菜单
Find the root cause of a bug or failing test. Spawns 1 debugger subagent that reproduces, ladders hypotheses, isolates with evidence, and applies the minimal fix. Use when a test fails, /build reports blocked, or "X stopped working". Does NOT design features (that's /plan).
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/ayusavin/labs-harness --skill debug命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | debug |
| description | Find the root cause of a bug or failing test. Spawns 1 debugger subagent that reproduces, ladders hypotheses, isolates with evidence, and applies the minimal fix. Use when a test fails, /build reports blocked, or "X stopped working". Does NOT design features (that's /plan). |
ORCHESTRATOR. One debugger subagent. It diagnoses before it touches anything.
/debug "<error text / failing test / what broke>" (optionally /debug <slug> to tie it
to a feature build)
swarm-report/<slug>-build.md if a slug was given.Task, general-purpose). Prompt:
Answer TERSE. Read
.claude/agents/debugger.mdand follow it exactly. Symptom: <verbatim error / failing test>. Feature slug (if any): .
fixed → suggest /review <slug> to check the fix.root_cause_found (found but not fixed) or stuck → show the hypothesis ladder;
the user decides the fix, or re-run /build <slug> with the root cause as input.cannot_reproduce → ask the user for exact repro steps; do not guess-patch./plan → /build → /review. If a test fails or review says rework → /debug →
back to /build. The Stop test-gate hook blocks "done" until tests actually run.