Systematic debugging approaches for isolating and fixing software defects. Use when something isn't working and the cause is unclear.

Dogfooding discovery agent — establish human-approved project baseline from public docs without code inspection

Analyze issues to identify the next work item and update focus.md. Enforces issue-first workflow and confidence-based batch limits.

Comprehensive project hygiene: archive issues, validate schema, clean clutter, align docs, check git, update ignores.

Extract, plan, or propose implementation details at configurable depth levels (low/normal/extensive). Outputs to reference files for team discussion and handoff.

Implement only after a validated/approved plan. Use for coding: small diffs, frequent tests, no refactors, stop on ambiguity.

Migrate a project into another, ensuring functionality and validating complete content transfer. Use for monorepo consolidation, template upgrades, or codebase mergers.

MkDocs documentation site management: initializing, updating, building, and deploying

Identify and map different sections of a software project (API, frontend, database, CLI, domain). Use for context scoping and architecture documentation.

Handle failures and errors during workflow. Use when build breaks, tests fail unexpectedly, or agent gets stuck. Semi-automatic recovery with user confirmation for destructive actions.

Create clean git branches from feature work, excluding agent-ops files. Use for PR preparation.

Manage semantic versioning, changelog generation, and release notes. Auto-generates entries from completed issues or git diff.

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.

Design robust multi-step agent systems with tools and error handling.

This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.

Orchestrates multi-agent workflows by delegating ALL tasks to spawned subagents via /spawn command. Parallelizes independent work, supervises execution, tracks progress in UUID-based output directories, and generates summary reports. Never executes tasks directly. Triggers on keywords: orchestrate, manage agents, spawn agents, parallel tasks, coordinate agents, multi-agent, orc, delegate tasks

Coordinate multiple AI agents and skills for complex workflows

Expert agent organizer specializing in multi-agent orchestration, team assembly, and workflow optimization. Masters task decomposition, agent selection, and coordination strategies with focus on achieving optimal team performance and resource utilization.

Generate standardized .agent-os directory structure with product documentation, mission, tech-stack, roadmap, and decision records. Enables AI-native workflows.

Track and report agent invocation metrics including usage counts, success/failure rates, and completion times. Use for understanding which agents are utilized, identifying underused agents, and optimizing agent delegation patterns.

Write effective system prompts for TD AI agents. Covers role definition, constraint specification, output formatting, tool usage instructions, and prompt structure patterns.

Agent SDK development utilities for creating, testing, and managing AI agents with comprehensive tooling and debugging capabilities.

Systematic framework for selecting the optimal specialized agent for any task. Use when delegating to subagents via the Task tool to ensure the most appropriate specialist is chosen based on framework, domain, task type, and complexity. Applies decision tree logic to match tasks with agent expertise.

Assists in creating Agent Skills of varying complexity levels (simple, moderate, complex). Use when the user wants to create, design, or build a new Agent Skill, or when they need guidance on skill architecture, workflow design, schema validation, or template structure.

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.

Create and manage AI agent skills following best practices. Use when creating new skills, optimizing context, designing multi-agent systems, or implementing progressive disclosure patterns.

Guide creation of focused single-purpose agents following the One Agent One Prompt One Purpose principle. Use when designing new agents, refactoring general agents into specialists, or optimizing agent context for a single task.

Expert technical writer specializing in clear, accurate documentation and content creation. Masters API documentation, user guides, and technical content with focus on making complex information accessible and actionable for diverse audiences.

Optimize ElevenLabs conversational AI agents for real estate applications. Use when creating new agents, improving conversation quality, selecting voices, engineering system prompts, configuring agent parameters, or analyzing agent performance metrics. Includes voice selection, model tuning, prompt engineering, and A/B testing strategies.

Complete workflow for building, implementing, and testing goal-driven agents. Orchestrates building-agents-* and testing-agent skills. Use when starting a new agent project, unsure which skill to use, or need end-to-end guidance.

AgentHero AI - Hierarchical multi-agent orchestration system with PM coordination, file-based state management, and interactive menu interface. Use when managing complex multi-agent workflows, coordinating parallel sub-agents, or organizing large project tasks with multiple specialists. All created agents use aghero- prefix.

Interactive prompt engineering coach that elevates vague prompts through Socratic dialogue, multiple transformation styles, and guided learning. Use when improving prompts, learning agentic engineering, or wanting coached guidance rather than automated transformation. NEVER auto-executes - always displays and asks first.

Use when building AI agent systems. Covers agent loops, tool calling, planning patterns, memory systems, multi-agent coordination, and safety guardrails. Apply when creating autonomous AI workflows, coding assistants, or task automation systems.

Track and measure agentic coding KPIs for ZTE progression. Use when measuring workflow effectiveness, tracking Size/Attempts/Streak/Presence metrics, or assessing readiness for autonomous operation.

Audit codebase for agentic layer coverage and identify gaps. Use when assessing agentic layer maturity, identifying investment opportunities, or evaluating primitive coverage.

Design and implement agentic AI workflows and patterns. Covers ReAct, planning agents, tool use, memory systems, and multi-agent orchestration. Use when building autonomous AI agents, implementing complex task automation, or designing intelligent workflow systems.

>

Generate a project-specific AGENTS.md from a user goal, then confirm before overwriting.

Branch skill for building and improving agents. Use when creating new agents, adapting marketplace agents, validating agent structure, writing system prompts, or improving existing agents. Triggers: 'create agent', 'improve agent', 'validate agent', 'fix agent', 'agent frontmatter', 'system prompt', 'adapt agent', 'customize agent', 'agent examples', 'agent tools'.

Create or update root and nested AGENTS.md files that document scoped conventions, monorepo module maps, cross-domain workflows, and (optionally) per-module feature maps (feature -> paths, entrypoints, tests, docs). Use when the user asks for AGENTS.md, nested agent instructions, or a module/feature map.

Dynamic agent composition and management system. USE WHEN user says create custom agents, spin up custom agents, specialized agents, OR asks for agent personalities, available traits, agent voices. Handles custom agent creation, personality assignment, voice mapping, and parallel agent orchestration.

Create and maintain AgentV YAML evaluation files for testing AI agent performance. Use this skill when creating new eval files, adding eval cases, or configuring custom evaluators (code validators or LLM judges) for agent testing workflows.

This skill provides automated assistance for metrics aggregator tasks.

Master agile metrics with velocity, burn-down charts, cycle time, and team health indicators for data-driven improvement.

Generate agile release plans with sprints and roadmaps using unique sprint codes. Use when creating sprint schedules, product roadmaps, release planning, or when user mentions agile planning, sprints, roadmap, or release plans.

When facilitating sprint retrospectives or team improvement sessions.

Agile product management, Scrum practices, and team collaboration for iterative product development.

Quality Assurance & Design Validation Agent

<skill>

后端代码生成 Skill，负责在 SoT 约束下生成 FastAPI 后端代码。