garrytan
@garrytan
Public Skills
benchmark
by garrytan
Performance regression detection using the browse daemon. (gstack)
canary
by garrytan
Post-deploy canary monitoring. (gstack)
qa
by garrytan
Systematically QA test a web application and fix bugs found. (gstack)
pair-agent
by garrytan
Pair a remote AI agent with your browser. (gstack)
autoplan
by garrytan
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)
ios-qa
by garrytan
Live-device iOS QA for SwiftUI apps. (gstack)
health
by garrytan
Code quality dashboard. (gstack)
ios-sync
by garrytan
Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)
ios-clean
by garrytan
"Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)"
landing-report
by garrytan
Read-only queue dashboard for workspace-aware ship. (gstack)
benchmark-models
by garrytan
Cross-model benchmark for gstack skills. (gstack)
plan-devex-review
by garrytan
Interactive developer experience plan review. (gstack)
plan-design-review
by garrytan
Designer's eye plan review — interactive, like CEO and Eng review. (gstack)
context-save
by garrytan
Save working context. (gstack)
document-release
by garrytan
Post-ship documentation update. (gstack)
gstack-upgrade
by garrytan
Upgrade gstack to the latest version.
gstack
by garrytan
Fast headless browser for QA testing and site dogfooding. (gstack)
browse
by garrytan
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this".
codex
by garrytan
OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex".
cso
by garrytan
Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep scan, 2/10 bar). Trend tracking across audit runs. Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review".
careful
by garrytan
Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode".