Menu

Individual skill

incident-investigation

Investigate a named user's session, error, stuck agent run, or replay evidence. Use for what a user did, why something failed for them, or what they typed.

templates/analytics/.agents/skills/incident-investigation/SKILL.md

Read pinned source

Source commit ff01b4009091c2140edb34d6f790ec64e7823356

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 2, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
7,645
Repository last updated
Nov 7, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Incident Investigation

Use the first-party observability actions instead of generic SQL. These
read-only investigation tools remain available in Plan mode; run the query
instead of deferring it to execution mode. Load any that are not callable yet
with one `tool-search` call naming all of them.

## A Named User's Session Or Error

1. Resolve the user's email from context, then call `list-session-recordings`
   with `userId` over a bounded recent window to find the relevant sessions. Do
   not require `hasErrors=true` for this initial lookup: replay, network, and
   stuck-run evidence can exist while the recording's JavaScript `errorCount` is
   zero. Use `hasErrors=true` only when the user asks for recordings with