Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Design principles for building polished, native-feeling SwiftUI apps and widgets. Use this skill when creating or modifying SwiftUI views, iOS widgets (WidgetKit), or any native Apple UI. Ensures proper spacing, typography, colors, and widget implementations that look and feel like quality apps rather than AI-generated slop.
Integrate and optimize Core ML models in iOS apps for on-device machine learning inference. Covers model loading (.mlmodelc, .mlpackage), predictions with auto-generated classes and MLFeatureProvider, compute unit configuration (CPU, GPU, Neural Engine), MLTensor, VNCoreMLRequest, MLComputePlan, multi-model pipelines, and deployment strategies. Use when loading Core ML models, making predictions, configuring compute units, or profiling model performance.
Generate engaging, localized App Store release notes (What's New) from git log, bullet points, or free text using canonical metadata under `./metadata`. Optionally pairs with promotional text updates.
Generate images, videos, and audio with fal.ai serverless AI. Use when building AI image generation, video generation, image editing, or real-time AI features. Triggers on fal.ai, fal, AI image generation, Flux, SDXL, real-time AI, serverless AI.
Integrate with Figma API for design automation and code generation. Use when extracting design tokens, generating React/CSS code from Figma components, syncing design systems, building Figma plugins, or automating design-to-code workflows. Triggers on Figma API, design tokens, Figma plugin, design-to-code, Figma export, Figma component, Dev Mode.
Declarative animation patterns using flutter_animate v4.5.x with composable effects (fade, scale, slide, shimmer, shake, blur), GLSL fragment shaders, and scroll-synchronized animations. Use this skill for adding UI animations and transitions, building staggered or sequenced effects, creating custom animation effects, fixing animation jank or performance issues, implementing shimmer loading states, or adding scroll-driven animations. Supports delays, curves, adaptive effects, and easy extension method chaining (.animate()).
Generative UI (GenUI) for Flutter using AI models like Google Gemini, Anthropic Claude, or OpenAI via the genui package. Use this skill when building dynamic AI-driven interfaces, conversational UI flows, server-rendered screen layouts, LLM-powered dashboards, chat-based UI generation, or implementing prompt-to-UI systems. Supports AI-generated widgets, reactive data binding, ContentGenerator integration, and A2uiMessageProcessor for real-time UI updates from AI responses. Ideal for apps where UI structure is determined by AI/LLM output rather than hardcoded layouts.
Generates immutable Dart data classes, sealed union types, and deep copyWith using Freezed (v3.2.x) with optional json_serializable integration. Use when creating DTOs, API response models, app state classes, or any model requiring immutability, pattern matching, or JSON serialization. Activates on: @freezed annotation, freezed_annotation import, immutable data class request, copyWith deep nesting, union/sealed types for loading/data/error states, generic response wrappers, or build_runner code generation for models.
>-
> Write personalized cold emails that get replies. 3-5 sentences. One CTA. No fluff.
> Generate cron job configurations for common automation patterns. Your scheduling assistant.
> Generate a structured daily business briefing from any data sources in under 60 seconds.
> Generate a professional service proposal in 60 seconds from client name, industry, and pain points.
AI image, video, and music generation. Flux, Veo 3.1, Suno V5.
Generates REST API documentation from route definitions.
Generate CSS and JS animation presets for common UI patterns. Includes entrance, exit, emphasis, and transition animations with correct easing curves.
Generate complete color scales (50-950) from a single base color using perceptual color science (OKLCH). Outputs CSS custom properties.
Extract React component props, defaults, and types from TypeScript files. Generate markdown documentation automatically.
Generate structured design briefs from natural language prompts. Outputs problem statement, constraints, success criteria, and scope definition.
Structure feedback using SBI framework (Situation-Behavior-Impact). Converts observations into professional feedback.
Combine individual SVG icon files into an optimized SVG sprite sheet with symbol references.
Generate Open Graph (og:image) social sharing images with customizable templates using Playwright. Supports title, description, brand colors, and logo.
Generate personal changelogs of what you shipped, learned, and connected with. Weekly and monthly.
Convert markdown to Slack mrkdwn format. Generate formatted announcements, status updates, and standup messages.
Generate social media graphics (Instagram, Twitter, LinkedIn) from templates using Playwright. Brand-configurable.
Generate daily standup updates from git log or manual input. Formats as Yesterday/Today/Blockers.
Compile weekly summaries from git commits. Groups by date, shows stats, ready for Slack or email.
Generate a context-aware, production-grade design system from the SDL blueprint. Produces design tokens, typography, palette, motion language, and component inventory — grounded in the product domain, audience, and architecture. Use this skill when generating or refining the SDL design section, scaffolding frontend projects, or when the user asks about visual direction.
A structured workflow for creating comprehensive character reference sheets that maintain visual consistency across AI-generated images and video clips. The character sheet locks every visual attribut
mlops-tabular
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
Generate the complete Vercel-deployable Astro project for a vision board builder lead magnet, including builder UI, reveal page with Glif-generated graphics, social sharing, email automation, and anal
Use Jujutsu (jj) for version control instead of git. Always check current revision before making changes — if the task semantically differs from the current revision's description, create a new revision first.
Use when you need copy-paste DOT templates for common diagram types — start from a working pattern rather than blank canvas
Scaffold a complete, production-ready Azure project from scratch for ANY use case: RAG chatbots, multi-agent systems, API backends, data pipelines, Azure Functions, full-stack web apps, ML training/inference, or event-driven microservices. USE FOR: gathering requirements through adaptive questioning, generating complete project folder structures with all source files, Azure Bicep infrastructure, azure.yaml for azd-up deployment, Docker configuration, CI/CD workflows, README with architecture diagrams, and Responsible AI documentation. Produces fully deployable Azure projects targeting Azure Container Apps, Azure AI Foundry, Azure Functions, or Azure ML. DO NOT USE FOR: modifying existing projects, deploying to Azure (use azure-deploy skill), managing Azure resources (use azure-prepare skill).
>
_An overview of the current repository and its related projects, generated by [AgentPrimer](https://github.com/deanthecoder/AgentPrimer)._
This project scaffolds API layers (service, biz, data) from OpenAPI descriptions. When working under the repository, follow the
This SDK is generated by [Fern](https://buildwithfern.com/). Most files under `src/main/java/com/deepgram/` are auto-generated and should not be edited directly. Some files are hand-written or carry m
<!-- AUTO-GENERATED by add_openclaw_agent.sh (codex shim) -->
**Generated:** 2026-02-12 | **Commit:** 4a2d0ba
Add Transloadit Smart CDN URL signing to a Next.js App Router project (server-side signing route + optional client demo page).
Add Uppy Dashboard + Transloadit uploads to a Next.js (App Router) app, with server-side signature generation and optional /s3/store export.
One-off image generation (prompt -> image file) using Transloadit via the `transloadit` CLI. Prefer `image generate` for text-only and input-guided generation, and use `--output` when you need a deterministic path.
Scan project to auto-generate .worktree.json for worktree port management
当用户处于 exploring 阶段（CONTEXT 当前阶段含'探索方向'）且发出具体请求时使用：询问推荐方向、要求对比方向、问某个方向适不适合、问某个方向是做什么的。触发条件：CONTEXT 显示'探索方向' + 用户消息含方向/推荐/对比/适合/介绍等意图。边界：纯问候走 coach-greeting；完全无方向走 coach-direction-scaffold；A vs B 纠结走 coach-decision-socratic。
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or idea. Triggers on '解剖概念', '概念解剖', 'explain concept', 'learn concept', '/ljg-learn'. Produces markdown output.
Spawn child agents with isolated storage and typed RPC using subAgent(), abortSubAgent(), and deleteSubAgent().
Instrument HuggingFace SmolAgents and send traces to OpenObserve via OpenTelemetry.
Create a SOLIDWORKS (CAD) desktop add-in using the SOLIDWORKS API SDK templates or by implementing ISwAddin/SwAddin manually; includes COM/registry registration, ConnectToSW/DisconnectFromSW lifecycle, CommandManager UI, callbacks, icons, and toolbar considerations.