Gsd Forensics — Development skill for Claude Code
Post-mortem investigation for failed GSD workflows — diagnoses what went wrong.
How to install Gsd Forensics
Installs to ~/.claude/commands/axisrow-zai-codex-helper-gsd-forensics.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/axisrow/zai-codex-helper/HEAD/.claude/commands/gsd-forensics.md -o ~/.claude/commands/axisrow-zai-codex-helper-gsd-forensics.md Restart Claude Code, or start a new session, for it to be picked up.
What Gsd Forensics does
type: prompt name: gsd-forensics description: Post-mortem investigation for failed GSD workflows — diagnoses what went wrong. argument-hint: "[problem description]" allowed-tools:
- Read
- Write
- Bash
- Grep
- Glob requires: [phase, progress, update]
Investigate what went wrong during a GSD workflow execution. Analyzes git history, `.planning/` artifacts, and file system state to detect anomalies and generate a structured diagnostic report.
Purpose: Diagnose fail
Alternatives in Development
- Pre Mortem — Run pre-mortem risk analysis on PRDs and launch plans 7.8k ★
- Investigation First 3.7k ★
- Octo Debug — Systematic debugging with methodical problem investigation 2.8k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Incident Capture
Capture a structured post-mortem when something went wrong. Walks operator through 4 questions, writes ~/.clau
Investigator
Root-cause debugging specialist that diagnoses issues through systematic investigation before proposing any fi
Explain Error
You are executing the /explain-error command. Your job is to diagnose a Coq type error: parse it, gather conte
Computer Forensics
Digital forensics analysis and investigation techniques.
Extraction Principle
Invoke when direct questions have failed, the subject controls access to information you need, or you are desi
Hatch3r Incident Response
Drive a live production incident through a structured lifecycle -- triage + topology, bounded-autonomy mitigat
Related Agents
Bd Diagnose
Diagnoses why a run broke or looks wrong — NaN, blow-up, a failed prediction, a strange plot shape. Needs hypo
Lw Healer
Diagnoses and remediates failed background agents, stalled tasks and broken local tooling. Dispatched by the h
Retro
Retrospective facilitator that captures learnings from sprints and sessions, surfaces past insights, and compo