AI Skills Hub - Browse 180,000+ Agent Skills

心跳技能 - 定期检查 HEARTBEAT.md 并执行任务。

Review recent edits and update all documentation including architecture docs, API specs, and edit history. Creates missing docs for new implementations.

Track your Solana wallet balances and transactions in real-time. Use when the user wants to monitor SOL, SPL tokens, or DeFi positions.

Provides sceneFromJSX: Converts React JSX to Weave SceneNode. Called when users write scenes using React or troubleshoot JSX conversion issues.

Provides Weave DevTools runtime bridging (attachWeaveDevtools, scene mirror, hook protocol). Called when users have questions about extension integration, instance discovery, or event protocols.

Provides OffscreenCanvas + Worker adaptation and message protocol. Called when users have questions about worker rendering, message communication, or main thread/worker consistency.

Provides Worker-side rendering adaptation and worker entry point exports. Called when users have questions about worker rendering output, message protocols, or image generation pipelines.

Provides core editor logic (registry, scene/JSX conversion, etc.). Called when users extend editor capabilities, handle import/export, or change node schemas.

Read and summarize content from URLs.

Search Wikipedia for encyclopedic information.

Perform mathematical calculations.

Get the current date and time.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

SEO fundamentals, E-E-A-T, Core Web Vitals, and Google algorithm principles.

Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF documents or when the user mentions PDFs, forms, or document extraction.

Run pytest with coverage and baseline tracking. Use when the user invokes /tests.

Backend development specialist covering API design, database integration, microservices architecture, and modern backend patterns.

Enterprise code quality orchestrator with TRUST 5 validation, proactive analysis, and automated best practices enforcement

Comprehensive development workflow specialist combining DDD testing, debugging, performance optimization, code review, PR review, and quality assurance into unified development workflows

Enterprise context and session management with token budget optimization and state persistence

多大脑协作技能 - 将复杂任务分解并分配给多个AI模型并行处理，最后汇总结果

Fix a GitHub issue

BNB Chain knowledge AI agent with autonomous posting capabilities

Perform bi-directional sync for memo and global-kb repos and update release artifacts. Use when the user requests memory sync or after releases.

Classifies a user request into task types (feature, modification, bugfix, refactor) and extracts intent keywords. Use at the start of PM analysis.

Build frontend pages, reusable components, layouts, and apply styling for responsive and modern UI.

Explore the resources at your disposal as needed to discover the information needed complete a task. Use when the information needed to complete a task is not already known.

Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory

Create a draft pull request for the current branch

Comprehensive GitHub code review with AI-powered swarm coordination - Swarm-based review orchestration - Intelligent comment generation - Quality gate enforcement

Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration - github

Expert for ASM (Agent Skill Manager). Helps with initialization, dependencies, and code modifications.

Use interfaces and dependency injection to decouple code; bind implementations in the container

Evolve APIs safely using versioned DTOs/transformers, deprecations, and compatibility tests

Expert code reviewer with deep knowledge of software engineering best practices, design patterns, and code quality standards. Use this skill when reviewing code changes, pull requests, or conducting code quality assessments.

QA engineer with expertise in software testing methodologies, test design, and quality assurance practices. Use this skill when planning tests, writing test cases, or improving test coverage and quality.

Creates work plan documents with trackable execution plans. Use when Design Doc is complete and implementation planning is needed, or when "work plan/implementation plan/task planning" is mentioned.

🌐 **Casino URL:** https://casino.agentbenny.ai 🦞 **Part of:** [AgentBenny AI Swarm](https://www.agentbenny.ai) 🪙 **Token:** [$ABAI on Base](https://dexscreener.com/base/0x7ee37a91621d09cc5298f0b184037f19c0f6681a1481fae587819550ff9c4b50)

Next.js App Router principles. Server Components, data fetching, routing patterns.

Estelle 일반 모드. 자유로운 대화와 코딩 작업

Interview me about a plan. Triggers on 'interview me'.

Manage Google Docs - create documents, read/write content, formatting, export

Manage Google Drive - upload, download, share files, create folders

This section defines the layout, structure, gestures, and interaction behavior of the Daily Recommendation page exactly as described.

本地搜索技能，无需外部API key，使用DuckDuckGo实现。

Ultimate AI agent memory system. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Works with Claude, Cursor, GPT, OpenClaw agents.

Produce <retrospective> artifacts (postmortems, playbooks) capturing lessons, root causes, and guardrails for future work.

Retrieve up-to-date, version-specific documentation and code examples from libraries using Context7 MCP. Use when generating code, answering API questions, or needing current library documentation. Automatically invoked for code generation tasks involving external libraries.

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

Used to create a new skill. Used when a user wants to create a new skill

Complete implementation of Cloudflare R2 object storage with Convex backend and Next.js frontend. Covers bucket setup, CDN configuration, file upload/download, and both public and private access patterns. Use when adding cloud storage capabilities to a Convex + Next.js application for images, videos, documents, or any file type.

Implements complete voice conversation features using OpenAI Whisper (STT), GPT models, and TTS with Vercel AI SDK for Expo + Convex apps. Use when adding voice recording, transcription, AI responses, or text-to-speech to any React Native application.

Produce an implementation brief derived from the target idea prompt.

Outfit recommendations for AI agents. Help your human look their best.

Healthy Diary 앱에 통합될 AI 건강 어시스턴트 챗봇의 구현 가이드입니다. 사용자의 식단, 운동, 건강 관련 질문에 답하고 개인화된 조언을 제공합니다.

对代码变更进行全面审查，检查质量、安全性和性能问题。

Patterns for collaboration between humans, between AI, and between humans and AI together. Use when navigating how to work together well, designing teams, building multi-agent systems, resolving coordination challenges, or wanting to collaborate with more care and intention. Helps recognize patterns that allow collective work to thrive.

Consult Oracle for architecture tradeoffs, deep debugging, and high-risk decisions

Use Researcher for evidence from codebase/docs/web with concrete references

When to use: - You need a complete A/B test plan.

When to use: - You need a DS-focused code or PR review.

When to use: - You need a data quality audit for pipelines or datasets.

When to use: - You need a structured trade memo.

When to use: - You need a concise options or volatility note.

Use this skill for requests related to LangGraph in order to fetch relevant documentation to provide accurate, up-to-date guidance.

백엔드 코드를 리팩토링합니다. 라우터 분리, 서비스 레이어 구성이 필요할 때 사용하세요.

Orchestrates a dual-AI engineering loop where Antigravity plans and implements, while Codex validates and reviews, with continuous feedback for optimal code quality

A methodology for iterative development that compounds knowledge across sessions.

Standard procedure for committing and pushing changes.

Removes common patterns from AI generated code that wouldn't exist with human created code

Initialize session, load memory & capabilities.

Prefer const over let and readonly properties where possible Use when enforcing code quality standards. Quality category skill.

Keep lines under 80-120 characters depending on team standards Use when maintaining consistent code style. Style category skill.

Test boundary conditions: empty arrays, null/undefined, zero, negative numbers, maximum values Use when writing and organizing tests. Testing category skill.

Encode output appropriately for the context (HTML, JavaScript, CSS, URL) Use when implementing security best practices. Security category skill.

Use HTTPS for all endpoints, including internal services Use when implementing security best practices. Security category skill.

Each microservice should own a specific business capability end-to-end (including its data) Use when designing system architecture. Architecture category skill.

Always use parameterized queries or prepared statements Use when implementing security best practices. Security category skill.

For major decisions, create ADRs documenting: the context and problem statement, decision drivers... Use when documenting code and APIs. Documentation category skill.

Order imports by: built-in modules, external packages, internal modules, relative imports Use when maintaining consistent code style. Style category skill.

Regularly audit dependencies for known vulnerabilities (npm audit, Snyk, Dependabot) Use when implementing security best practices. Security category skill.

Tests must not depend on execution order or state from other tests Use when writing and organizing tests. Testing category skill.

Write clear, correct code first Use when optimizing code performance. Performance category skill.

Use events to decouple producers from consumers Use when designing system architecture. Architecture category skill.

Separate pure computation from side effects (I/O, mutations, API calls) Use when enforcing code quality standards. Quality category skill.

When implementing complex algorithms, mathematical formulas, or intricate business rules, add com... Use when documenting code and APIs. Documentation category skill.

Use descriptive names for functions, variables, and classes that explain their purpose Use when documenting code and APIs. Documentation category skill.

Select only the columns you need—avoid SELECT * Use when optimizing code performance. Performance category skill.

Never commit secrets (API keys, passwords, tokens) to version control Use when implementing security best practices. Security category skill.

Validate all user inputs against expected formats, lengths, and character sets Use when implementing security best practices. Security category skill.

Follow Keep a Changelog format with sections: Added, Changed, Deprecated, Removed, Fixed, Security Use when documenting code and APIs. Documentation category skill.

Use established authentication libraries rather than implementing from scratch Use when implementing security best practices. Security category skill.

Use Promise Use when optimizing code performance. Performance category skill.

Good comments explain: business rules ("Tax is calculated differently for EU customers due to VAT... Use when documenting code and APIs. Documentation category skill.

Work with Git repositories from the command line.

Execute prompts with integrated teaming checks, agent routing, and post-run integration verification

Implement secure authentication systems including signup, signin, password hashing, JWT tokens, and Better Auth integration.

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Continuously improve the creation and maintenance of Databricks Assistant Instructions by recording and applying lessons learned. This skill is always on and serves as a meta-skill for instruction development.

Ser el **experto contable peruano** que valida TODA operación contable contra la normativa vigente, sugiere mejoras basadas en la arquitectura real, y anticipa problemas tributarios con referencias auditables.