claude-1337

Engineering excellence for builders. Use when: writing code, making technical decisions, refactoring, reviewing, completing implementation work.

Modern terminal tools: ripgrep, fd, bat, eza, fzf, xh, jq, atuin. Use when: searching files, grepping patterns, viewing code.

Rust production patterns. Use when: building Rust systems. Covers ownership decisions, async gotchas, crate selection, domain knowledge (networking, embedded, WASM, FFI, proc-macros).

Elite Kotlin development patterns. Use when: writing Kotlin for backend (Ktor, Spring Boot), Android, Multiplatform. Covers coroutines, structured concurrency, Flow, scope functions, null safety, Java interop, testing (Kotest, MockK), benchmarking (kotlinx-benchmark).

JVM static and runtime analysis. Use when: finding dead code, optimizing Java/Kotlin apps, profiling, debugging memory leaks. Covers SootUp, Scavenger, async-profiler, JFR, ProGuard.

Build Claude extensions with quality methodology. Composes with plugin-dev and agent-sdk-dev for schemas. Use when: creating extensions, need quality validation, building for 1337 marketplace.

Documentation methodology. Feynman technique meets Diataxis. Use when: writing docs, tutorials, explanations, READMEs. Includes feynman agent.

Write rigorous evals for LLM agents, skills, MCP servers, and prompts. Use when: building test suites, measuring effectiveness, choosing frameworks. Covers: DeepEval, Braintrust, RAGAS, precision/recall, F1.

Frontend experience engineering. Use when: animations, 3D/WebGL, scrollytelling, data visualization, typography, color systems, design patterns. Covers Motion, GSAP, Three.js, R3F, Threlte, D3, OKLCH, fluid type.

AI image and video generation. Use when: Midjourney prompting, choosing image/video models, troubleshooting AI art, reference types, style transfer, text-in-image.

Architectural reasoning with The Guild. 13 specialized agents with orthogonal perspectives for multi-viewpoint architecture review.

Prompt engineering for different model architectures. Use when: writing prompts for reasoning models (o1, Gemini Deep Think) vs autoregressive models (Claude, GPT-4). Covers search space constraints, scenario injection, triangulation.