AI Ml AI Skills

MLX Swift - High-performance ML framework for Apple Silicon with lazy evaluation, automatic differentiation, and unified memory

Writing screenplays in the style of Ozu Yasujiro and Noda Kogo (小津安二郎・野田高梧) — distilled from six complete screenplays (晚春 Late Spring, 麦秋 Early Summer, 东京物语 Tokyo Story, 浮草 Floating Weeds, 秋日和 Late…

Unified CloudBase execution guide for all-in-one skill installs. Use this first for CloudBase app tasks, especially existing apps with TODOs, fixed pages, or active handlers. Routes PostgreSQL /…

Launch Android applications by package name. Open any installed app programmatically.

赛题一每日首轮攻击序列 — 被 injection-cycle 在每日首次触发时读取

Data pipelines, feature stores, and embedding generation for AI/ML systems. Use when building RAG pipelines, ML feature serving, or data transformations. Covers feature stores (Feast, Tecton),…

Use the ax CLI instead of curl + throwaway parsing scripts whenever you fetch a URL, explore an unknown web page, or extract structured data from HTML. Trigger whenever you are about to write an…

Builds AI-native products using Dan Shipper's 5-product playbook and Brandon Chu's AI product frameworks. Use when implementing prompt engineering, creating AI-native UX, scaling AI products, or…

Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration

操作阿布应用内置的可见浏览器：打开网页、点击、填写、截图和提取数据。用户要求在阿布内预览或操作网页时使用；无需安装浏览器扩展。

Provides workflows to write, debug, and optimize prompts for LLMs, including few-shot example selection, chain-of-thought structuring, system prompt design, and template composition. Use when the user…

Generate and maintain BPMN 2.0 diagrams linked to Gherkin scenarios

AI SDK-based image generation using official OpenAI and Google APIs. Supports text-to-image, reference images, aspect ratios, and quality presets.

使用 agentao-kanban 看板进行任务管理（拆任务 / 状态流转 / 后台服务 / 看产物）。 本技能负责：① 初始化 .kanban/ 项目 ② 把需求拆成原子卡片入板 ③ 推动状态流转 INBOX → READY → DOING → REVIEW → DONE ④ 启停 daemon 与 Web UI ⑤ 察看卡片状态与产物。 触发关键词（中/英）：看板 / kanban /…

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus)…

Accessibility testing toolkit using Selenium WebDriver 4+ with Java 21+ and axe-core engine. Use when asked to validate WCAG 2.2 AA compliance, scan pages or components for a11y violations, test…

Create REST/GraphQL API endpoint with validation, error handling, and tests. Auto-invoke when user says "add endpoint", "create API", "new route", or "add route".

AI voice assistants with custom instructions, knowledge bases, and tool integrations.

Implement API Platform filters - v4 Parameters API (QueryParameter) and legacy #[ApiFilter] - for search, date, range, boolean, and custom filtering

Master Anthropic's prompt engineering techniques to generate new prompts or improve existing ones using best practices for Claude AI models.

Web search without an API key using DuckDuckGo Lite via web_fetch. Use as a fallback when web_search fails with missing_brave_api_key error, or whenever you need to search the web and no search API is…

Use when working with Payload projects (payload.config.ts, collections, fields, hooks, access control, Payload API). Use when debugging validation errors, security issues, relationship queries,…

Architecture Decision Records (ADRs) — opt-in convention for documenting significant, hard-to-reverse architectural decisions using the Nygard template.

Parse and analyze CSV files with data validation

When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this…

Living Architecture Map — auto-generate Mermaid diagrams of your codebase. Use when user wants to visualize architecture, understand code structure, generate diagrams, or document system design.

Creates and improves portable Agent Skills with a validator, routing scenarios, and evidence-based keep, cut, merge, or retire decisions. Use when asked to "write a skill", "update all skills", "audit…

Data fetching with TanStack Query, loading states, and error handling

Build chat on Android with the headless CometChat Chat SDK v5 and your OWN UI — init/login ordering, the method map, request-builder pagination, listener lifecycle, and a production-ready app surface…

Managing design tokens and system context for LLM-driven UI development. Covers loading, persisting, and optimizing design decisions within context windows.

Use when building a web frontend with Deno — running React, Vite, Astro, SvelteKit, Next.js, Nuxt or other npm frameworks under Deno, or working with Fresh, Deno's own island-architecture framework.…

Team composition knowledge for Claude Code Agent Teams - when to suggest teams, optimal sizing, spawn prompt patterns

Deep expertise on LTX-2 video pipelines, Flux 2 image/inpainting pipelines, and memory coordination on unified Apple Silicon hardware. Use this for debugging GPU memory issues (OOM), modifying tensor…

Configures and hardens MCP servers for Claude Code and Codex agents. Use when connecting databases, APIs, files, or SaaS via MCP, or building custom servers.

Use when implementing reduced motion alternatives, vestibular-safe animations, WCAG compliance, or designing for users with motion sensitivity.

Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common…

Self-evolving AI agent system with 26 tools, three-layer memory, MCP plugins, and 24/7 self-repair in pure Python.

Implementing production frontend code for React/Vue/Svelte: hooks design, state management, Server Components, form handling, data fetching. Converts Forge prototypes to production quality.

Build ServiceNow Agent Workspace configurations — workspaces, lists, forms, contextual side panels, Agent Assist similar-record finders, and workspace-specific UI actions on sys_aw_* tables.

Copilot agent that assists with machine learning model development, training, evaluation, deployment, and MLOps Trigger terms: machine learning, ML, AI, model training, MLOps, model deployment,…

Guide to migrating an existing Capacitor iOS app from CocoaPods to Swift Package Manager (SPM). Use this skill when users want Capacitor 8-style SPM projects, need to run or recover from…

Arco Design React UI component library reference (@arco-design/web-react). Use this skill whenever the user asks to build a page, create a UI, write frontend code, develop a web application, design a…

Design AI agent responsibilities, tools, memory, orchestration, and evaluation when defining an agent architecture or system contract.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Convenciones de codificación base entre proyectos para nomenclatura, legibilidad, inmutabilidad y revisión de calidad de código. Usar skills de frontend o backend para patrones específicos de…

Integrate Firecrawl `/scrape` into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer…

Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger:…

Checks requirements.txt, pyproject.toml, and package.json dependency manifests for surface-level direct-dependency footguns: standard-library shadowing pins, abandoned backports, unpinned…

Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /caveman-stats.

Use this when fulfilling claude-mem observer jobs on Grok Bot: reply only skip_summary or one full observation XML, never prose.