‹ 首页

thrunt-forensics

@backbay-labs · 收录于 1 周前

Post-mortem investigation for failed THRUNT workflows — analyzes git history, artifacts, and state to diagnose what went wrong

场景工作流故障排查事后分析根因定位

适合你，如果经常需要排查自动化工作流失败的原因

/ 下载安装
thrunt-forensics.skill双击,或拖进 Claude 桌面版 / Cowork,即完成安装↓ .skill↓ .zip
用别的 agent?下载 .zip 解压,把文件夹放进它的技能目录
Claude Code~/.claude/skills/(项目级 .claude/skills/)
Codex CLI~/.codex/skills/
Cursor自动读取上面两处目录
其他工具见其文档的「skills」目录;两个下载是同一份文件,只是名字不同
/ 通过 npx 安装 校验哈希
npx oh-my-skill add backbay-labs/thrunt-god/thrunt-forensics
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- backbay-labs/thrunt-god/thrunt-forensics
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify backbay-labs/thrunt-god/thrunt-forensics
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
34GitHub stars
~462上下文体积 · 单文件
镜像托管

怎么用

技能原文 SKILL.md作者撰写 · MIT · 1e21b3d

<objective> Investigate what went wrong during a THRUNT workflow execution. Analyzes git history, .planning/ artifacts, and file system state to detect anomalies and generate a structured diagnostic report.

Purpose: Diagnose failed or stuck workflows so the user can understand root cause and take corrective action. Output: Forensic report saved to .planning/forensics/, presented inline, with optional issue creation. </objective>

<execution_context> @.github/thrunt-god/workflows/forensics.md </execution_context>

<context> Data sources:

  • git log (recent commits, patterns, time gaps)
  • git status / git diff (uncommitted work, conflicts)
  • .planning/STATE.md (current position, session history)
  • .planning/HUNTMAP.md (phase scope and progress)
  • .planning/phases/*/ (PLAN.md, SUMMARY.md, FINDINGS.md, CONTEXT.md)
  • .planning/reports/SESSION_REPORT.md (last session outcomes)

User input:

  • Problem description: $ARGUMENTS (optional — will ask if not provided)

</context>

<process> Read and execute the forensics workflow from @.github/thrunt-god/workflows/forensics.md end-to-end. </process>

<success_criteria>

  • Evidence gathered from all available data sources
  • At least 4 anomaly types checked (stuck loop, missing artifacts, abandoned work, crash/interruption)
  • Structured forensic report written to .planning/forensics/report-{timestamp}.md
  • Report presented inline with findings, anomalies, and recommendations
  • Interactive investigation offered for deeper analysis
  • GitHub issue creation offered if actionable findings exist

</success_criteria>

<critical_rules>

  • Read-only investigation: Do not modify project source files during forensics. Only write the forensic report and update STATE.md session tracking.
  • Redact sensitive data: Strip absolute paths, API keys, tokens from reports and issues.
  • Ground findings in evidence: Every anomaly must cite specific commits, files, or state data.
  • No speculation without evidence: If data is insufficient, say so — do not fabricate root causes.

</critical_rules>

按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。
…