Development

Perplexity Sonar API development with search-augmented generation, real-time web search, citations, and OpenAI-compatible Chat Completions. Use for AI-powered applications requiring up-to-date information, research assistants, and grounded responses with sources.

WHEN: API documentation, JSDoc/TSDoc comments, Props documentation, Storybook story writingWHAT: Function/class/type JSDoc + React Props table + Markdown API docs + Storybook storiesWHEN NOT: README writing → readme-generator, Code explanation → code-reviewer

Expert on FLUI's three-tree architecture (View-Element-Render), widget composition, and Flutter-inspired patterns. Use when discussing views, elements, render objects, widget trees, or UI architecture.

Creer un nouveau flow d'automatisation de formulaire complet, incluant exploration du site web, implementation et tests. (project)

Xenium benchmarking 本地文档快照（全量 HTML）- 包含完整模块文档

Help user START tasks with activation support for ADHD. Use when user is stuck, overwhelmed, or asking what to do next. Auto-triggers on phrases like "I'm stuck", "can't get started", "overwhelmed", "what should I do", "next step", "where do I start", "jag fastnar", "kan inte börja", "vad ska jag göra", "nästa steg".

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.

Google python-genai SDK for Gemini 3 Flash, Gemini 3 Pro, and Gemini models. Use when building with Google's Gemini API, google-genai, implementing thinking/reasoning, structured outputs, function calling, image generation, or multimodal. Triggers on "gemini", "google ai", "genai".

Analyzes codebases to map architecture, dependencies, complexity metrics, and data flows for rapid onboarding. Use when exploring new repos, understanding project layout, analyzing dependencies, measuring code complexity, or preparing codebase documentation.

Comprehensive code review checklist covering readability, maintainability, performance, security, and best practices. Use when reviewing code or conducting quality checks.This skill provides systematic code review guidance:- Language-specific best practices (JavaScript, Python, Java, etc.)- Security checklist (OWASP Top 10)- Performance optimization points- Maintainability and readability checks- Automated review integration (Codex CLI MCP)Triggers: "code review", "review checklist", "quality check", "check code", "コードレビュー", "品質チェック", "レビュー観点"

Search the web using Brave Search API and fetch page content with HTML-to-markdown conversion. Use when user needs current information, online documentation, or specific URL content beyond knowledge cutoff.

Manage Kubernetes clusters with KubeKey: check installation, install KubeKey, create clusters, scale nodes, upgrade clusters, and view configurations. Use when working with Kubernetes cluster deployment, management, or when the user mentions KubeKey, kk, or Kubernetes cluster operations.

Manages React state with Jotai including atoms, derived atoms, async atoms, and utilities. Use when building React applications needing atomic state, bottom-up state management, or fine-grained updates.

AGGRESSIVELY use TOON v2.0 format for biggish regular data (≥5 items, ≥60% uniform). Auto-applies to tables, logs, events, transactions, analytics, API responses, database results. Supports 3 array types (inline, tabular, expanded), 3 delimiters (comma, tab, pipe), key folding for nested objects. Triggers on structured data, arrays, repeated patterns. Use TOON by default when tokens matter - RAG pipelines, tool calls, agents, benchmarks. Keywords "data", "array", "list", "table", "log", "transaction", "metric", "analytics", "API", "database", "query", "TOON".

Spawn and manage hierarchical AI sub-agents (Cursor, Codex, Gemini) in isolated git worktrees with explicit role prompts, structured task briefs, and verification checklists. Supports work vs research modes, await vs fire-and-forget runtime, and role-aware wrappers for cleaner delegation. Use when: (1) Delegate tasks to AI agents, (2) Parallel work across features, (3) Research tasks needing web search, (4) Code refactoring or implementation, (5) Documentation updates, (6) Testing agent orchestration systems. Triggers: spawn agent, delegate to agent, agent orchestration, multi-agent, sub-agent, agent work, agent research.

Automate F5 Distributed Cloud web console operations through browser automation using mcp__claude-in-chrome MCP tools. Handles multi-provider authentication (Azure SSO, Google, Okta, SAML, native username/password), detecting session expiry and navigating login flows. Warns when VPN is required. Use when creating HTTP/TCP load balancers, origin pools, WAF policies, deploying cloud sites (AWS/Azure/GCP), managing DNS zones, configuring service policies, or executing any F5 XC GUI-based tasks. Triggers on: F5 XC console, GUI automation, browser automation, login, SSO, authenticate, tenant management, visual configuration, Web App and API Protection, WAAP.

This skill provides comprehensive knowledge for Cloudflare Images, covering both the Images API (upload/storage) and Image Transformations (optimize any image). It should be used when uploading images to Cloudflare, resizing images, optimizing image delivery, implementing direct creator uploads, creating image variants, generating signed URLs for private images, transforming images via Workers, or encountering image upload/transformation errors.Use when: setting up Cloudflare Images storage, implementing user-uploaded images, creating responsive images, optimizing image formats (WebP/AVIF), resizing images via URL or Workers, debugging CORS errors with direct uploads, handling image transformation errors (9401-9413), implementing signed URLs, managing image variants, or building image CDNs.Keywords: cloudflare images, image upload cloudflare, imagedelivery.net, cloudflare image transformations, /cdn-cgi/image/, direct creator upload, image variants, cf.image workers, signed urls images, flexible variants,

Create an interactive educational MicroSim using the p5.js JavaScript library with distinct regions for drawing and interactive controls. Each MicroSim is a directory located in the /docs/sims folder. It has a main.html file that references the javascript code and the main.html can be referenced as an iframe from the index.md. The metadata.json contains Dublin core metadata about the MicroSim.

Systematic framework for contributing to open source projects. Guides through issue discovery, integrated analysis with code exploration, implementation, and PR creation. Use when starting OSS contributions, analyzing issues, or creating pull requests. Includes modular sub-skills for each contribution phase.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Codex needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.