ayao-workflow-agent
Multi-agent workflow orchestrator for coding, writing, analysis, and image tasks via tmux-driven Claude Code and Codex agents. Use when: (1) user requests a feature/fix that should be delegated to coding agents, (2) managing parallel coding tasks across front-end and back-end, (3) monitoring active agent sessions and coordinating review, (4) user says 'start task', 'assign to agents', 'swarm mode', or references the ayao-workflow-agent playbook. NOT for: simple one-liner edits (just edit directly), reading code (use read tool), or single quick questions about code.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/ayao99315/ayao-workflow-agentWhat This Skill Does
ayao-workflow-agent is a sophisticated multi-agent orchestration framework designed for complex, multi-layered development projects. Instead of acting as a direct coder, this skill functions as a 'Project Manager' AI that deploys, monitors, and reviews a swarm of specialized coding agents (Claude Code and Codex) within tmux-managed environments. By centralizing task decomposition and cross-review protocols, it ensures that high-level requirements are translated into atomic, manageable coding tasks while maintaining strict architectural boundaries.
Installation
To integrate this skill into your environment, run the following command within your OpenClaw terminal:
clawhub install openclaw/skills/skills/ayao99315/ayao-workflow-agent
Ensure you have configured your tmux environment and permissions to allow the orchestration shell scripts to execute correctly.
Use Cases
- Complex Feature Development: When building a new module that spans both frontend and backend architectures, requiring parallel development tracks.
- Refactoring & Technical Debt: Managing large-scale code changes where cross-review between independent agents is necessary to prevent regression.
- Standardized Workflows: Ensuring every change, regardless of size, adheres to Conventional Commits and atomic, pushed-immediately commit standards.
- Swarm-based Debugging: Utilizing multiple agent personas (Codex for backend efficiency, Claude for frontend UI/UX) to solve complex bug reports.
Example Prompts
- "Start task: Implement the new OAuth2 authentication flow using the ayao-workflow-agent playbook."
- "Assign to agents: Refactor the user profile component and the corresponding database schema simultaneously."
- "Enter swarm mode and decompose the request to migrate the API from REST to GraphQL, ensuring the cc-review and codex-review agents are active."
Tips & Limitations
- Strict Decoupling: The orchestrator must never touch project files directly. If you find yourself wanting to edit code, stop; decompose the task and dispatch it instead.
- Always Dispatch: You must use
dispatch.shfor all agent tasks. Bypassing this tool will break the event loop, causing status updates to fail and leaving the orchestrator unaware of task completion. - File Isolation: Ensure agents are assigned to non-overlapping file scopes to prevent race conditions during parallel execution. Always review output via the designated review agents (cc-review/codex-review) to maintain code quality across the codebase.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-ayao99315-ayao-workflow-agent": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution
Related Skills
Pulseflow
Skill by ayao99315
Ayao Updater
Skill by ayao99315
opennexum-ts
Contract-driven multi-agent orchestration with ACP. TypeScript CLI for spawning and tracking coding agents via OpenClaw sessions_spawn.
opennexum
Contract-driven multi-agent orchestration with ACP. Contract sync, webhook + dispatch-queue dual dispatch, cross-review, auto-retry, batch progress tracking.