Review

This is a pre-landing code review skill that runs against your diff before you merge. It checks for SQL safety issues, LLM trust boundary violations, conditional side effects, and other structural problems. Part of the gstack toolchain, so you'll see it suggest itself when you're about to land changes. The preamble does a lot of environment setup,tracking sessions, checking for upgrades, loading project-specific learnings,which means it's tuned for teams with established conventions rather than one-off reviews. If you're working in a repo where bad SQL or sketchy LLM integration can cause real damage, this catches things static analysis might miss. It's opinionated about what matters.

skills.sh installs: 492
GitHub stars: 141K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add garrytan/gstack --skill review --agent claude-code

Installs into .claude/skills of the current project.

Files

Done means

Finish only when each of these exists (contract v1):

specialists-dispatched: the specialist selection printed (Dispatching N specialists: ...), then one Agent dispatch per specialist it names (none when a small diff skips them).
adversarial-pass: an Agent dispatch for the adversarial pass, its prompt including "Think like an attacker and a chaos engineer".
review-report: a Pre-Landing Review with Gate edits filled in (none: <why> where the skill's own stop rule leaves one empty).

~/.claude/skills/gstack/bin/gstack-skill-contract check reads them from the transcript (docs/skill-routing-and-contracts.md). For an item that truly does not apply, run ~/.claude/skills/gstack/bin/gstack-skill-contract waive <item> --reason "<why>" (this session only; it counts as a miss).