Agent Skills › WingedGuardian/GENesis-AGI › debugging

debugging

GitHub

用于系统性地诊断和解决Genesis或其依赖中的Bug、测试失败及运行时错误。通过复现、隔离、假设验证等步骤定位根因，应用最小修复并验证回归，最终输出结构化文档以预防复发。

src/genesis/skills/debugging/SKILL.md WingedGuardian/GENesis-AGI

Trigger Scenarios

测试意外失败出现运行时错误或非预期行为感知或反思产生异常结果障碍解决升级为技术问题

Install

npx skills add WingedGuardian/GENesis-AGI --skill debugging -g -y

More Options

Non-standard path

npx skills add https://github.com/WingedGuardian/GENesis-AGI/tree/main/src/genesis/skills/debugging -g -y

Use without installing

npx skills use WingedGuardian/GENesis-AGI@debugging

指定 Agent (Claude Code)

npx skills add WingedGuardian/GENesis-AGI --skill debugging -a claude-code -g -y

安装 repo 全部 skill

npx skills add WingedGuardian/GENesis-AGI --all -g -y

预览 repo 内 skill

npx skills add WingedGuardian/GENesis-AGI --list

SKILL.md

Frontmatter

{
    "name": "debugging",
    "phase": 6,
    "consumer": "cc_background_task",
    "skill_type": "workflow",
    "description": "Systematic debugging of issues — use when a test fails, runtime error occurs, unexpected behavior is reported, or an awareness tick produces anomalous results"
}

Debugging

Purpose

Systematically diagnose and resolve bugs, failures, or unexpected behavior in Genesis or its dependencies.

When to Use

A test fails unexpectedly.
Runtime error or unexpected behavior is reported.
An awareness tick or reflection produces anomalous results.
Obstacle resolution escalates a technical issue.

Workflow

Reproduce — Confirm the issue. Get the exact error, stack trace, or unexpected output. Define "expected vs. actual."
Isolate — Narrow the scope. Which module? Which function? Which input triggers it? Use binary search on the call chain.
Hypothesize — Form 2-3 candidate explanations. Rank by likelihood.
Test hypotheses — Write a minimal test or add logging to confirm/deny each hypothesis. Start with the most likely.
Fix — Apply the minimal correct fix. Do not fix adjacent issues in the same change.
Verify — Run the failing test. Run the full test suite. Confirm no regressions.
Document — Record the root cause and fix as an observation. Update procedures if the bug class is recurring.

Output Format

issue: <one-line description>
date: <YYYY-MM-DD>
root_cause: <what actually went wrong>
fix: <what was changed>
files_modified:
  - <file path>
regression_risk: low | medium | high
lesson: <what to remember to prevent recurrence>

Examples

Example: Hook fails in non-login shell

Trigger: Post-commit hook throws KeyError: 'HOME' in CI-like environment.

Expected output:

issue: Post-commit hook crashes when HOME not set in non-login sessions
date: 2026-04-06
root_cause: Hook script reads os.environ["HOME"] but non-login shells
  (systemd, cron) strip HOME from environment
fix: Guard with os.environ.get("HOME", "/root") fallback + persist HOME
  in /etc/environment during install
files_modified:
  - .claude/hooks/genesis-hook
  - scripts/install_guardian.sh
regression_risk: low
lesson: Never assume HOME exists — non-login shells strip it. Always
  use get() with fallback for environment variables in hook scripts.