发现 Skills

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill covers campaign strategy, ad creation, audience targeting, and optimization.

Build accessible UI primitives with Radix UI. Use when creating accessible dropdowns, dialogs, popovers, tabs, tooltips, or building a design system with unstyled, composable components.

Export and download Telegram chats, media, and channel content. Use when a user asks to export Telegram chat history, download media from Telegram channels or groups, archive Telegram conversations, backup Telegram messages, extract images or videos from Telegram, bulk download from Telegram channels, scrape Telegram content, or migrate Telegram data. Covers Telegram Desktop export, Telethon-based scripting, and TDLib approaches.

Generate unit, integration, and end-to-end tests for existing code. Use when a user asks to write tests, add test coverage, create unit tests, generate integration tests, build e2e tests, improve code coverage, write specs, or add testing to a project. Supports Jest, Vitest, Pytest, Playwright, React Testing Library, and Cypress. Analyzes code to produce meaningful assertions, edge cases, and mock setups.

Shared OptimizeSpec self-improvement references and templates. Use only as a supporting skill when another OptimizeSpec skill needs workflow, ASI, scorer, runner, or runtime-specific reference material.

Deep-dive explanation of how a specific file, feature, or data flow works. Triggers: 'explain', 'how does X work', 'walk me through', 'what does this do'.

Self-hosted Firecrawl deployment, troubleshooting, and best practices. TRIGGERS - firecrawl, self-hosted scraping, web scrape, scraper wrapper, littleblack, ZeroTier scraping.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been created, or you can generate a new theme on the fly.

A set of rules for creating the Skill assignment table (agent -> skills). Referenced by the skill-assigner when updating the mapping.

Diseña muebles a medida y genera planos técnicos HTML interactivos con despiece, BOM y lista de cortes. Usa cuando el usuario diga "diseñar mueble", "plano mueble", "bajo mesada", "placard", "biblioteca", "rack TV", "vanitory", "mueble a medida", "despiece", "mesa", "silla", "banco", "estantería", "mueble de cocina", "escritorio", "mesa ratona", o quiera calcular materiales/cortes para un mueble.

Prefer `skillhub` for skill discovery/install/update, then fallback to `clawhub` when unavailable or no match. Use when users ask about skills, 插件, or capability extension.

A skill that deploys a project-management flow (long-term memory + stacked Threads) into an arbitrary repository. By default it stores project long-term memory (CLAUDE.md) and Threads (OBJECTIVE.md→OUTPUT.md) under `.claude/my-projects/<slug>/`, but it can be customized to places like `.agents/my-projects/` according to runner/repo policies. Triggers include: “resume <slug>”, “continue”, “start project”, “create a new thread”, “write OUTPUT”, “pbcopy”, “close project”, “I want to put this exchange under project management”, “join project ○○”, “create an In Progress PJ from a PR/Issue”, “migrate to pj-flow”, “fix pj-flow behavior”, and “pjflow”. Compatible with both Claude Code and Codex Agent Skill environments.

Clean Code principles adapted for C#/.NET including naming, variables, functions, SOLID, error handling, and async patterns. Use when: (1) reviewing C# code, (2) refactoring for clarity, (3) writing new code, (4) code review feedback.

Expert guide for explaining Riftbound TCG rules using indexed reference documents. Use when answering questions about game mechanics, card interactions, combat, abilities, or tournament rules.

x402 protocol v2 for internet-native payments. Use when building x402 servers, clients, facilitators, or integrating x402 payment flows. Triggers: x402, payment required, 402, paywall, micropayment, EIP-3009, payment protocol, facilitator, PaymentPayload, PaymentRequirements.

Generate a project-specific DESIGN_SYSTEM.md that enforces consistent UI/UX across SPAs, traditional server-rendered sites, and hybrid systems. Includes tokens, component rules, accessibility gates, and production asset/manifest guidance.

Generate and edit images using Google Gemini (NanoBanana). Use when asked to generate images, create artwork, illustrations, concept art, edit images, perform style transfer, produce storyboards, design infographics, or handle any visual-creation task.

Generate architecture overview documents from codebase analysis. Extract precise code structure using tree-sitter-analyzer. Use when documenting project structure, creating architecture diagrams, or when referring to architecture overview, project structure, architecture, or system diagrams.

Creates, analyzes, updates, and improves Claude Code hooks including configuration, scripts, and security validation. Use when user asks how hooks work, explaining hook concepts, understanding hook types and event lifecycle, describing hook configuration, creating new hooks, analyzing existing hooks for improvements, validating hook security, debugging hook activation, updating hook configurations, or when user mentions "hook", "PreToolUse", "PostToolUse", "SessionStart", or other hook event types. Handles both command hooks and prompt-based hooks across all 9 event types.

Analyzes and explains Azure API Management architecture decisions for enterprise API marketplace implementations using VNet Internal mode, Front Door, hybrid authentication, and multi-environment strategies. Use when discussing APIM component selection, network topology, cost optimization, or comparing alternatives like workspaces vs instances, VNet Internal vs External mode, or Front Door vs Application Gateway.

REST API design best practices. Use when designing APIs, choosing status codes, or creating endpoints.

Reviews code for bugs, style, and best practices. Use when reviewing PRs or checking code quality.

Environment configuration and secrets management. Use when setting up .env files, managing secrets, or configuring environments.