Agent Skills
› davepoon/buildwithclaude
› gsd:forensics
gsd:forensics
GitHub用于调查失败的GSD工作流执行问题。通过分析git历史、规划工件和文件系统状态，检测异常并生成结构化的诊断报告，帮助用户定位根因并采取纠正措施。
Trigger Scenarios
工作流执行失败或卡住时
需要诊断自动化流程异常原因时
Install
npx skills add davepoon/buildwithclaude --skill gsd:forensics -g -y
SKILL.md
Frontmatter
{
"name": "gsd:forensics",
"type": "prompt",
"description": "Post-mortem investigation for failed GSD workflows — analyzes git history, artifacts, and state to diagnose what went wrong",
"allowed-tools": [
"Read",
"Write",
"Bash",
"Grep",
"Glob"
],
"argument-hint": "[problem description]"
}
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.
<execution_context> @${CLAUDE_PLUGIN_ROOT}/workflows/forensics.md </execution_context>
User input:
- Problem description: $ARGUMENTS (optional — will ask if not provided)
<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>
Version History
- 502fc01 Current 2026-07-05 15:13
