53 boosters for "bun" — open source, verified from GitHub, ready to install
Refero gives agents taste and product evidence. Use it before design work instead of relying on generic model knowledge. Refero has three research layers:
When reviewing or writing code, ensure:
Use this skill to produce transparent, source-grounded fact-checking work. The goal is not to sound certain; the goal is to show exactly what was checked, what evidence supports each conclusion, and where uncertainty remains.
"name": "workflow-audit", "description": "SwiftUI workflow audit — find dead ends, broken promises, and UX friction. Bundled with a phased plan generator.", "name": "Terry Nyberg"
Two tiers: hooks handle automatic context flow (surfacing, extraction, compaction survival). MCP tools handle explicit recall, write, and lifecycle operations. Three instances for neural inference. The wrapper defaults to . All three models auto-download via if no server is running (Metal on Appl
"name": "swe-interview-coach", "description": "SWE interview prep — behavioral (STAR story bank, company-tailored mocks, delivery drills, debriefs), system design (canonical walkthroughs, graded mocks on a shared local Excalidraw canvas, practice sessions, real-interview debriefs), and coding (DSA p
You are a writing editor that strips AI-isms from Malaysian Bahasa Melayu writing. Content AI dalam BM ada "accent" sendiri, yang pembaca Malaysia boleh spot dalam 3 saat je. Kerja kau, buang accent tu, supaya tulisan bunyi macam manusia Malaysia betul-betul tulis, bukan bot. Detect the language of
A mandatory human escalation agent that intercepts all errors and uncertainties across other agents to ensure human oversight. Useful for safety-critical workflows requiring explicit human approval before proceeding.
"name": "claude-legal", "name": "codearranger", "url": "https://github.com/codearranger"
"description": "Agent identity framework - don masques to adopt temporary cognitive identities"
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "research-os", "description": "Bundled plugins with shared context for research including vision planning, experiment planning and spec- and test-driven implementation workflows.",
LmDotnetTools provides C# coding style rules and conventions for Windsurf, covering namespace declarations, naming conventions, formatting, and code organization to maintain consistency across .NET projects.
This Cursor rule guides developers to use Bun as their primary JavaScript/TypeScript runtime instead of Node.js, npm, and common build tools. It benefits teams standardizing on Bun for faster development and simplified tooling.
Cursor rules template for Bun + MCP server projects that documents Bun utility APIs and version management. Useful for developers building TypeScript projects with Bun runtime in Cursor IDE.
QCO is a lightweight Next.js e-commerce starter kit optimized for Windsurf, providing developers with pre-configured best practices for modern stack components (Drizzle ORM, tRPC, Better Auth, Tailwind). It accelerates e-commerce project setup by eliminating boilerplate configuration for data fetching, validation, and backend communication.
"name": "church-of-code", "description": "The Church of Code scripture — a ranked hierarchy of commandments, articles of faith, abominations, and daily offices, bundled as a Claude Code skill in three context-size variants.", "name": "Tom Mornini",
This Cursor rule enforces Bun as the default runtime and package manager, automatically guiding developers to use Bun commands instead of Node.js, npm, or other tools. Developers actively using or migrating to Bun will find this invaluable for consistent toolchain decisions.
SkillGuard is a security reviewer for Claude/Cursor Skills that detects prompt injection, tool injection, data exfiltration, and unsafe automation risks. It's essential for developers and organizations installing or developing AI skills to ensure safe, policy-compliant code execution.
A specialized consultant agent for monorepo architecture, workspace dependencies, and build orchestration that helps TypeScript and Bun developers design, analyze, and troubleshoot complex multi-package projects without making direct modifications.
Bootstrapp automates Swift package project instantiation from template bundles by collecting and validating user parameters. Developers building Swift packages can use this to quickly scaffold projects with consistent configurations.
Ifcli MCP Server enables developers to chat with multiple AI providers (OpenAI, DeepSeek, OpenRouter, Ollama) directly from the CLI, supporting both standard and reasoning models through a unified interface.
Hono skill teaches developers the key patterns and APIs specific to the Hono web framework, helping them avoid Express-style mistakes and leverage Hono's context-based, async-first design across multiple runtimes.
An LLM-optimized TickTick task management MCP server that reduces token costs by 70% through intelligent time handling, enabling efficient AI-assisted task automation for productivity-focused developers and AI assistants.
Obsidian Booster enables AI assistants to read, write, search, and manage Obsidian vault notes directly from Claude Code, streamlining note management, task tracking, and incident documentation workflows.
