skills.rest
josephwander-arch
josephwander-archCOMMUNITY
Explore all skills by this author →
GitHub

manager-getting-started

Orchestrate backend selection and execution for multi-backend coding tasks.

Updated Aug 27, 2026
Search Tags:#orchestration#workflow-automation#code-review#parallel-execution#multi-backend#task-polling#ai-routing
One-click install
npx skills add https://github.com/josephwander-arch/manager --skill manager-getting-started
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: manager-getting-started
Source: https://github.com/josephwander-arch/manager/tree/main/skills/manager-getting-started
Command: npx skills add https://github.com/josephwander-arch/manager --skill manager-getting-started

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manager centralizes multi-AI orchestration so teams do not have to manually choose between backends, stitch parallel runs together, or build brittle workflow chains when delegating coding, review, and reasoning tasks to multiple AI providers.

Core Features & Use Cases

  • Task lifecycle & polling: Submit tasks, check status, and retrieve outputs across heterogeneous backends.
  • Smart routing & templates: Use auto_route or explicit routing to let Manager learn which backend performs best and save reusable workflow templates.
  • Parallel execution & workflows: Run concurrent review or generation steps, chain multi-step workflows with retries and escalation, and group parallel tasks by dependency.
  • Interactive sessions & direct calls: Start session-based interactions or call backends directly (Claude Code, Codex, Gemini CLI, GPT) for targeted jobs.
  • Analytics & monitoring: Collect execution stats, run analyzers to promote/demote backends, and surface active breadcrumbs in the dashboard.

Quick Start

Ask Manager to submit the coding task Add error handling to src/main.rs with auto_route enabled so it selects the best backend and returns the result.

Frequently Asked Questions about manager-getting-started

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run parallel coding tasks across Claude Code, OpenAI Codex, and Gemini CLI?▼

You can run parallel coding tasks across Claude Code, OpenAI Codex, and Gemini CLI by submitting concurrent tasks to a Manager MCP server, which groups parallel jobs by dependency and retrieves outputs across heterogeneous backends.

What is multi-AI workflow orchestration for code review and generation?▼

Multi-AI workflow orchestration centralizes coding, review, and reasoning tasks by routing them across configured AI backends, enabling concurrent execution, workflow chaining with retries, and session management without manual backend selection.

How do I set up smart routing for multi-backend AI coding tasks?▼

You can set up smart routing by enabling auto_route when submitting tasks, allowing the Manager server to learn which backend performs best, while also supporting explicit routing and reusable workflow templates for specific jobs.

Do I need API credentials to orchestrate tasks across multiple AI backends?▼

Yes, orchestrating tasks across multiple AI backends requires access to a running Manager MCP server with configured AI backends and valid API credentials to execute coding, review, and reasoning tasks successfully.

Can I chain multi-step AI workflows with retries and escalation?▼

Yes, you can chain multi-step AI workflows with retries and escalation by configuring workflow templates on the Manager server, allowing sequential generation and review steps to execute across backends with automatic failure handling.

What's the best way to monitor execution stats for parallel AI coding tasks?▼

The best way to monitor execution stats for parallel AI coding tasks is to use the Manager dashboard, which collects execution analytics, runs analyzers to promote or demote backends, and surfaces active breadcrumbs.

Related Skills

Explore More Software Engineering Skills→
rbinarrbinar
5

ds-delegate

Delegate complex coding tasks to external LLM backends within Claude Code.

Community
Advanced
apecloudapecloud
3

kubeblocks-switchover

Document primary/secondary switchover steps with pre-checks and verification.

Official
Intermediate
CUexterCUexter
2

blackbox

Orchestrate multi-model coding tasks via the Blackbox CLI.

Community
Advanced
dennisonbertramdennisonbertram
8

nano-banana

Generate images from natural language prompts via the Gemini API.

Community
Intermediate