Use this agent when you need expert backend development work in TypeScript with Bun runtime, including API design, database integration, server architecture, performance optimization, or any backend-focused development tasks. Examples: Context: User needs to implement a REST API endpoint for user authentication. user…
Use this agent when you need to develop, refactor, or optimize Python backend systems using modern tooling like uv. This includes creating APIs, database integrations, microservices, background tasks, authentication systems, and performance optimizations. Examples: Context: User needs to create a FastAPI application…
Use this agent when you need comprehensive code review from a senior fullstack developer perspective, including analysis of code quality, architecture decisions, security vulnerabilities, performance implications, and adherence to best practices. Examples: Context: User has just implemented a new authentication system…
Use this agent when you need to create, modify, or review frontend code, UI components, or user interfaces. Examples: Context: User needs to create a responsive navigation component for their React application. user: 'I need a navigation bar that works on both desktop and mobile' assistant: 'I'll use the ui-engineer…
A full-fledged Claude Code multi-team orchestration pattern that uses only the native agent teams feature - by decoupling the role of agent-as-leader and agent-as-spawner, a wide range of undocumented capacities for complex layered teams are unlocked.
Agent and skill catalog searcher for squad formation. Reads catalog paths from a user-level config and searches them for existing agents and skills that match capability gaps identified by the skill-identifier. Use when a squad-leader needs to check whether existing agents/skills cover the gaps in a SKILL ANALYSIS…
Skill identification specialist for multi-agent teams. Identifies what skills are required for a task, checks coverage against installed skills, recommends skills for specific agent roles, and surfaces gaps when they exist. Use when you need to identify required capabilities, check skill coverage, produce role-skill…
Coordinator and facilitator for complex tasks within a multi-agent team (squad). Acts as the main communication channel between the squad and the team lead (main Claude), requests new worker spawns as necessary, and helps to keep the squad on course and track progress. Use when faced with a complex task with no…
Designs optimal multi-agent team configurations for any software engineering situation. Analyzes the problem's traits (complexity, urgency, domain, risk), selects the best team pattern, defines agent roles, designs task dependency graphs, and recommends a communication topology. This agent should be used when users…
Techniques for writing comprehensive, self-contained prompts when spawning sub-agents or teammates via the Task tool. Use when delegating work to agents, designing multi-agent workflows, or when spawned agents are returning poor results due to insufficient context. Covers frontloading, file path enumeration…
Analyze user objectives to identify and recommend the optimal set of skills, tools, and knowledge needed to complete tasks effectively. Provide skill gap analysis, pattern-based recommendations, and workflow design for complex tasks. This skill should be used when users need help determining what skills are required…
Protocol reference for delegated squad coordination. Defines the spawn request and completion report message formats that agents use to communicate within a delegated multi-agent squad. This skill should be used when agents need to send spawn requests, write completion reports, or understand the communication…
Expert knowledge base of team organization patterns for multi-agent AI systems and software engineering. Provides pattern selection guidance for scenarios including incident response, greenfield design, legacy migration, security audits, performance optimization, API design, data pipelines, testing, documentation, and…
Hooks that provide Claude with feedback about its own context budget throughout a session, enabling adaptive, context-aware planning and resource conservation.
View or change context-awareness plugin configuration. Use this when the user asks to configure the settings for the context-awareness plugin, or when they ask to view the current configuration.
Gives Claude a calibrated sense of how long engineering tasks actually take when an agent does them — correcting the human-developer overestimation bias and grounding estimates in measured durations of the user's own completed /goal runs.