Engineering excellence for builders. Use when: writing code, making technical decisions, refactoring, reviewing, completing implementation work.
EnglishWrite rigorous evals for LLM agents, multi-agent systems, skills, MCP servers, and prompts. Use when: building test suites, measuring agent effectiveness, evaluating coordination, or choosing eval frameworks. Covers: DeepEval, Braintrust, RAGAS, precision/recall, F1, task completion, pass@k, iterative metrics, multi-agent coordination.
EnglishSvelte-first frontend experience engineering. Use when building interactive experiences: animations, 3D/WebGL, scrollytelling, data visualization, or any visual/interactive work. Covers GSAP, Threlte 8, D3, Layer Cake, PixiJS, Melt UI, typography, and design patterns. Triggers on (1) animation/motion design, (2) 3D/WebGL work, (3) scroll-driven storytelling, (4) data visualization, (5) headless UI, (6) graphics/sprites.
EnglishTeaching and information sharing across all contexts. Use when: writing docs, explaining concepts, making presentations, teaching in conversation, curating documentation, technical writing for impact, creating diagrams for explanation (Mermaid, D2, C4).
EnglishBuild Claude cognitive extensions with quality methodology. Composes with plugin-dev and agent-sdk-dev. Use when: creating skills/hooks/agents/commands/MCP/plugins, need quality validation, building for the 1337 marketplace.
EnglishJVM runtime analysis. Use when: profiling JVM performance, tuning GC, debugging memory leaks, finding dead code with production data. Not for general Java development or syntax questions.
EnglishElite 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).
EnglishRust production patterns. Use when: building Rust CLI, backend, frontend, or native apps. Covers axum, tonic, sqlx, Leptos, Dioxus, Tauri, clap, tokio. Production gotchas (blocking, cancellation, mutex), ownership decisions, crate selection. Routes to specialized domains: embedded, FFI, proc-macros, proxies/data-plane.
EnglishAI image and video generation. Use when: creating artwork, images, illustrations, animations, videos, visual assets, AI art generation, style guidance, choosing image or video models, text-in-image.
English
AGENT SKILLS ATLASIncludes Build Core, Build Eval, Build Experience, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Build Core
Engineering excellence for builders. Use when: writing code, making technical decisions, refactoring, reviewing, completing implementation work.
Build Eval
Write rigorous evals for LLM agents, multi-agent systems, skills, MCP servers, and prompts. Use when: building test suites, measuring agent effectiveness, evaluating coordination, or choosing eval frameworks. Covers: DeepEval, Braintrust, RAGAS, precision/recall, F1, task completion, pass@k, iterative metrics, multi-agent coordination.
Build Experience
Svelte-first frontend experience engineering. Use when building interactive experiences: animations, 3D/WebGL, scrollytelling, data visualization, or any visual/interactive work. Covers GSAP, Threlte 8, D3, Layer Cake, PixiJS, Melt UI, typography, and design patterns. Triggers on (1) animation/motion design, (2) 3D/WebGL work, (3) scroll-driven storytelling, (4) data visualization, (5) headless UI, (6) graphics/sprites.
Build Explanations
Teaching and information sharing across all contexts. Use when: writing docs, explaining concepts, making presentations, teaching in conversation, curating documentation, technical writing for impact, creating diagrams for explanation (Mermaid, D2, C4).
Build Extension Builder
Build Claude cognitive extensions with quality methodology. Composes with plugin-dev and agent-sdk-dev. Use when: creating skills/hooks/agents/commands/MCP/plugins, need quality validation, building for the 1337 marketplace.
Build Jvm Analysis
JVM runtime analysis. Use when: profiling JVM performance, tuning GC, debugging memory leaks, finding dead code with production data. Not for general Java development or syntax questions.
Build Kotlin
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).
Build Rust
Rust production patterns. Use when: building Rust CLI, backend, frontend, or native apps. Covers axum, tonic, sqlx, Leptos, Dioxus, Tauri, clap, tokio. Production gotchas (blocking, cancellation, mutex), ownership decisions, crate selection. Routes to specialized domains: embedded, FFI, proc-macros, proxies/data-plane.
Visual Creation
AI image and video generation. Use when: creating artwork, images, illustrations, animations, videos, visual assets, AI art generation, style guidance, choosing image or video models, text-in-image.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Build Core skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.