gstack-openclaw-investigate

An agent skill by garrytan, from garrytan/gstack. Tags: analysis, debugging, troubleshooting.

What it does

Use when asked to debug, fix a bug, investigate an error, or do root cause analysis, and when users report errors, stack traces, unexpected behavior, or say something stopped working.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add garrytan/gstack --skill gstack-openclaw-investigate

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/garrytan/gstack
cp -r gstack/openclaw/skills/gstack-openclaw-investigate ~/.claude/skills/gstack-openclaw-investigate

Safety box score

Grade B, low risk: 11 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a debugging workflow skill: it tells the agent to read code, inspect git history, reproduce bugs, run tests, and write a debug report. Its main risks are ordinary command execution during investigation, a small amount of network use for external search, and writing a report into `memory/`; it does not itself include destructive or privileged operations.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It explicitly directs the agent to run investigation commands and tests, e.g. `git log --oneline -20 -- <affected-files>` and `Run the full test suite`, which is normal but still command execution.
Network access	1 (low)	It allows an `External search` for error types online, which can send sanitized problem context off machine, but only as part of debugging.
Filesystem reach	1 (low)	It instructs saving a report to `memory/` and reading source code/ logs, but does not call for writes outside the workspace or destructive file operations.
Secrets & credentials	0 (none)	It does not ask for passwords, tokens, browser sessions, `.env` files, or other credentials; it only says to sanitize sensitive data before searching.
Privilege & persistence	0 (none)	There is no sudo, service registration, global install, or OS settings change in the skill.
Instruction hijack surface	0 (none)	The text contains no instruction to ignore higher-priority rules, hide actions, or follow fetched remote instructions.
Irreversible actions	0 (none)	It is a debugging-only workflow and does not push, deploy, post, pay, book, or delete anything.
Transparency	0 (none)	The skill is plain markdown with no binaries, generated code, or hidden/decoded content.

Before installing

Read `SKILL.md` and confirm you are okay with the agent running repo commands and tests.
Check whether `memory/` is a workspace-local folder and whether you want debug reports persisted there.
Decide if external web search during debugging is acceptable in your environment.
If you have sensitive reproduction data, verify that sanitization is enough before letting the agent search online.

Rated 2026-10-20 by an automated review of 1 file from the skill's repository.

Source

Repository: garrytan/gstack (all skills from this repository)
Path: openclaw/skills/gstack-openclaw-investigate/SKILL.md
Branch: main
Updated: 2026-10-05

principle-fix-root-causes — Apply when debugging.
investigate — Systematic debugging with root cause investigation. (gstack)
diagnosing-bugs — Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
investigate-first — Diagnose ambiguous failures before editing.
troubleshooting-application-failures — Troubleshoots failing applications by discovering and analyzing CloudWatch log groups to identify error patterns, root causes, and actionable solutions.
agents-debug — Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes.