tavily-best-practices
Build production-ready Tavily integrations with best practices baked in. Reference documentation for developers using coding assistants (Claude Code, Cursor, etc.) to implement web search, content extraction, crawling, and research in agentic workflows, RAG systems, or autonomous agents.
audit-and-add-project-skills
Audits project skills in .agent/skills/ and Codex skills for Cursor compatibility, then helps add compatible skills to .cursor/skills/. Use when the user wants to migrate project skills to Cursor, check if skills work with Cursor, or add existing skills to Cursor.
search
Search the web using Tavily's LLM-optimized search API. Returns relevant results with content snippets, scores, and metadata. Use when you need to find web content on any topic without writing code.
audit
Perform a forensic logic audit of NinjaScript strategy files.
patch
Execute a surgical code patch based on a pre-defined plan.
extract
Extract content from specific URLs using Tavily's extraction API. Returns clean markdown/text from web pages. Use when you have specific URLs and need their content without writing code.
crawl
Crawl any website and save pages as local markdown files. Use when you need to download documentation, knowledge bases, or web content for offline access or analysis. No code required - just provide a URL.
servel
Self-hosted deployment platform specialist. Use when deploying applications, managing infrastructure, or working with Docker Swarm deployments. Enforces dogfooding policy - ALWAYS use servel commands instead of direct Docker operations. Triggers for deploy, infrastructure, postgres, redis, supabase, backup, restore, logs, exec, shell, container, docker, secrets, SSL, domains, dev mode, CI/CD, alerts, traefik, routing, server management, capacity, rebalance, registry, node management, access control, volumes, audit, bastion, tunnel, or port-forward.
apple-mail
Interact with Apple Mail on macOS. Use for reading, sending, searching, and managing emails.
spotify
Control Spotify on macOS. Use for playing music, controlling playback, and getting track information.
tonejs
Web Audio framework for creating interactive music in browsers. Use when building audio applications, synthesizers, musical instruments, effects processors, audio visualizations, DAWs, step sequencers, or any browser-based sound generation. Handles synthesis, scheduling, sample playback, effects, and audio routing.
latex-figure-table-layout
Professional LaTeX figure and table positioning. Handle float placement, subfigure/subtable layouts, side-by-side arrangements, and cross-column figures. Does NOT adjust sizes, widths, or scaling.
interactive-intro-writer
Interactive deep learning paper Introduction writing assistant. Helps users discover scientific narrative, innovation points, and contributions through multi-turn dialogue. Supports writing from scratch or polishing existing LaTeX files. Follows standard Introduction structure: Background → Problem → Existing Work → Limitations → Overall Approach → Method Overview → Three Contributions.
Feature-Based-Layered-Architecture
Feature-Based Layered Architecture for Next.js (App Router) with Supabase. Use when creating API routes, services, repositories, or components with TypeScript. Covers Handler/Service/Repository/Adapter layers, Zod validation, and feature module structure.
clerk-auth-expert
Expert in Clerk authentication for React Native/Expo apps. Handles user authentication, session management, protected routes, and integration with backend services.
ray
Expert in Apache Ray distributed computing. Use when converting Python code to Ray workloads, debugging Ray applications, optimizing Ray performance, or working with Ray Core, Ray Data, Ray Train, Ray Serve, or Ray Tune. Automatically fetches relevant documentation from Ray, HuggingFace, PyTorch, and other ML/distributed frameworks based on code context.
prompt-distiller
|
creative-insights-api
Calls the Motion creative insights api
python-testing-standards
Comprehensive Python testing best practices, pytest conventions, test structure patterns (AAA, Given-When-Then), fixture usage, mocking strategies, code coverage standards, and common anti-patterns. Essential reference for code reviews, test writing, and ensuring high-quality Python test suites with pytest, unittest.mock, and pytest-cov.
agent-skill-templates
Comprehensive templates, patterns, and best practices for creating Claude Code subagents and skills. Use when building new agents/skills or need reference examples for proper structure and formatting.
python-async-patterns
Comprehensive guide to Python async/await patterns, best practices, and anti-patterns. Covers asyncio fundamentals, coroutines, async context managers, task management, common libraries (aiohttp, aiofiles, asyncpg), framework integration (FastAPI, Django), performance considerations, and proper exception handling. Use when reviewing or writing asynchronous Python code.
fastapi-patterns
Comprehensive FastAPI best practices, patterns, and conventions for building production-ready Python web APIs. Covers application structure, async patterns, Pydantic models, dependency injection, database integration, authentication, error handling, testing, OpenAPI documentation, performance optimization, and common anti-patterns. Essential reference for FastAPI code reviews and development.
django-conventions
Comprehensive Django best practices covering project structure, models (field choices, Meta options, managers, QuerySets, migrations), views (CBVs vs FBVs, generic views), Django REST Framework (serializers, ViewSets, permissions), forms, templates, security (CSRF, XSS, SQL injection), performance (N+1 queries, select_related, prefetch_related, caching), testing, and common anti-patterns. Essential reference for Django code reviews and development.
python-type-hints-guide
Comprehensive reference guide for Python type hints, static type checking with mypy, modern type annotation patterns (PEP 484, 585, 604, 612, 613), and type hint best practices for Python 3.9+. Use during code reviews to ensure proper type annotation usage, evaluate mypy configuration, and identify type hint anti-patterns.
sdlc-repository-templates
Templates, standards, and structure requirements for generating SDLC approach learning repositories. Use when creating new methodology learning repositories, artifact documentation, or validating repository structure.
java-best-practices
Comprehensive Java development best practices covering SOLID principles, DRY, Clean Code, Java-specific patterns (Optional, immutability, streams, lambdas), exception handling, collections, concurrency, testing with JUnit 5 and Mockito, code organization, performance optimization, and common anti-patterns. Essential reference for uncle-duke-java agent during code reviews and architecture guidance.
spring-framework-patterns
Comprehensive Spring Framework and Spring Boot best practices including dependency injection patterns, bean lifecycle and scopes, REST API development, Spring Data JPA, service layer design, Spring Security, testing strategies, caching, AOP, async processing, error handling, and common anti-patterns. Essential reference for code reviews and Spring Boot application development.
ui-expert
Build, refine, or review web UI/UX with strong visual taste, interaction design, accessibility, and front-end implementation quality. Use whenever the user wants a page, component, layout, design system, dashboard, landing page, form, navigation, responsive behavior, styling pass, UX polish, accessibility improvement, motion pass, or asks to make a web interface look or feel better. Framework-independent: think in HTML, CSS, and JavaScript primitives first, then adapt to the stack at hand.
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
commit
Use when asked to create a git commit, split changes into commits, or write a commit message. Prefer small commits that are easy to review. Follow this repo's commit message pattern when clear from recent history or touched-path history; otherwise default to conventional commits. Never commit gitignored, ephemeral, generated, local-only, or secret files.
librarian
Use for code research that needs dependency internals, upstream implementation examples, or external prior art. Always delegate to a subagent that investigates with opensrc and web search, then return only distilled findings, versions, paths, and links.
fakturoid
Czech invoicing API integration for Fakturoid. Use when the user needs to create, manage, or retrieve invoices, contacts/subjects, or expenses from Fakturoid. Supports OAuth 2.0 authentication, invoice creation with Czech tax compliance (IČO, DIČ, VAT), PDF downloads, payment tracking, expense management, inventory, recurring invoices, webhooks, and invoice templates (generators). Triggers on mentions of Fakturoid, Czech invoicing, IČO/DIČ, or invoice management tasks.
intelligems-segment-analysis
Analyze which audience segments each active Intelligems experiment is winning in. Shows device type, visitor type, and traffic source breakdowns with confidence levels. Use when you want to see segment-level performance of A/B tests.
agency-digest-setup
Get daily A/B test updates in Slack for multiple brands. Use when you want morning summaries of all your Intelligems tests, need to monitor tests across multiple stores or clients, or want automated Slack notifications with key metrics like revenue per visitor, profit per visitor, and conversion rates. Perfect for agencies managing multiple brands.
test-health-check-setup
Get alerts in Slack when your A/B tests need attention. Use when you want daily health checks for your Intelligems tests, need to know when conversion drops or traffic is low, or want to monitor statistical significance progress. Sends one message per test with clear status indicators. Great for single-brand monitoring.
ant-design-guide
包含 Ant Design (Antd) 所有核心组件的官方文档索引及最佳实践。用于查询组件 API、Props 定义及最新特性。
pro-components-guide
包含 Ant Design Pro Components (ProComponents) 的组件列表、适用场景及官方文档链接。用于辅助代码生成和参数查询。
commit-safe
Skill for safe commits. Reviews changes before selective commits. Proposes file-specific commits for large changes, prevents use of git add -A.
auto-build
Skill for auto-detecting project type and executing builds. Suggests builds after code changes, proposes fixes for build errors. Supports Node.js, Rust, Python, Go, and Makefile projects.
worktree-manager
Skill for creating and managing Git worktrees. Proposes worktree creation for complex tasks or multi-file changes, guides merge and cleanup on task completion. Integrates with checkpoint-manager.
checkpoint-manager
Skill for tracking and managing task progress. Checks pending tasks at conversation start, proposes task creation for new requests, suggests completion reports when work is done. Integrates with checkpoint system.
sprint-coordinator
Coordinate sprint execution across planning, standups, release readiness, and delegated task batches. Use when Codex or Claude Code needs to turn goals into sprint milestones and tasks, summarize daily sprint status, compute a go or no-go release view from existing health signals, or prepare task-router style delegation payloads for parallel execution.
vision-scorer-mcp
Deterministic MCP-based visual compliance scoring for Kerala Rage assets with hard gates for token usage, wireframe alignment, manifest integrity, and hero composition quality.
storybook-scaffolder
Generates a Storybook story file (*.stories.tsx) with M3 design token
design-compliance-dashboard
Tracks and visualizes the progress of the design system migration. Generates compliance reports across Typography, Shape, Color, Motion, and Accessibility metrics to provide a clear path to the "Definition of Done."
wireframe-annotator
Generate annotated ASCII wireframes based on the "Annotated Wireframe
task-router-mcp
"Multi-agent task orchestration MCP server. Queue-based workflow where\
webapp-testing
Runs or writes Playwright tests for the 'careercopilot' webapp. Use when
task-delegator
Delegate tasks to specialized agents and coordinate multi-agent workflows
theme-factory
Internal placeholder skill for theme-factory.
Page 1490 of 1704 · 85187 results
