Collects detailed web performance metrics (TTFB, FCP, LCP, DOM timings, resource sizes and request counts) using a browse daemon and produces baseline and comparison reports. It identifies regressions, slowest resources, and gives concrete remediation suggestions like code-splitting, lazy loading, and async/defer for third-party scripts.
Use this skill when you want to: capture a performance baseline before changes, run quick or full audits on pages, compare current metrics to a baseline to detect regressions, or generate trend reports across multiple runs. Typical triggers: making a PR that changes frontend assets, shipping new third-party scripts, or investigating sudden load-time regressions.
Compatible with agent environments that can run shell tools and a browse daemon (Claude Code / gstack-style environments).
This skill has not been reviewed by our automated audit pipeline yet.
Plan Design Review
Interactive, designer-eye review of design plans: rates dimensions, finds gaps, and edits the plan to add missing UI decisions and interaction states.
gstack: Land and Deploy — Merge, Deploy, Verify
Release-engineering workflow: merge a PR, wait for CI/deploy, run canary checks and optionally revert — designed for safe, auditable production landings.
Retro
MANUAL TRIGGER ONLY: invoke only when user types /retro. Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics w...
