skills.rest
ponsde
ponsdeCOMMUNITY
Explore all skills by this author →
GitHub

debug-engineer

Review coder output and leader modifications across agent-change cycles.

Updated Mar 2, 2026
Search Tags:#documentation#debug#code-review#discussion#bug-fix#change-management
One-click install
npx skills add https://github.com/ponsde/multi-agent-workflow --skill debug-engineer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: debug-engineer
Source: https://github.com/ponsde/multi-agent-workflow/tree/main/skills/debug
Command: npx skills add https://github.com/ponsde/multi-agent-workflow --skill debug-engineer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Debug 角色负责对 Coder 的产出和 Leader 的修改进行审查，发现问题后直接修复，确保代码质量与交付节奏。

Core Features & Use Cases

  • 三层审查框架：正确性、健壮性、工程质量，确保改动的逻辑正确、健壮且可维护。
  • 场景覆盖：审查 Coder 产出、进行定点修复、验收 Leader 的修改三种工作场景。
  • 工作流记录：按阶段读取 AI-CONTEXT.md、change 产出物与 discussion.md，并将审查结果追加到 discussion.md，形成可追溯的对话历史。

Quick Start

请在接到任务后，先阅读 AI-CONTEXT.md 及变更产出物，然后执行三层审查并将结果汇报给 Leader。

Frequently Asked Questions about debug-engineer

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

FAQPage Schema
What is a three-layer code review framework for multi-agent software projects?▼

A three-layer code review framework evaluates changes across correctness, robustness, and engineering quality to ensure multi-agent software modifications remain logically sound, resilient, and maintainable throughout agent-change cycles.

How do I automate bug-fix workflows and review coder output in a multi-agent environment?▼

You automate bug-fix workflows by reading AI-CONTEXT.md and change artifacts, applying targeted fixes to coder output, validating leader modifications, and appending structured review results to discussion.md logs for cross-round traceability.

Can I use this automated code review process to validate leader modifications across agent-change cycles?▼

Yes, validating leader modifications across agent-change cycles is a core scenario, ensuring modifications are reviewed for correctness and robustness while maintaining structured discussion logs for full traceability.

How do I maintain cross-round traceability for code review and bug-fix discussions?▼

You maintain cross-round traceability by appending review results, targeted fixes, and validation outcomes to discussion.md, creating a structured conversation history that tracks changes across all agent-change cycles.

Does this structured discussion log approach work without external dependencies for change management?▼

Yes, this change management approach operates with zero external dependencies, relying solely on reading AI-CONTEXT.md and change artifacts to execute the three-layer review and record results directly in discussion.md.

Related Skills

Explore More Software Engineering Skills→
conn-castleconn-castle
9

plan-work

Convert change requests into scoped plans, task lists, and context files.

Official
Intermediate
STUkhSTUkh
27

sparq:generate-manual

Generate manual test cases from QA requirements across HP, VE, SEC, EC, and A11Y.

Community
Advanced
ZeliperZeliper

spawn-coder

Delegate coding tasks to a coder-agent via the Task tool.

Community
Intermediate
iulianditaiuliandita
2

full-review

Orchestrate parallel execution of four audit skills for codebase quality assessment.

Community
Advanced