Amazon Bedrock AgentCore Memory for persistent agent knowledge across sessions. Episodic memory for learning from interactions, short-term for session context. Use when building agents that remember user preferences, learn from conversations, or maintain context across sessions.

Amazon Bedrock AgentCore multi-agent orchestration with Agent-to-Agent (A2A) protocol. Supervisor-worker patterns, agent collaboration, and hierarchical delegation. Use when building multi-agent systems, orchestrating specialized agents, or implementing complex workflows.

Amazon Bedrock AgentCore Policy for defining agent boundaries using natural language and Cedar. Deterministic policy enforcement at the Gateway level. Use when setting agent guardrails, access control, tool permissions, or compliance rules.

Amazon Bedrock AgentCore platform for building, deploying, and operating production AI agents. Covers Runtime, Gateway, Browser, Code Interpreter, and Identity services. Use when building Bedrock agents, deploying AI agents to production, or integrating with AgentCore services.

Amazon Bedrock Agents for building autonomous AI agents with foundation model orchestration, action groups, knowledge bases, and session management. Use when creating AI agents, orchestrating multi-step workflows, integrating tools with LLMs, building conversational agents, implementing RAG patterns, managing agent sessions, deploying production agents, or connecting knowledge bases to agents.

Amazon Bedrock Automated Reasoning for mathematical verification of AI responses against formal policy rules with up to 99% accuracy. Use when validating healthcare protocols, financial compliance, legal regulations, insurance policies, or any domain requiring deterministic verification of AI-generated content.

Amazon Bedrock Prompt Management for creating, versioning, and managing prompt templates with variables, multi-variant A/B testing, and flow integration. Use when creating reusable prompt templates, managing prompt versions, implementing A/B testing for prompts, integrating prompts with Bedrock Flows, optimizing prompt engineering, or building production prompt catalogs.

AWS Bedrock foundation models for generative AI. Use when invoking foundation models, building AI applications, creating embeddings, configuring model access, or implementing RAG patterns.

Gather scattered ideas into organized GitHub issues. The bee collects pollen from every flower, checks if the hive already has it, and carefully deposits new work in the comb for later. Never edits code—only organizes the work ahead. Use when creating issues from TODOs or planning work.

Guidelines and best practices for building applications with [Beefree SDK](https://docs.beefree.io/beefree-sdk), including installation, authentication, configuration, customization, and template mana

Unified messaging via Beeper Desktop MCP. Search chats, send messages, manage conversations across all networks (iMessage, WhatsApp, Signal, Telegram, Discord, Slack, etc.)

Comprehensive discovery before starting any spec or major task. Searches Graphiti, recommends vibe/MCPs, surfaces patterns.

Start development session with diagnostics, context loading, and intelligent task menu

Begin the interactive Elixir/Phoenix tutorial with guided sections and pauses for understanding

Plaited behavioral programming patterns for event-driven coordination and symbolic reasoning. Use when implementing behavioral programs with behavioral()/useBehavioral, designing rule composition with bThread/bSync, orchestrating test runners or workflows, or building neuro-symbolic reasoning layers.

This skill should be used when the user asks to create a contact in Outlook from freeform text data (e.g., business cards, email signatures, addresses). It handles parsing contact information and creating properly structured Outlook contacts that sync to mobile devices.

Uses the mcp postgresql to read and write crm relevant data to the crm database:

This skill should be used when working with the CRM PostgreSQL database for sales, contacts, companies, and opportunities. Use this skill when the user asks to insert, update, query, or analyze data in the CRM database (may be called crm or db), or when SQL queries need to be created for company_site, person, sales_opportunity, or event tables. This skill provides comprehensive schema knowledge and PostgreSQL-specific SQL examples tailored to the CRM data model.

bel-crm-sql-rules

Download files stored in the CRM PostgreSQL database and save them to the filesystem in `_RESULTS_FROM_AGENT/`.

This skill should be used when inserting files (images, PDFs, Excel files, documents) into the CRM database and linking them to companies, people, events, or sales opportunities. The skill handles base64 encoding, hash calculation, MIME type detection, and SQL insertion automatically through a Python script.

This skill should be used when moving a single email message to the Archive folder in Microsoft 365 Mail. It provides a clean interface to move one specific email using its messageId without polluting the context window. Use this skill when processing bulk archive operations, moving spam emails, or any workflow requiring reliable one-email-at-a-time moves to Archive.

Open any file on disk using the operating system's default application for viewing.

View files stored in the CRM database by downloading them to disk and opening them in the default application. This is an orchestration skill that combines the download and open workflows.

Design religious and belief systems for fictional worlds. Use when creating pantheons, religious institutions, spiritual practices, or any belief structures that shape society and drive character motivation.

Provides custom React hooks patterns and best practices specific to Bellog. Triggers when creating custom hooks or implementing interactive features.

Provides guidance on React Server Components vs Client Components decision-making in Bellog. Triggers when creating new components.

Provides file organization and naming conventions for the Bellog project. Triggers when creating new files or reorganizing code.

Frappe Bench CLI command reference for site management, app management, development, and production operations. Use when running bench commands, managing sites, migrations, builds, or deployments.

>-

Guide for benchmarking FlashInfer kernels with CUPTI timing

Quick-start command to run SWE-bench Lite evaluation with sensible defaults.

Benchmark HBF performance using Apache Bench (ab). Measures static asset serving, versioned filesystem operations, and QuickJS runtime routes. Maintains historical data for performance tracking over time.

Expert UI/UX design guidance for unique, accessible interfaces. Use for visual decisions, colors, typography, layouts. Always ask before making design decisions. Use this skill when the user asks to build web components, pages, or applications.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

You are an expert writer who embodies Ben Swift's distinctive voice---a blend of

BentoML skill for model packaging, serving, and containerization.

[Dev] Extracts and organizes best practices for a given topic into a minimal tree structure (max depth 3, max 5 children per node). Use during task planning when writing subtasks in Docs/{name}_Task.md - output is added under each subtask as a concise reference guide. Pure reasoning task with strict formatting rules: keywords/noun phrases only, no prose. (project)

搜索并提炼业界/开源最佳实践的 SOP，强调可信来源、适用边界与可执行建议。

Checks code for best practice violations including DRY violations, SOLID principles, error handling patterns, testing practices, documentation standards, and version control practices. Returns structured best practice reports with improvement suggestions.

You are a research expert specializing in finding and synthesizing best practices from external sources. Your goal is to gather comprehensive information from official documentation, community standar

Enables Claude to browse Best Buy products, manage lists, and track orders

Navigate creative blocks using the Arcanean Bestiary - a taxonomy of psychological obstacles every creator faces, with naming rituals and navigation protocols for each creature type

Activate a beta feature using an activation code

Use when fixing issues identified in beta tester feedback. Guides systematic root cause analysis, worktree-based fixes, regression testing, and release preparation. Invoke with structured beta reports or issue lists.

This skill provides a systematic workflow for improving static pattern matchers through iterative test cycles. Use this approach to:

集成 Better Auth（TypeScript 鉴权框架）时使用。支持邮箱密码、OAuth、魔法链接、Passkey 等，通过插件扩展。编写或配置 Better Auth 时触发。

Integrate Better Auth for JWT-based authentication in Next.js frontend and FastAPI backend. Handles signup, login, logout, token management, and protected routes. Use when implementing authentication for Phase 2.

Expert Better Auth skill with production best practices, session management, security hardening, and deployment optimization. Use with Better Auth MCP server.

Integrate with Better Auth SSO for OAuth2/OIDC authentication. Use this skill when implementing SSO login flows, PKCE authentication, token management, JWKS verification, or global logout in Next.js applications connecting to a Better Auth server.