investigate
Systematic debugging with root-cause discipline: reproduce, hypothesize, test one variable at a time, and distinguish confirmed from plausible in the report.
Anatomy
| Parent repo | garrytan/gstack |
|---|---|
| Path | skills/investigate |
| Trigger conditions | Slash command: /investigate |
| Instruction format | yaml-frontmatter-md |
| Required tools | shell |
| Reusability | universal |
| Complexity | medium |
| Ships scripts / examples / tests / boundaries | no / yes / no / yes |
Failure modes
Slash-triggered, so it protects nothing unless invoked; superpowers' auto-triggering equivalent fires without being remembered.
Verdict
The confirmed-versus-plausible reporting requirement is the standout: it makes overclaiming visible in the artifact itself.
Related skills
Blocks the agent from claiming work is complete, fixed, or passing until it has run verification commands and confirmed output. Evidence…
Forces root-cause investigation before any fix: reproduce, hypothesize one cause at a time, test the hypothesis, then patch. Bans…
Frequently asked questions
What does the investigate skill do?
Systematic debugging with root-cause discipline: reproduce, hypothesize, test one variable at a time, and distinguish confirmed from plausible in the report.
When does investigate trigger?
Its stated trigger: Slash command: /investigate. Trigger precision is a scored reliability dimension.