agency-agents-orchestrator

Orchestrates multi-agent development pipelines with task-by-task QA validation loops.

Updated Jul 27, 2026
One-click install
npx skills add https://github.com/imMamdouhaboammar/Mimera --skill agency-agents-orchestrator-immamdouhaboammar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agency-agents-orchestrator
Source: https://github.com/imMamdouhaboammar/Mimera/tree/main/.agents/skills/agents-orchestrator
Command: npx skills add https://github.com/imMamdouhaboammar/Mimera --skill agency-agents-orchestrator-immamdouhaboammar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Coordinating a full development workflow across multiple specialist agents is error-prone: tasks get skipped, quality checks are bypassed, and broken implementations advance unchecked. This Skill runs the entire pipeline autonomously, enforcing quality gates at every step. ## Core Features & Use Cases - End-to-End Pipeline Management: Runs the full workflow from project-manager-senior (spec-to-task conversion) through ArchitectUX (technical foundation) to developer implementation and final integration testing. - Dev-QA Continuous Loops: Each task must pass EvidenceQA validation with screenshot evidence before advancing; failed tasks loop back to developers with specific feedback, up to 3 retry attempts before escalation. - Structured Status Reporting: Produces pipeline progress reports and completion summaries tracking task counts, retry metrics, and production readiness. - Use Case: Given a project specification file, the orchestrator spawns the right specialist agents in sequence, validates each of 8 implementation tasks individually, and only proceeds to final integration testing once all tasks pass QA. ## Quick Start Ask the orchestrator to execute the complete development pipeline for your project specification file, running the autonomous workflow from task planning through per-task QA validation to final integration testing.

Frequently Asked Questions about agency-agents-orchestrator

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

FAQPage Schema
How do I run a full development pipeline with multiple AI agents?

Provide a project specification file and issue a single launch command. The orchestrator spawns a project manager to create the task list, an architect for the technical foundation, then loops developer and QA agents per task until all pass, finishing with integration testing.

How does the dev-QA loop handle failed tasks?

Failed tasks loop back to the developer agent with the QA agent's specific feedback. Each task allows a maximum of 3 retry attempts; after that the task is marked blocked and escalated, while the pipeline continues to final integration testing.

What agents can the orchestrator coordinate?

It coordinates specialist agents across design, engineering, marketing, product management, support, and testing categories, including Frontend Developer, Backend Architect, EvidenceQA, ArchitectUX, and testing-reality-checker, selecting agents based on task type.

What inputs does the orchestrator need to start?

It requires a project specification file located at project-specs/[project]-setup.md. The orchestrator verifies this file exists before spawning the project manager agent to generate the task list.

When does the pipeline advance to final integration testing?

Integration testing begins only after every task in the task list has individually passed QA validation. A testing-reality-checker agent then cross-validates all findings and defaults to NEEDS WORK unless evidence proves production readiness.