural lanes (no Agent spawning). Primary DeepSeek entry point — use for flash extraction, pro reasoning, research, and NVIDIA lanes.Votes: 0GitHub stars: 2
- Deepseek WorkhorseYURI Workhorse X1 — DeepSeek-backed orchestration for structured reasoning, planning, and execution via forge/plan/execute pipeline.Votes: 0GitHub stars: 2
- Openclaw OffloadAlways-on autonomous check daemon running natively in Musubi. Runs every 33min via LaunchAgent — proactive system health, memory pulse, external signal checks, vault alerts. The 09OC research lane is retired into @deepseek-flash.Votes: 0GitHub stars: 2
- Gan Loop**Role:** Score generated content against rubric. Provide specific, actionable feedback. **Constraint:** Read rubric fresh every iteration. Don't grade on "improvement"—grade on absolute quality. **Style:** Direct, evidence-based, with exact quotes and fix suggestions ---Votes: 0GitHub stars: 2
- Activate Yuri SkillsRecall and load the minimal canonical YURI skill set before every substantive YURI task, including implementation, analysis, research, planning, review, or verification. Do not use for trivial acknowledgements or status-only replies.Votes: 0GitHub stars: 2
- Adversarial VerificationUse when verifying completed work, reviewing Claude or Codex output, wiring routes or adapters, relaunching lanes, committing, pushing, or avoiding first-run confidence.Votes: 0GitHub stars: 2
- Agent ScoutCreate and configure Scout research assistant agent. Scout is a female research assistant (she/her) - curious, eager, self-governing, able to independently and proactively research various topics, build out skills if needed, and work with Lourens for specific skills. Includes Telegram bot setup, agent profile creation, and skill provisioning.Votes: 0GitHub stars: 2
- Agentic Engineering Fleet DisciplineGoverning a multi-agent fleet (OMP/MURE) for real deliverables — right-sizing governance vs mission, owner-vs-peer authority, OMP producer dispatch reliability (M3 empty-yield), sandbox confinement, and avoiding conservative stalls. Use when orchestrating governed producers/reducers/verifiers, dispatching via compileOmpSpawn/task, or when a governance ceremony is blocking delivery.Votes: 0GitHub stars: 2
- Audit Log FirewallPolicy-based monitoring and command-line enforcement for high-risk agent operations. Intercepts sensitive commands and logs them for human auditing.Votes: 0GitHub stars: 2
- Auto ResearchUse when running or designing a measured self-improvement loop on a YURI subsystem — "climb this metric", "optimize the resolver", "autoresearch", "improve X until the score goes up" — or when deciding whether a subsystem is loop-improvable at all. Also use before touching an evaluator, benchmark, or scorer while a loop is in flight.Votes: 0GitHub stars: 2
- Browser HarnessDirect browser control via CDP. Use when the user wants to automate, scrape, test, or interact with web pages. Connects to the user's already-running Chrome.Votes: 0GitHub stars: 2
- Cgs MoldTurn a gun scan into a handoff-ready custom-gear.ch (René Spatz) holster split-mold, fully inside Blender via blender-mcp. Use when the owner says "make a mold from this scan", "cgs-mold", "turn <gun> scan into a mold", or provides a gun scan + active Blender MCP and asks for a holster mold. Blender-only — no FreeCAD.Votes: 0GitHub stars: 2
- Cheap Tier Recon DispatchWhen dispatching cheap recon / spec-drafting work in a MURE workflow, fan across canary-proven cheap-tier routes by sub-task rather than running it inline in Sol. Trigger: any R0 read-only recon or R1 spec drafting that can be split across cheap-frontier models.Votes: 0GitHub stars: 2
- Claude Output LaneRoutes reusable Claude output (plans, ideas, findings, reviews, draft artifacts, diff proposals, questions, decisions, evidence packets) for Codex/main inspection. Use when Claude produces structured output that another lane must inspect, or when mentioning 'Claude output', 'lane handoff', 'output routing', or 'cross-lane artifact'.Votes: 0GitHub stars: 2
- Codex Plugin Control PlaneRoutes any Codex plugin, app connector, MCP tool, or plugin-provided skill through the YURI control plane before external reads, writes, browser actions, design, cloud, or GitHub tools are used. Use this before using any plugin capability inside YURI-OS-MUSUBI, or when mentioning 'plugin', 'MCP tool', 'app connector', 'browser action', 'design tool', 'GitHub tool', or 'tool_search'.Votes: 0GitHub stars: 2
- Commit Scope And Fix VerificationVerifying commit scope and distinguishing real fixes from test-narrowing/suppression. Use when auditing a commit, judging whether a green test reflects a genuine fix, classifying whitelist/allowlist exceptions, or navigating protected-path guards. Covers omnibus-commit hazards, verify-against-committed-state, live-vs-stale exception classification, and claim-by-claim adjudication of independent audits.Votes: 0GitHub stars: 2
- Design Assistant InboxUse when working from Chrome Design Assistant browser selections, pending visual design requests, or the local design-assistant MCP/HTTP bridge.Votes: 0GitHub stars: 2
- End Of TransmissionContinuous background reflection engine that auto-triggers at checkpoints (task completion, context ≥60%, after errors) and runs a full 9-phase pipeline on manual /eot. Use when context is nearing capacity, after completing a major task, after errors, or when you type /eot to trigger structured session reflection.Votes: 0GitHub stars: 2
- Executing PlansUse when you have a written implementation plan to execute in a separate session with review checkpointsVotes: 0GitHub stars: 2
- Failure Evolution LoopReal failure capture, root-cause analysis, regression design (outputs a runnable-test SPECIFICATION — does not write test files directly), and memory-driven improvement for Yuri OS / Yuri. Inspired by Zenkai / Saiyan Power, translated into enterprise-safe system behavior. Use when the user says 'capture this failure', 'analyze root cause', 'prevent regression', or 'learn from this bug'.Votes: 0GitHub stars: 2
- Fleet EconomyUse when orchestrating any non-trivial multi-part task with subagents or model lanes — builds, audits, refactors, research sweeps, migrations — or when deciding which model tier handles a unit of work, how wide to fan out, or whether a heavy lane should itself delegate. Triggers include "orchestrate", "fan out", "route to cheap/heavy models", "workflowz", "MoE", "MLP", "fleet", or a task large enough to split across agents.Votes: 0GitHub stars: 2
- Fleet Model EconomyUse when fanning out MURE/subagent lanes across model tiers, deciding cheap-vs-heavy routing, or orchestrating a fleet — the canonical doctrine now lives in the fleet-economy skill; load that instead.Votes: 0GitHub stars: 2
- Frontend DesignDesign skill for external, non-YURI, non-Kagami surfaces. Use when building client work, external products, public-facing sites, or any UI that is NOT YURI HUD or Kagami. Enforces high-end intentional design systems, prevents AI slop. For YURI/Kagami surfaces, use design-master instead.Votes: 0GitHub stars: 2
- Genjutsu Canvas GenerativeAlgorithmic and generative art with Canvas 2D - particles, flow fields, noise, fractals, L-systems.Votes: 0GitHub stars: 2
- Genjutsu CastCast genjutsu on a UI - creative coding for motion, micro-interactions, and wow-factor. Scans the stack, proposes an interaction thesis, loads the right sub-skills, implements the illusion. Adapts to Web, Android (Compose), Apple (SwiftUI).Votes: 0GitHub stars: 2
- Genjutsu Compose GraphicsAdvanced Compose visuals - Material 3 Expressive motion physics, AGSL shaders (Android 13+), Canvas/DrawScope generative, graphicsLayer effects.Votes: 0GitHub stars: 2
- Genjutsu Compose MotionJetpack Compose animation foundations - animate*AsState, AnimatedVisibility, Crossfade, updateTransition, SharedTransitionLayout, gestures.Votes: 0GitHub stars: 2
- Genjutsu Compose MultiplatformCompose Multiplatform / KMP patterns - expect/actual composables, platform-specific code, density and font handling cross-target, iOS/Android/Desktop interop.Votes: 0GitHub stars: 2
- Genjutsu Css NativeZero-dependency animations and visual techniques - scroll-driven, View Transitions, @starting-style, modern CSS.Votes: 0GitHub stars: 2
- Genjutsu Design AuditDesign audit checklist - motion gaps, accessibility, color consistency, responsive, performance.Votes: 0GitHub stars: 2
- Genjutsu Desktop PrinciplesDesktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.Votes: 0GitHub stars: 2
- Genjutsu Framer MotionFramer Motion / Motion sub-skill - AnimatePresence, layout animations, gestures, motion values.Votes: 0GitHub stars: 2
- Genjutsu GsapGSAP animation engine sub-skill - core, timeline, ScrollTrigger, plugins.Votes: 0GitHub stars: 2
- Genjutsu Mobile PrinciplesMobile-specific UX principles - touch targets, hover-less doctrine, thumb zones, safe areas, gestures, mobile perf budgets. Cross-platform (web mobile, iOS, Android).Votes: 0GitHub stars: 2
- Genjutsu Motion PrinciplesMotion design foundation - timing, easing, enter/exit patterns, accessibility, performance.Votes: 0GitHub stars: 2
- Genjutsu PaintPaint a complete visual universe with genjutsu - art direction brainstorm, design system, implementation, audit. Anti-AI-slop design pipeline. Adapts to Web, Android (Compose), Apple (SwiftUI).Votes: 0GitHub stars: 2
- Genjutsu Swiftui GraphicsAdvanced SwiftUI visuals - Metal shaders (.colorEffect, .layerEffect, .distortionEffect), .visualEffect, Liquid Glass (iOS 26), Canvas, holographic and CRT effects.Votes: 0GitHub stars: 2
- Genjutsu Swiftui MotionSwiftUI animation foundations - withAnimation, transitions, matchedGeometryEffect, PhaseAnimator, KeyframeAnimator, springs, gestures.Votes: 0GitHub stars: 2
- Genjutsu Threejs R3fThree.js and React Three Fiber sub-skill - 3D scenes, shaders, postprocessing.Votes: 0GitHub stars: 2
- Genjutsu Ui Ux Pro MaxUI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles...Votes: 0GitHub stars: 2
- Git Guardrails Claude CodeSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.Votes: 0GitHub stars: 2