5,123 boosters — open source, verified from GitHub, ready to install
"description": "You say it, AutoCode ships it. 47 skills. Code to deployment in one session. I-Lang v3.0 powered.", "name": "I-Lang Research, Eastsoft Inc.", "url": "https://github.com/ilang-ai/autocode"
Provides quick-start guidance and code examples for integrating Upstash Vector, a high-performance vector database, into TypeScript applications. Developers building RAG systems, semantic search, or embedding-based features will benefit from this unified entry point.
"name": "forward-deployed-selling", "description": "Operating doctrine for AI-era enterprise sales. Use when an agent works on accounts, deals, outreach, coaching, or pipeline — any revenue-affecting decision.", "name": "Angel Armendariz",
"name": "mindmap-markmap-viewer", "description": "Turn Markdown outlines, notes, docs, or plans into an interactive mind map — a single self-contained HTML file that opens offline anywhere (markmap.js, white-on-dark, zoom/expand/export toolbar, context-preserving search).", "name": "Jaderson Vargas"
Every service needs a unique key from . Never use plain strings. Use . Note: type params FIRST, then key in second call. Use an explicit constructor effect and . Parameterized or reusable constructor functions should be named . Zero-arg constructor values may stay to avoid immediate IIFEs.
This file provides guidance to AI Agent when working with code in this repository. Pre-commit hooks: husky + lint-staged runs on and on . Full server-side rendering ( in astro.config.mjs). All pages are server-rendered by default. API routes must export .
"name": "montage-web", "description": "Wanted Lab Design System for Web", "name": "montage-web-guide",
A TypeScript boilerplate for building MCP servers with STDIO and HTTP transport support, designed to help developers quickly scaffold and extend their own Model Context Protocol integrations for Claude and other AI platforms.
"name": "seer-skill", "description": "Visual feedback capture for macOS app windows.", "repository": "https://github.com/w00ing/seer-skill",
Use this skill when the user gives a topic or keyword set and wants a local literature-harvesting workflow, not a one-off manual search. This skill is self-contained. The target project does not need to already contain: The bundled copies live under:
"name": "template-bridge", "description": "Unified superpowers+beads workflow + proactive template catalog (413+ specialist agents on-demand from claude-code-templates)", "name": "maslennikov-ig",
If anything is unclear or you want this tailored to specific agent roles (refactoring, feature, doc-only), tell me which role and I'll iterate.
do not run any npm commands until explicitly asked
Heuristic scoring (no AI key configured).
atris is a self-improving context system that provides structured agent rules and workflows for AI coding assistants like Cursor, enabling developers to maintain organized task management, code navigation, and communication standards across projects.
"name": "claude-code-superpowers", "description": "24 elite skills across 5 layers: discipline, domain expertise, intelligence, coordination, and execution. Turn Claude Code into a proactive engineering partner.", "name": "GadaaLabs",
A Godot game engine integration tool that enables Claude to launch the Godot editor, run projects, and capture debug output directly. Game developers using Claude for assistance can streamline their workflow by automating engine interactions.
零配置获取 A 股多维度量化数据，数据源自 恢恢量化。 所有脚本位于本 skill 目录下 ，用 Bash 工具运行： 盘后日报，覆盖赚钱效应、热门题材、连板天梯、游资龙虎榜、行业资金、焦点新闻。
A skill that counts atoms in chemical equations, determines balance status, and applies coefficients to balance unbalanced equations—useful for chemistry students, educators, and anyone learning stoichiometry.
A Cursor IDE rule set that enforces idiomatic Elixir coding standards and best practices, including functional programming patterns, code style conventions, and test structure guidelines. Beneficial for Elixir developers using Cursor who want consistent, high-quality code generation.
"""Function description Description of param1 Description of param2
is an eval workbench for agent skills. It runs a model in an isolated Docker directory, provides skills/references as normal workspace files, captures an agent trace, and grades deterministic local outcomes. Use this skill as the source of truth for authoring eval suites in this repo. Detailed sche
"description": "Ship software systematically: project lifecycle, TDD, parallel agents, code review, security auditing, and infrastructure validation", "email": "lgbarn@users.noreply.github.com"
"name": "use-agently", "description": "Use Agently CLI", "homepage": "https://use-agently.com",
