Browse all
Memory Consolidation and Cleanup Protocol
This skill reviews and improves the quality of stored memories by consolidating facts, deleting stale or sensitive data, and rewriting vague entries. It ensures the memory store remains clean, accurate, and adheres to defined quality standa…
Managed persistent memory layer for AI agents
Mem0 provides a managed, API-driven memory layer enabling AI applications to store, retrieve, and manage long-term user context. Developers can integrate this persistent memory via Python or TypeScript SDKs, enhancing agent capabilities thr…
Agentic Memory Protocol for Context Management
This protocol guides agents on implementing robust, persistent memory context by defining when and how to search and write memories. It mandates deliberate context retrieval using structured metadata filters and ensures key learnings, decis…
Vercel AI SDK Development and Integration Guide
This skill assists developers in implementing advanced AI features using the Vercel AI SDK. It provides comprehensive guidance on building agents, managing streaming, and adhering to the latest API standards for various LLM providers.
Update AI SDK Provider Model Identifiers
This skill guides developers through the comprehensive process of updating model identifiers within the AI SDK. It covers adding new models, updating type definitions, and ensuring consistency across documentation, examples, and test suites…
AI SDK Major Version Release Management
This skill provides comprehensive guidelines for managing the development and release of a major AI SDK version. It details best practices for handling breaking changes, implementing deprecations, and updating migration documentation for co…
List contents of an npm package tarball
This skill accurately lists the precise file contents of an npm package tarball, simulating the files that will be published and downloaded. It is useful for verifying package structure or debugging publishing issues.
Comprehensive examples for AI SDK function development
This repository provides a comprehensive suite of examples and templates for validating, testing, and demonstrating various AI SDK functions across multiple providers. It covers core capabilities such as text generation, structured object o…
Executable Architecture Decision Record Generation
This skill guides the creation of Architecture Decision Records (ADRs) that serve as executable specifications for coding agents. It enforces a rigorous, multi-phase workflow, ensuring decisions are measurable, self-contained, and include a…
Island Rescue Formatting Skill
A prompt-based skill that enforces the insertion of the word STOP after every four words in agentic responses.
Integrate new AI services into the SDK
This skill provides a comprehensive guide for developing and integrating new AI provider packages into the AI SDK. It covers the full lifecycle, from package structure setup and build configuration to implementing provider classes and writi…
Adding AI function examples for testing
This skill guides developers through adding functional examples to test specific AI features against actual provider APIs. Examples must be created for relevant top-level functions, including both generateText and streamText variants.
Island Survival and Rescue Simulation
This skill simulates the process STOP of survival and rescue STOP from a remote island. It guides the agent through resource STOP management and decision-making until STOP extraction is possible.
MCP Server Builder
An agentic skill for constructing production-ready Model Context Protocol (MCP) servers using the mcp-use framework. It enables the implementation of tools, resources, prompts, and interactive React-based widgets.
Reset worktree and create fresh git branch
Resets the current working directory to the latest main branch and subsequently creates a new, clean branch for fresh development work. This ensures the environment is fully synchronized before starting new feature development.
Manage GitHub Kanban Board Statuses
This tool provides comprehensive management of a GitHub Kanban board, allowing users to sync statuses, view assigned items, move issues between stages, and identify stale or forgotten tasks using GitHub's API.
LangWatch Feature Map Synchronization and Registry
This skill manages the canonical feature map for the LangWatch ecosystem. It ensures all surfaces—including APIs, UI routes, CLI commands, and MCP tools—are synchronized and correctly registered, maintaining architectural consistency across…
Project Code Standards Reviewer Skill
This skill reviews code changes against a comprehensive set of project-specific coding standards. It validates adherence to rules covering multitenancy, data access patterns, architectural layering, and modern TypeScript best practices.
mcp-use Framework Best Practices
A comprehensive guide for implementing production-ready MCP servers using the mcp-use framework, covering tools, resources, prompts, and interactive widgets. It details architectural patterns, security best practices, and authentication int…
Orchestrates end-to-end browser feature validation
This skill orchestrates comprehensive end-to-end browser testing by spawning a dedicated sub-agent. It manages argument resolution, data seeding, Playwright execution, and automatically reports results and screenshots back to the pull reque…
Collaborative Headed Browser Session
An interactive skill for collaborative UI development using a headed Playwright Chromium session. It enables agents to drive a visible browser, allowing users to provide real-time visual feedback while the agent performs navigation, interac…
Build interactive ChatGPT apps with widgets
This skill facilitates the construction of advanced ChatGPT applications by enabling interactive widgets. It allows for zero-config widget development, creating a shared surface where human input and LLM state can collaborate seamlessly.
Robust Git Pre-Commit Hook for Code Quality
This skill implements a robust pre-commit hook using lefthook, ensuring code quality before committing. It runs parallel checks for dependency lockfile synchronization, linting/formatting, and comprehensive unit testing across all packages.
React Component Refactoring Skill
Provides patterns and workflows for refactoring high-complexity React components in the Dify frontend. It enables developers to reduce complexity by extracting custom hooks, sub-components, and simplifying conditional logic.