agustinusnathaniel

Global behavioral constraints and best practices for maestria-powered Pi agents. Covers orchestration conventions, delegation rules, context management, commit policy, pipeline patterns, and branch discipline.

Maestria agent orchestration dispatcher. Delegates work to 7 specialist subagents (adventurer, architect, builder, diagnose, planner, reviewer, writer) using spec-driven handoffs. Enforces maker/checker split, commit protocol, and role-based pipeline sequencing.

Methodology + delegation + swarm usage for the maestria workflow

Codebase reconnaissance agent for deep code understanding. Maps unknown territory - traces call chains, maps module relationships, generates structured reports for downstream specialists. Use for: understanding unfamiliar code, tracing dependencies, gathering context before implementation, investigating module structures. One role per session: exploration only - never implement or design.

Architecture decisions using decision matrices and ADRs. Evaluates options with weighted criteria, clarifies business context first. Use for: technology choices, implementation approaches, trade-off analysis.

Focused implementation agent for atomic tasks. Executes one verifiable unit of work with minimal context. Use for: targeted fixes, feature implementation, refactors, adding tests.

Systematic 6-step regression tracing. From error message to root cause to prevention. Use for: cryptic errors, regressions, production bugs.

Create detailed implementation plans with phased dependencies, timelines, and success criteria. Breaks down complex features into verifiable milestones. Use for: complex features requiring multi-phase execution, when the plan needs review before building.

Scaffold new JS/TS projects from curated starter templates pre-configured with Biome, TypeScript strict mode, GitHub Actions CI, VS Code settings, and AI agent skills. Use when user wants to create a new project, scaffold an app from a template, or mentions "create-xtarter-app", "npx create-xtarter-app", "scaffold", "starter template", or a template name like "next-tailwind", "vite-chakra", "vite-tailwind", "vite-hero", or "next-chakra".

Apply production-grade conformance configurations (linting, type checking, CI, editor settings, AI skills, release tooling) to JS/TS projects. Scans package.json and config files to auto-detect framework, bundler, and styling, then resolves applicable tasks. Use when user mentions "xtarterize", "conformance", "setup linting", "add CI", "configure project", "init xtarterize", or any task name like "lint/biome", "ts/strict", or "ci/workflow".

Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for", "read the source of", "how does X work internally", "get the implementation of", "opensrc path", or any task requiring access to dependency source code beyond types and docs.

Compact the current conversation into a handoff document for another agent to pick up.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Replace with description of the skill and when Claude should use it.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

HeroUI Native component library for React Native (Tailwind v4 via Uniwind). Use when building mobile UIs with HeroUI Native — creating Buttons, Cards, TextFields, Dialogs; installing heroui-native; configuring dark/light themes; or fetching component docs. Keywords: HeroUI Native, heroui-native, React Native UI, Uniwind, mobile components.

Uniwind — Tailwind CSS v4 styling for React Native. Use when adding, building, or styling components in a React Native project that uses Tailwind with className. Triggers on: className on RN components, Tailwind classes in RN, global.css with @import 'uniwind', withUniwindConfig, withUniwind, metro.config.js with Uniwind, useResolveClassNames, useCSSVariable, useUniwind, dark:/light: theming, platform selectors (ios:/android:/native:/web:/tv:), data-[prop=value], responsive breakpoints (sm:/md:/lg:), tailwind-variants, tv() variants, ScopedTheme, Uniwind.setTheme, Uniwind.updateCSSVariables, @theme, @utility, @variant, CSS variables in RN, colorClassName, tintColorClassName, contentContainerClassName, Uniwind Pro (animations, transitions, shadow tree, native insets), safe area utilities, gradients, hairlineWidth(), fontScale(), pixelRatio(), light-dark(), OKLCH, cn, tailwind-merge, HeroUI Native, react-native-reusables, Gluestack. Does NOT handle migration — use migrate-nativewind-to-uniwind skill.

Configure @tanstack/devtools-vite for source inspection (data-tsd-source, inspectHotkey, ignore patterns), console piping (client-to-server, server-to-client, levels), enhanced logging, server event bus (port, host, HTTPS), production stripping (removeDevtoolsOnBuild), editor integration (launch-editor, custom editor.open). Must be FIRST plugin in Vite config. Vite ^6 || ^7 only.

Vite+ skill for development workflow and CLI operations. Use this skill to route user requests to the appropriate bundled Vite+ docs.

Ultracite is a zero-config linting and formatting preset for JavaScript/TypeScript projects. Use when: (1) Setting up or initializing Ultracite in a project (ultracite init), (2) Running linting or formatting commands (check, fix, doctor), (3) Writing or reviewing JS/TS code in a project that uses Ultracite — to follow its code standards, (4) Troubleshooting linting/formatting issues, (5) User mentions 'ultracite', 'lint', 'format', 'code quality', or 'biome/eslint/oxlint' in a project with Ultracite installed.

Make architecture decisions using decision matrices and iterative refinement. Use when comparing implementation approaches, evaluating trade-offs, selecting technology, or facing multiple viable paths. Prioritizes business context over technical purity — clarifies the problem before deciding, presents options with trade-offs, documents decisions as lightweight ADRs.