#SkillRepo stars
- 14449Pair Programmingfrankxai/claude-skills-libraryAI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification. Use when pairing on code with driver/navigator roles, doing TDD, or wanting real-time review while building.48
- 14450Partner Anthropicfrankxai/claude-skills-libraryAnthropic intelligence — Claude model family, Claude Code, MCP protocol, Claude for Work programs, May 2026 state, Frank's relationship state, integration patterns. Use when generating Anthropic content, writing about Claude/MCP/Claude Code, partnership-conversation prep for Anthropic, or evaluating new Anthropic releases.48
- 14451Partner Arrowfrankxai/claude-skills-libraryArrow Electronics ECS intelligence — ArrowSphere marketplace, AI Accelerator program, Oracle Global Distributor of the Year 2025, Oracle x NVIDIA accelerator pack, May 2026 state, Frank's active strategic conversation, integration patterns. Use when generating Arrow content, writing about ArrowSphere or the EMEA distribution channel, partnership-conversation prep for Arrow, or evaluating new Arrow programs.48
- 14452Partner Googlefrankxai/claude-skills-libraryGoogle Cloud intelligence — Gemini (Nano Banana / Veo / Imagen), Vertex AI, ADK, A2A protocol, Cloud Partner Advantage, May 2026 state, Frank's relationship state, integration patterns. Use when generating Google Cloud content, writing about Gemini/ADK/A2A, partnership-conversation prep for Google, or evaluating new Google Cloud releases.48
- 14453Partner Nvidiafrankxai/claude-skills-libraryNVIDIA intelligence — NIM microservices, NeMo, NVIDIA AI Enterprise, DGX Cloud, Inception program, EMEA accelerator wave, May 2026 state, Frank's relationship state, integration patterns. Use when generating NVIDIA content, writing about NIM/NeMo/AI Enterprise, partnership-conversation prep for NVIDIA, or evaluating new NVIDIA releases.48
- 14454Partner Vercelfrankxai/claude-skills-libraryVercel intelligence — Next.js + Turbopack, AI SDK, AI Gateway, Fluid Compute, Sandbox, Queues, Agent, Vercel Partner Program, May 2026 state, Frank's relationship state, integration patterns. Use when generating Vercel content, writing about Next.js or the AI SDK, partnership-conversation prep for Vercel, or evaluating new Vercel releases.48
- 14455Performance Analysisfrankxai/claude-skills-libraryPerformance analysis, bottleneck detection, and optimization recommendations. Use when profiling slow code or systems, hunting a performance regression, or producing an optimization plan with measurable targets.48
- 14456Plan and Execute0xranx/agentbriefWrite a detailed plan before coding and execute it step by step43
- 14457Product Management Expertfrankxai/claude-skills-libraryProduct management expertise for strategy, discovery, prioritization, roadmaps, PRDs, metrics, and stakeholder communication. Use when defining what to build, why, and how to measure success.48
- 14458Prompt Hubfrankxai/claude-skills-libraryCompose the 13-agent Prompt Hub team via @prompt-conductor. Use when designing prompts, optimizing prompts, evaluating prompts, importing patterns from Fabric / awesome-chatgpt-prompts / awesome-claude-prompts, running IFS introspection or psychometric profiling, or building knowledge-base prompt sets. Auto-trigger on phrases like "design a prompt for X", "optimize this prompt", "evaluate my system prompt", "harvest patterns from Y", "rerank category Z", "IFS session", "profile me on Big Five", "build RAG prompts for X". The Hub is horizontal substrate — every FrankX pillar can use it. Compose48
- 14459QA Test and Fix0xranx/agentbriefWhen the user wants to find and fix bugs, or says 'QA this,' 'test this,' 'find bugs,' 'why is this broken,' 'it doesn't work,' 'check for bugs,' 'smoke test,' or after any significant code change. This is the full QA cycle: discover → reproduce → diagnose → fix → verify.43
- 14460R3f Scenefrankxai/claude-skills-libraryBuild one React Three Fiber scene that loads late, stops rendering off-screen, holds a designed still under reduced motion, and falls back to a poster without WebGL. Use when a page needs real geometry, a camera, lights, a model, or 3D interaction; when someone shares three.js, react-three-fiber, drei, or Three.js Journey material and asks for the effect; or when reviewing or repairing an existing <Canvas> for cost. Starts and ends in gpu-surface.48
- 14461Reactfrankxai/claude-skills-libraryCore React 19 patterns including hooks, Suspense, lazy loading, component structure, TypeScript best practices, and performance optimization. Use when working with React components, hooks, lazy loading, Suspense boundaries, or React-specific TypeScript patterns.48
- 14462Reasoningbank Agentdbfrankxai/claude-skills-libraryImplement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.48
- 14463Reasoningbank Intelligencefrankxai/claude-skills-libraryImplement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.48
- 14464Regression Testing0xranx/agentbriefWhen the user wants to prevent regressions, improve test coverage, or says 'add tests,' 'improve coverage,' 'we keep breaking this,' 'write regression tests,' 'characterization tests,' or after fixing a production bug to ensure it never recurs.43
- 14465Release Notes0xranx/agentbriefWhen the user needs to write release notes, changelogs, or document what changed in a release. Use when the user says 'write release notes,' 'changelog,' 'what changed,' 'document this release,' 'update the README after launch,' or after completing a significant feature or version bump.43
- 14466Remotion to Hyperframesfrankxai/claude-skills-libraryTranslate an existing Remotion (React-based) video composition into a HyperFrames HTML composition. Use ONLY when the user explicitly asks to port, convert, migrate, translate, or rewrite a Remotion composition as HyperFrames (e.g. "port my Remotion project to HyperFrames"). Do NOT use when (a) authoring a NEW HyperFrames composition (even if A/B-testing a Remotion video); (b) Remotion is mentioned in passing; (c) Remotion code is shared as reference, not for translation; (d) the user wants "the same video as my Remotion one" without explicitly asking to migrate the source — treat as a fresh H48
- 14467Repo Masteryfrankxai/claude-skills-libraryMaster ACOS, FrankX, Starlight-Intelligence-System, arcanea, claude-code-config and full starlight/repos ecosystem. Architecture, skills/hooks/MCP map, harness integration points. Read CLAUDE.md/AGENTS.md/GROK.md first. Use MCPs (github, fs-starlight), gstack, subagents, grep, terminal. Excellence gates required. Trigger: repo, ACOS, ecosystem, mastery, cross-repo.48
- 14468Review Process0xranx/agentbriefStep-by-step workflow for conducting thorough code reviews43
- 14469Routine Contractfrankxai/claude-skills-libraryThe operating contract for any scheduled or unattended agent session — a cron job, a Routine, a CI-triggered agent, a nightly sweep. Use when writing, reviewing, debugging or scheduling automation that runs without a human present, and whenever a scheduled job reports success but you cannot find what it produced. Defines preflight, why unattended sessions must not call orchestration tools that require user opt-in, the three-bullet digest that makes output durable, and why a run that persists nothing must exit non-zero rather than report green.48
- 14470Santa Methodfrankxai/claude-skills-librarySend a finished change to two reviewers who did not write it, using one rubric, and stop after three rounds. Use before a public page, a priced artifact, or a pull request that changes behavior.48
- 14471Search Firstfrankxai/claude-skills-libraryLook for an existing repo, package, and skill before writing a new one. Use when starting a feature, adding a dependency, or about to create a folder or utility on Frank's machine.48
- 14472Security Reviewfrankxai/claude-skills-libraryScan a port or a diff before it lands, and apply the narrow deny list for this machine. Use before copying upstream skills, hooks, or commands into a repo or into the live Claude directory.48
- 14473Security Review0xranx/agentbriefSystematic checklist and process for reviewing code for security vulnerabilities43
- 14474Self Improving0xranx/agentbriefLearn from corrections, mistakes, and discoveries during conversations. When the user corrects you, when something fails unexpectedly, or when you discover a project-specific pattern worth remembering — record it as a learning so future sessions benefit automatically.43
- 14475Shadcnfrankxai/claude-skills-libraryshadcn/ui component library patterns with Radix UI primitives and Tailwind CSS. Use when creating tables, forms, dialogs, cards, buttons, or any UI component using shadcn/ui, installing shadcn components, or styling with shadcn patterns.48
- 14476Shader Backdropfrankxai/claude-skills-libraryBuild a slow, token-coloured shader backdrop behind a headline — mesh gradient, grain gradient, or another Paper Shaders field — with a CSS poster underneath and a designed still. Use when someone asks for an animated gradient background, a mesh or aurora gradient, a grainy gradient hero, a moving background, or shares a ShaderGradient or shadergradient.co link; and when translating a ShaderGradient configuration into a lighter engine. Starts and ends in gpu-surface.48
- 14477Sifrankxai/claude-skills-librarySuperintelligence router — composes /superintelligence reasoning with swarm execution only when verb intent demands it. Defaults to reasoning-only to prevent runaway swarm cost. Triggers — /si <ask>, "think deeply about X", "analyze X with full depth", or any ask requiring multi-perspective + first-principles + contrarian framing.48
- 14478Skill Builderfrankxai/claude-skills-libraryCreate new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.48
- 14479Social Media Strategyfrankxai/claude-skills-libraryPlatform-specific tactics, content optimization, audience growth, and analytics-driven social media strategy. Use when planning a social strategy, optimizing posts for a specific platform, or growing and measuring an audience.48
- 14480Source Driven Developmentfrankxai/claude-skills-libraryGround framework, SDK and API code in the current official docs before writing it, and cite them. Use before code against an external package, CLI or cloud API, when reviewing a PR that uses one, or before stating a version, price, model fact or security advisory.48
- 14481Sparc Methodologyfrankxai/claude-skills-librarySPARC (Specification, Pseudocode, Architecture, Refinement, Completion) development methodology with multi-agent orchestration. Use when running a structured spec-to-code workflow or decomposing a feature through the SPARC phases.48
- 14482Spartan Warriorfrankxai/claude-skills-libraryEmbody the unbreakable Spartan ethos of discipline, courage, and relentless excellence through laconic wisdom and warrior mentality forged in hardship. Use when facing procrastination or hardship and wanting disciplined, laconic resolve and a do-hard-things mindset.48
- 14483Specification0xranx/agentbriefWhen the user needs to write a PRD, feature spec, technical spec, or define requirements. Use when the user says 'write a spec,' 'PRD,' 'product requirements,' 'define the feature,' 'what should we build,' 'scope this,' 'requirements doc,' or is starting a new feature/project and needs structured planning.43
- 14484SQL Query Builder0xranx/agentbriefWhen the user needs help writing SQL queries, analyzing data, building reports, or says 'write a query,' 'SQL help,' 'pull this data,' 'how many users,' 'funnel analysis,' 'cohort analysis,' 'retention query,' or needs to extract insights from a database.43
- 14485Starlight Chroniclefrankxai/claude-skills-libraryThe reflective layer of the FrankX OS. A four-cadence practice — weekly Palace Review, monthly Survey, quarterly Constellation Census, annual Legacy Audit — that witnesses what's been built, blesses what is whole, and orients the next move from a sovereign vantage. Couples to /changelog as its factual underlayer. Use when invoking /palace, /chronicle, /bless, or when a Sunday reflection is requested.48
- 14486Strategic Compactfrankxai/claude-skills-libraryWrite what worked, what failed, and what is still open to a file, then compact at a phase boundary. Use when a long session is about to cross from research into editing, or from a finished milestone into the next task.48
- 14487Stream Chainfrankxai/claude-skills-libraryStream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows. Use when piping output between agents/tools as streaming JSON or building a sequential transform pipeline.48
- 14488Suno AI Masteryfrankxai/claude-skills-libraryExpert prompt engineering and music generation with Suno AI v4.5+ for professional-quality songs across all genres. Use when writing Suno prompts, designing song structure/styles, or producing commercial-quality AI music.48
- 14489Suno Prompt Architectfrankxai/claude-skills-libraryExpert Suno AI prompt engineering for professional music creation. Use this skill when creating Suno prompts for any AI-generated music that needs commercial quality.48
- 14490Swarm Advancedfrankxai/claude-skills-libraryAdvanced swarm-orchestration patterns for research, development, testing, and complex distributed workflows. Use when scaling beyond a few agents, designing dynamic swarm topologies, or coordinating large parallel agent workloads.48
- 14491Swarm Orchestrationfrankxai/claude-skills-libraryOrchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.48
- 14492Systematic Debugging0xranx/agentbriefStructured methodology for finding root causes before writing fixes43
- 14493Tailwindfrankxai/claude-skills-libraryTailwind CSS v4.2 browser-runtime patterns for HyperFrames compositions. Use when scaffolding or editing projects created with `hyperframes init --tailwind`, writing Tailwind utility classes in composition HTML, adding CSS-first Tailwind v4 theme tokens, debugging v3 vs v4 syntax, or deciding when to compile Tailwind to CSS instead of using the browser runtime.48
- 14494Tailwindcssfrankxai/claude-skills-libraryTailwind CSS v4 utility-first styling patterns including responsive design, dark mode, and custom configuration. Use when styling with Tailwind, adding utility classes, configuring Tailwind, setting up dark mode, or customizing the theme.48
- 14495TDD0xranx/agentbriefRed-green-refactor cycle for test-driven development43
- 14496Threefrankxai/claude-skills-libraryThree.js and WebGL adapter patterns for HyperFrames. Use when creating deterministic Three.js scenes, WebGL canvas layers, AnimationMixer timelines, camera motion, shader-driven visuals, or canvas renders that respond to HyperFrames hf-seek events.48