Ivan Ong
Community@xotong
π Hi there! Iβm Ivan Ong, a Year 4 student at Nanyang Technological University (NTU) specialising in DevSecOps and Cloud Security.
Agent Skills by Ivan Ong
Showing 153 vetted skills indexed across 1 GitHub repositories.
claude-api
Guide Claude API integration across languages with streaming and tool use.
webapp-testing
Automate local web app UI testing with Playwright and with_server.py.
mcp-builder
Design and implement MCP servers with validation and transport configurations.
writing-hookify-rules
Write configurable Hookify rules detecting unwanted patterns in agent interactions.
pair-agent
Pair a remote AI agent with your browser via HTTP requests.
benchmark
Measure webpage performance metrics with the browse daemon to detect regressions across PRs.
design-html
Generate production-ready HTML and CSS from mockups, plans, or descriptions.
plan-tune
Tune gstack AskUserQuestion prompts to respect user preferences and reduce interruptions.
design-shotgun
Generate multiple AI design variants and present them in a side-by-side comparison board.
plan-design-review
Score UI/UX design plans 0-10 and suggest fixes.
stream-chain
Stream each agent's output into the next step for multi-agent workflows.
autoplan
Automate sequential review of CEO, design, engineering, and DX plans.
design-consultation
Plan and codify a design system into a DESIGN.md source of truth.
learn
Aggregate and index project learnings across gstack sessions.
freeze
Restrict file edits to a user-specified directory for the current session.
Hooks Automation
Coordinate Claude Code operations with pre- and post-operation hooks.
careful
Scan Bash commands for destructive patterns and prompt before execution.
cso
Automate infrastructure-first security audits across CI/CD pipelines and dependencies.
Verification & Quality Assurance
Automate verification checks and rollback with configurable truth scoring thresholds.
canary
Monitor live applications post-deployment for console errors and performance regressions.
open-gstack-browser
Launch a visible AI-controlled Chromium browser with a GStack sidebar for live action feeds.
investigate
Trace root causes in failing software through a structured four-phase investigation workflow.
agentic-jujutsu
Coordinate multiple AI agents with quantum-resistant version control and ReasoningBank guidance.
context-restore
Restore the most recently saved context across branches and workspaces.