skills.rest
lucasmiachon-blip
lucasmiachon-blipCOMMUNITY
Explore all skills by this author →
GitHub

debug-team

Coordinate a multi-agent debugging workflow with human-in-the-loop gating.

Updated Aug 23, 2026
Search Tags:#planning#debugging#multi-agent#orchestrator#human-in-the-loop#bug-fix
One-click install
npx skills add https://github.com/lucasmiachon-blip/OLMO --skill debug-team-lucasmiachon-blip
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: debug-team
Source: https://github.com/lucasmiachon-blip/OLMO/tree/main/.claude/skills/debug-team
Command: npx skills add https://github.com/lucasmiachon-blip/OLMO --skill debug-team-lucasmiachon-blip

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Multi-agent bug diagnosis orchestrator for complex bugs that require collaboration across symptom collection, diagnosis, architect planning, patching, and validation, with human-in-the-loop gating.

Core Features & Use Cases

  • Orchestrates a 5-phase debugging flow with strict gating and plan persistence.
  • Supports Single-agent and MAS pathways with iterative verification and rollback.
  • Provides a human-in-the-loop decision step to approve patches and final verdicts.

Quick Start

Describe the bug with /debug-team <bug-description> to start the flow.

Frequently Asked Questions about debug-team

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

FAQPage Schema
How do I debug complex bugs that span multiple files and require multiple hypotheses?▼

A multi-agent orchestrator coordinates a 5-phase debugging workflow—symptom collection, diagnosis, architect planning, patching, and validation—to diagnose and fix complex bugs spanning multiple files with human-in-the-loop gating.

What is multi-agent debugging orchestration and when do I need it?▼

Multi-agent debugging orchestration coordinates specialized agents across symptom collection, diagnosis, planning, patching, and validation phases. Use it when a complex bug spans multiple files or competing hypotheses requiring iterative verification and rollback.

Can I review and approve patches before they are applied during the debugging workflow?▼

Yes, the workflow enforces strict gates with human-in-the-loop decision steps, allowing you to review and approve patch plans and final verdicts before any modifications are applied or validated.

How do I start a multi-agent bug diagnosis flow?▼

Start the multi-agent bug diagnosis flow by invoking /debug-team with a detailed bug description. This triggers the orchestrator to initiate symptom collection, diagnosis, architect planning, patching, and validation phases with strict gating.

What happens if a patch fails validation during the debugging process?▼

If a patch fails validation, the orchestrator supports partial and abort handling with iterative verification and rollback, ensuring the system safely reverts changes or retries phases before issuing a final verdict.

Related Skills

Explore More Software Engineering Skills→
ArtRivArtRiv

gsd-debug

Diagnose software issues by gathering symptoms and running structured root-cause investigations.

Community
Advanced
robkamrobkam
12

bugfix-red-green-proof

Enforce a red-green-proof loop starting with a failing regression test.

Community
Advanced
cxnaivecxnaive

requesting-code-review

Automate pre-commit code verification with static security analysis and regression checks.

Community
Advanced
legoutlegout
3

ai-agent-architect

Design, implement, and harden AI agent architectures with guardrails and evaluation plans.

Community
Advanced