BALAI-OS

Activates the "Chameleon" persona for working in existing codebases shared with human teammates. Absorbs the codebase's established style and patterns before writing code. Issues explicit warnings when mimicking sub-optimal patterns. Use when the user says "hackathon", "team project", "internship", "other people's code", "brownfield", or asks to "match the existing style."

Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.

Activates the Kairou Persona (The Architect) to create implementation plans, project specifications, and architectural blueprints. Use when the user asks to "plan", "roadmap", or "architect" a solution.

Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.

Use when designing APIs, selecting between REST/GraphQL/tRPC, determining response formats, versioning strategies, or pagination.

Use when creating full-stack applications from scratch, determining project types, selecting tech stacks, or coordinating multiple agents for complex builds.

Use when making architecture decisions or analyzing system design—Architectural decision-making frameworks, Requirements analysis, trade-off evaluation, ADR documentation.

Use when writing pragmatic code, refactoring for simplicity, or enforcing coding standards (SRP, DRY, KISS).

Unified code analysis skill combining 'Architecture Inspector' and 'Debug Investigator' capabilities. Use when analyzing code flow, debugging bugs, or auditing architecture.

Use when conducting code reviews, checking for security vulnerabilities, or ensuring code quality best practices.

Use when designing database schemas, selecting ORMs, planning indexing strategies, or choosing between SQL/NoSQL/Serverless databases.

Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.

React and Next.js performance optimization from Vercel Engineering. Use when building React components, optimizing performance, eliminating waterfalls, reducing bundle size, reviewing code for performance issues, or implementing server/client-side optimizations.

Use when developing Node.js applications, selecting frameworks (Express/Fastify/Hono), or implementing async patterns and security best practices.

Use when developing Python applications, selecting frameworks (FastAPI/Django/Flask), or implementing async patterns and type hints.

Use when styling with Tailwind CSS, upgrading to v4, designing responsive layouts, or configuring design tokens.

Use when implementing any feature or bugfix, before writing implementation code

Use when planning test strategies, writing unit/integration tests, or selecting mocking patterns.

Use when testing web applications end-to-end, writing Playwright scripts, or performing deep automated audits.

Use when planning cost-effective deployments, optimizing hosting costs, or implementing FinOps strategies.

Use when planning production deployments, defining rollout strategies, or establishing safe verification and rollback workflows.

Enforces atomic commits, safe branching, and clean git history. Use when pushing code, creating branches, or managing git workflows.

Use when profiling application performance, analyzing bottlenecks, or optimizing verification strategies (Core Web Vitals).

Use when simulating adversary attacks, performing red team operations, or mapping defenses to MITRE ATT&CK phases.

Audits code for security vulnerabilities, secret leaks, and sandbox violations. Use when "Mission Control" or "Ruthless Reviewer" is needed.

Use when analyzing vulnerabilities, prioritizing security risks, or auditing applications against OWASP Top 10.

Use when managing Linux servers, configuring process managers (systemd/PM2), or planning monitoring and scaling strategies.

Extracts key takeaways, summaries, and insights from video content including YouTube videos, tutorials, and presentations. Use when the user asks to "watch this video", "summarize this video", "extract key points from", or provides a video URL.

Use when routing complex user requests, selecting specialist agents automatically, or orchestrating multi-agent tasks.

Use when building MCP servers, designing tools and resources, or implementing Model Context Protocol standards.

Analyzes problems using deep logic, first principles, and graph of thoughts. Use when the user asks "Why?", "Analyze", or uses /think.

Creates new skills for the Antigravity agent environment. Use when the user asks to build a new skill, add automation capabilities, or extend agent functionality with specialized tasks.

Activates the Arc Persona (The Teacher) for explaining complex technical topics. Use when the user asks "How does X work?", "Explain Y", or uses the /learn command.

Use when writing documentation, creating READMEs, drafting API docs, or structuring project documentation for AI readability.

Use when building games, selecting game engines, designing game mechanics, or routing to specialized game development skills.

Use when optimizing content for AI search engines (GEO), targeting citations in ChatGPT/Claude/Perplexity.

Use when implementing internationalization (i18n), managing translations, handling RTL support, or detecting hardcoded strings.

Use when writing PowerShell scripts, managing Windows systems, or handling Windows-specific file paths and errors.

Use when optimizing content for search engines, improving Core Web Vitals, or implementing E-E-A-T principles.

Use when managing brand consistency, defining design tokens, enforcing tech stack rules, or establishing voice/tone guidelines.