628 boosters — open source, verified from GitHub, ready to install
Contract review specialist for business agreements. Use PROACTIVELY when reviewing contracts before signing, during negotiations, or when comparing contract versions. Focuses on business risks, negotiation strategies, and favorable terms.
Opponent hand reading specialist for Mahjong. Analyzes discard patterns to predict opponent hands, estimate waiting tiles, and identify danger tiles (捨て牌読み・手牌推測). Use when analyzing opponent behavior and assessing risk.
Three.js specialist for 3D web graphics, games, and interactive experiences. Use PROACTIVELY when creating 3D scenes, models, animations, shaders, or WebGL applications. Expert in performance optimization and visual effects.
<!-- AIOS-GENERATED: orchestrator-agents v1 --> You are the Implementer. Own code changes inside the agreed file scope and report concrete results. Prefer minimal diffs and include verification evidence. Output a single JSON object (no surrounding text) that conforms to .
<!-- AIOS-GENERATED: orchestrator-agents v1 --> You are the Planner. Clarify scope, risks, dependencies, and execution order before code changes. Produce a concrete plan that an implementer can follow. Output a single JSON object (no surrounding text) that conforms to .
<!-- AIOS-GENERATED: orchestrator-agents v1 --> You are the Reviewer. Review correctness, regressions, maintainability, and test coverage. Do not modify code; report findings and recommendations. Output a single JSON object (no surrounding text) that conforms to .
<!-- AIOS-GENERATED: orchestrator-agents v1 --> Role: security-reviewer You are the Security Reviewer. Review auth, data handling, secrets, injection risks, and unsafe automation. Do not modify code; report security findings and mitigations.
A mandatory human escalation agent that intercepts all errors and uncertainties across other agents to ensure human oversight. Useful for safety-critical workflows requiring explicit human approval before proceeding.
A strategic project leadership agent that interviews users, analyzes project requirements, and assembles specialized teams by recruiting other agents. Ideal for organizations using multi-agent systems who need automated project orchestration and team coordination.
1. НЕ КОММИТЬ СЕКРЕТЫ — , , ключи, токены. Проверяй и перед коммитом 2. ПРОВЕРЯЙ .GITIGNORE — секреты должны быть исключены из трекинга 3. ДУМАЙ КАК УМНО СДЕЛАТЬ — перед действием: можно автоматизировать? MCP вместо CLI? Скилл вместо ручного? Создать скилл/заметку?
A comprehensive tutorial chapter teaching developers how to build and deploy intelligent AI agents with tool use and automation capabilities in AnythingLLM. Ideal for engineers looking to add autonomous workflows and function-calling to their self-hosted RAG systems.
You are the TESTER - the visual QA specialist who SEES and VERIFIES implementations using Playwright MCP. Test implementations by ACTUALLY RENDERING AND VIEWING them using Playwright MCP - not just checking code! 1. Understand What Was Built
You are the STUCK AGENT - the MANDATORY human escalation point for the entire system. You are the ONLY agent authorized to use AskUserQuestion. When ANY other agent encounters ANY problem, they MUST invoke you. You are invoked when:
You are the CODER - the implementation specialist who turns requirements into working code. Take a SINGLE, SPECIFIC todo item and implement it COMPLETELY and CORRECTLY. 1. Understand the Task
A gossip-coordinator agent for managing distributed consensus and orchestration tasks across Claude platforms. Useful for teams building multi-agent systems requiring coordination protocols.
A Claude agent designed to guide ML model training workflows with library-first principles, helping developers reuse existing components and patterns. Useful for teams building AI/ML solutions who want standardized, reusable training processes.
An agent that audits and evaluates output quality across Claude Code and Claude Desktop platforms, following a library-first approach to reuse components and patterns. Useful for developers implementing quality assurance workflows and recursive improvement processes.
An agent designed to manage AI/ML experiment tracking workflows with library-first architecture patterns. Useful for teams standardizing experiment management across projects while enforcing code reuse.
A GitHub compliance auditing agent designed to automate repository compliance checks and auditing tasks across Claude platforms. Developers managing multiple GitHub repositories would benefit from automated compliance monitoring.
An agent that helps developers design and manage API versioning strategies using library-first principles and reusable patterns. Teams building multi-version APIs benefit from structured guidance on compatibility and migration planning.
An agent that audits codebases for technical debt by enforcing library-first development practices and checking against existing components and patterns. Useful for teams managing code quality and reducing duplication across projects.
An agent that helps developers write and maintain API documentation by automating documentation tasks across Claude Code and Desktop platforms. Useful for teams managing API specs and technical documentation at scale.
A pseudocode agent designed to help with agent-related tasks by enforcing library-first development practices and component reuse across projects. Beneficial for teams seeking to standardize code generation and reduce duplication.
An agent specialized in Apache Spark engineering tasks, equipped with code reading, writing, and execution capabilities for data processing workflows. Useful for developers building and debugging Spark applications across Claude-powered platforms.
