LaunchKit · 2026
Back to skills
Garry Tan

Garry Tan

27 skills available

·View on GitHub
1
browse

A headless Chromium controller for testing and verifying web apps.

2
careful

Adds safety guardrails to bash commands by intercepting destructive operations before they run.

3
canary

Canary monitors a live app after a deploy by checking pages for console errors, performance regressions, and load failures.

4
design-consultation

Runs a design consultation session to build a complete design system from scratch.

5
design-review

Audits a live site for visual problems — spacing inconsistencies, hierarchy failures, typography issues, AI-generated layout patterns, and sluggish interactions.

6
freeze

Restricts Claude's Edit and Write operations to a single directory for the duration of a session.

7
document-release

Runs after code ships to bring all project documentation in sync with what actually changed.

8
benchmark

Measures web page performance by collecting real PerformanceAPI data from a running browser session.

9
gstack-upgrade

Upgrades gstack to the latest version.

10
guard

Guard mode combines two safety layers: destructive command warnings (rm -rf, DROP TABLE, force-push) and directory-scoped edit restrictions.

11
cso

Runs a multi-phase security audit across a codebase.

12
autoplan

Runs CEO, design, and engineering review skills on a plan file in sequence, making intermediate decisions automatically using six built-in principles.

13
land-and-deploy

Picks up where /ship leaves off.

14
codex

Wraps the OpenAI Codex CLI to provide three code analysis modes: a structured diff review with a pass/fail gate, an adversarial challenge that searches for edge cases and failure paths, and a consult mode for open-ended questions with session continuity across turns.

15
investigate

A structured debugging workflow that enforces root cause analysis before any fix is applied.

16
qa-only

Runs a structured QA pass on a web application and produces a report with a health score, screenshots, and reproduction steps.

17
qa

A QA skill that runs browser-based testing on web applications, finds bugs, and fixes them in source code.

18
setup-browser-cookies

Imports cookies from an installed Chromium browser into a headless Playwright session.

19
setup-deploy

Detects your deployment platform (Fly.

20
retro

Runs a weekly engineering retrospective by analyzing git history, commit patterns, and code quality signals.

21
office-hours

A two-mode office hours simulation that saves a design document.

22
unfreeze

Clears the directory restriction set by /freeze, restoring edit access to all directories in the current session.

23
plan-design-review

Reviews UI/UX design decisions in a plan file before implementation.

24
plan-eng-review

Runs an engineering manager-style review on a plan before coding starts.

25
plan-ceo-review

Reviews development plans from a CEO/founder perspective before implementation.

26
review

Pre-landing PR review that analyzes a branch's diff against the base branch.

27
ship

Runs the full ship workflow from a feature branch in one command.