liauw-media
@liauw-media
Public Skills
code-review
by liauw-media
"Self-review before declaring work complete"
frontend-design
by liauw-media
Create distinctive, production-grade frontend interfaces with high design quality. Use when building web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
playwright-frontend-testing
by liauw-media
"Use when testing frontend applications. AI-assisted browser testing with Playwright MCP. Fast, deterministic, no vision models needed."
brand-guidelines
by liauw-media
"Establish or analyze brand identity guidelines. Creates comprehensive brand documentation that frontend-design, testing, and other skills automatically reference for consistent execution."
browser-automation-debugging
by liauw-media
"Use when debugging web applications or automating browser tasks. Leverage Chrome DevTools MCP for inspection, performance analysis, and automated testing."
lighthouse-performance-optimization
by liauw-media
"Use when optimizing website performance. Run Google Lighthouse audits via MCP to measure metrics, identify bottlenecks, and iterate on improvements."
git-platform-cli
by liauw-media
"MANDATORY: Use gh (GitHub) or glab (GitLab) CLI for ALL issue/task management. Unified workflow across platforms."
pre-commit-hooks
by liauw-media
"MANDATORY setup for all projects. Automated code quality enforcement before commits. Prevents bad code from entering repository."
git-workflow
by liauw-media
"Use when making commits, creating branches, or managing Git operations. Ensures consistent Git practices and proper commit messages."
verification-before-completion
by liauw-media
"Use when finishing any task. Final checklist before marking complete. Ensures nothing forgotten, all tests pass, documentation updated."
testing-anti-patterns
by liauw-media
"Use to avoid critical testing mistakes. Five Iron Laws: Never test mock behavior, Never add test-only methods, Never mock without understanding, Always integration test, Always test error paths."
sharing-skills
by liauw-media
"Use when contributing skills back to the community. Follow git workflow: sync upstream → create branch → develop skill → test with writing-skills → commit → push → PR. One skill per PR."
writing-skills
by liauw-media
"Use when creating reusable process documentation. Apply TDD: baseline without skill → document failures → write skill → test → iterate. Four types: Discipline, Technique, Pattern, Reference. Iron Law: No skill without failing test first."
testing-skills-with-subagents
by liauw-media
"Use to validate process documentation. Apply TDD to skill writing: RED (run without skill, document failures) → GREEN (write skill) → REFACTOR (close loopholes). Test under pressure: time constraints, sunk cost, exhaustion, authority."
root-cause-tracing
by liauw-media
"Use when symptoms don't reveal the cause. Trace backward through call chains to find where problems originate. Follow: Observe symptom → Find immediate cause → Identify caller → Keep tracing → Locate trigger."
requesting-code-review
by liauw-media
"Use when completing tasks or major features. Know when and how to request reviews. Provides git commit range to code-reviewer agent."
defense-in-depth
by liauw-media
"Use when implementing validation or safety checks. Multi-layer validation approach prevents bugs through redundant safeguards. Makes bugs structurally impossible."
condition-based-waiting
by liauw-media
"Use when tests fail intermittently. Replace arbitrary timeouts with condition polling. Eliminates flaky tests caused by timing assumptions."
receiving-code-review
by liauw-media
"Use when processing code review feedback. Technical evaluation of feedback, verify before implementing. No performative agreement or gratitude."
finishing-a-development-branch
by liauw-media
"Use when ready to merge feature branch. Complete checklist before creating PR/MR. Ensures professional quality and prevents embarrassing mistakes."
test-driven-development
by liauw-media
"Use when adding features or fixing bugs. Follow RED/GREEN/REFACTOR cycle. Write failing test first, implement minimal code to pass, then refactor."
dispatching-parallel-agents
by liauw-media
"Use when multiple independent tasks can run simultaneously. Enables efficient parallel work execution with specialized agents."
systematic-debugging
by liauw-media
"Use when encountering bugs or unexpected behavior. Methodical approach to identify root cause: Reproduce → Isolate → Identify → Fix → Verify."
writing-plans
by liauw-media
"Use after brainstorming, before implementation. Breaks work into discrete, actionable tasks with clear verification points."