Forensic — Development skill for Claude Code
Investigate what went wrong in a failed build.
How to install Forensic
Installs to ~/.claude/skills/droidnoob-hew-forensic/SKILL.md
mkdir -p ~/.claude/skills/droidnoob-hew-forensic && curl -fsSL https://raw.githubusercontent.com/droidnoob/hew/HEAD/commands/forensic.md -o ~/.claude/skills/droidnoob-hew-forensic/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Forensic does
description: Investigate what went wrong in a failed build.
Walk `hew task show` audit trails. Check dependency resolution via `hew dep tree `. Find where things broke. Use Beads' Dolt history (`bd history `) to compare states across commits — no `hew` wrapper for history yet.
Alternatives in Development
- Investigate — Investigation Skill 1.9k ★
- Investigate Performance — Investigate a Nimbalyst performance problem (freeze, lag, idle CPU, slow op, memory growth) with measured evid 1.6k ★
- Projectmem — Open-source coding agent memory 766 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Gsd Forensics
Post-mortem investigation for failed GSD workflows — diagnoses what went wrong.
Incident Capture
Capture a structured post-mortem when something went wrong. Walks operator through 4 questions, writes ~/.clau
Agent Clinic
Diagnostic plugins for Claude Code and Codex: why a session went wrong, and whether a proposed change is too m
Explain Error
You are executing the /explain-error command. Your job is to diagnose a Coq type error: parse it, gather conte
What Went Wrong
Explain where a past session went wrong, step by step, from its saved record
Sota Report
Write a SOTA-skills field report for this session — where the guidance failed, was absent, was wrong, or was r
Related Agents
CI Digest
Reads one verbose log (a failed GitHub Actions job, or a local gate log file) and returns only the failures wi
Time Travel
Forensic analyst of failures from six months ahead. Takes a plan (a launch, a project, a migration, a career m
Retro
Retrospective facilitator that captures learnings from sprints and sessions, surfaces past insights, and compo
