By moonbitlang
Develop MoonBit apps by binding C libraries via native FFI with extern declarations, stubs, configs, callbacks, and string conversions; extract formal API specs and organized test suites from implementations for spec-driven testing; resolve language, compiler, package, toolchain, backend, and FFI issues using fresh docs and IDE sources.
npx claudepluginhub moonbitlang/skills --plugin moonbit-skillsGuide for writing MoonBit bindings to C libraries using native FFI. Use when adding extern "c" declarations, writing C stubs with moonbit.h, configuring native-stub and link.native in moon.pkg or moon.pkg.json, choosing
Extract formal spec and comprehensive test suites from existing MoonBit implementations. Use when asked to "extract spec from implementation", "generate tests from code", or "create spec-driven tests for existing package". Analyzes existing code to produce spec.mbt with `declare` keyword stubs and organized test files (valid/invalid).
Use this skill when the user needs help solving MoonBit language, code, compiler diagnostic, package, toolchain, backend, FFI, test, or "does MoonBit have X?" questions. Use it even when MoonBit is only implied by .mbt files, moon.mod.json, moon.pkg.json, moon commands, wasm/js/native targets, or mooncakes packages. This skill helps choose the right MoonBit source of truth, discover APIs with moon ide, avoid stale assumptions, and validate fixes.
MoonBit code generation best practices. Use when writing MoonBit code to avoid common AI mistakes with syntax, tests, and benchmarks.
Integrated Rust development skills for multiple domains (UI, Robotics, etc.)
Meta-plugin that installs all skills from all plugins in the marketplace
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Share bugs, ideas, or general feedback.
Agent Skills are folders of instructions, scripts, and resources that AI agents can discover and use to perform at specific tasks. Write once, use everywhere.
Clone the repository with submodules so every bundled skill is available locally:
git clone --recurse-submodules https://github.com/moonbitlang/skills.git
cd skills
If you already cloned the repository without submodules, initialize them afterward:
git submodule update --init --recursive
Each skill lives in its own directory under skills/.
For agents that can install skills from natural language prompts, such as Codex, Claude, Gemini CLI, OpenCode, and similar tools, ask the agent to install the skills listed in this repository:
install the skills listed in this repo: https://raw.githubusercontent.com/moonbitlang/skills/refs/heads/master/.claude-plugin/marketplace.json
Run /plugin in the CLI, and select Add Marketplace. Input moonbitlang/skills to add this marketplace.
Then install the moonbit-skills plugin from the marketplace. The plugin exposes the bundled skills from the skills/ directory.
Run in the CLI: $skill-installer install <skill-name> by submodule from https://github.com/moonbitlang/skills.git
Or, run $skill-installer install all skills listed in https://raw.githubusercontent.com/moonbitlang/skills/refs/heads/master/.claude-plugin/marketplace.json to install all skills in this repo.
The license of an individual skill can be found directly inside the skill's directory inside the LICENSE.txt file.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim