347 boosters for "base" — open source, verified from GitHub, ready to install
DyNote 是面向 Codex 这类 Agent 的抖音学习工具，不是一次性摘要器。核心原则是“数据资产先行，学习笔记后置”：先把字幕/转写、评论、元数据和 AI 快读沉淀为可复用资产，再按用户需求生成可追溯的学习笔记、总结和写作材料。默认目标不是字幕工程文件，而是先落一份原始数据包：、、、、、、，并用 归档可复用资产。默认把独立字幕轨或本地自动语音识别转写当作事实主干；当转写密度低、任务需要画面理解或用户只要快速筛选时，再用已登录抖音网页版的“问AI / 识别画面”补充，豆包只作为抖音 AI 不可用时的备用快读或待核验假设。 联网或登录态操作必须先使用 。不要读取、复制或打印 Cooki
Opportunity-Solution Trees help product teams structure discovery work and connect customer needs to solutions using Teresa Torres's framework. Useful for product managers, researchers, and developers deciding what to build and validating assumptions.
A CLI booster for managing Gitea repositories, issues, and pull requests directly from the terminal. Useful for developers who prefer command-line workflows or need to automate Gitea operations in scripts.
A Prisma/PostgreSQL database management skill that helps developers modify Motivia's schema, add tables/fields/relations, and execute migrations. Essential for anyone working on the Motivia project's data layer.
"name": "prism-mcp-server", "mcpName": "io.github.dcostenco/prism-mcp", "description": "The Mind Palace for AI Agents — persistent memory (SQLite/Supabase), behavioral learning & IDE rules sync, multimodal VLM image captioning, pluggable LLM providers (OpenAI/Anthropic/Gemini/Ollama), OpenTelemetry
"name": "firecrawl-workflows", "displayName": "Firecrawl Workflows", "description": "Outcome-focused Firecrawl workflow skills for research, SEO audits, QA, knowledge bases, lead lists, dashboard reporting, shopping, and design-system extraction.",
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "opentrace-oss", "description": "Knowledge graph tools for exploring system architecture, code structure, and service dependencies",
"description": "Ukrainian theatrical absurd communication style based on Les Podervyansky's works. Includes MYTETSMODE and DEDMODE for epic dramatic interactions.", "name": "Roman Rader", "email": "antigluk@gmail.com"
This booster automates the creation and verification of date-based folder hierarchies in Google Drive for the SNMG18 Working Docs project, helping teams stay organized with consistent month and day folder structures.
PRPM Testing Patterns provides Cursor-specific guidance on testing strategies and best practices for the Prompt Package Manager codebase using Vitest, including a test pyramid structure and concrete code examples for developers building or maintaining PRPM.
"name": "pinion-os", "description": "On-chain AI skills via x402 micropayments on Base", "homepage": "https://github.com/chu2bard/pinion-os",
An autonomous agent designed to handle project design and coding tasks end-to-end without human intervention, leveraging Claude's code execution capabilities. Useful for developers seeking automated development workflows and system introspection.
Run CI checks locally, mirroring the GitHub Actions workflow in . Assume all tools (stack, coqc, coq_makefile) are already installed — no Docker or opam setup needed. Do NOT use (that's only for CI containers). All commands must be run from the workspace root using relative paths. The argument is:
trace-mcp is a framework-aware code intelligence MCP server. It exposes 120+ tools that return semantic, structured results over a cross-language dependency graph. When trace-mcp is available, it is almost always cheaper and more accurate than native file tools. Activate this skill whenever you need
"name": "manim-skill", "description": "Claude Code Skill for creating mathematical animations using Manim Community Edition. Plan, code, render, and iterate on 3Blue1Brown-style videos.", "name": "Yusuke Miyashita"
std::string to_uppercase(const std::string& input);
"name": "@touchskyer/memex", "mcpName": "io.github.iamtouchskyer/memex", "version": "0.1.29",
Generate production-grade animations using Motion.dev following Apple/Jon Ive principles: ❌ Don't use for: Determine project context and animation goals:
You are tasked with retrieving relevant knowledge from the Obsidian vault using multi-layer semantic search. 1. First Layer - Initial Search: 2. Second Layer - Direct Associations:
Use this skill to operate as a tool-driven RLM workflow for large repositories. 1. Verify prerequisites: 2. Run a baseline audit:
Suggest additional team members based on the user's outcomes and selected mode. The lead and facilitator are always included. Keep teams to 3-5 members total. Up to 8 for complex multi-domain work. All members except the lead are read-only. Present your suggestion.
Return the following mode definition verbatim to the team lead. Do not summarize or interpret — the lead needs the full specification. You are the team lead. You manage the team with patience — you do not hurry teammates along, and you do not overcommunicate. You coordinate the team, relay user feed
Ask an opening question to gauge where the user stands: Use these question types, escalating from simple to complex: When the user arrives at the answer, ask them to summarize:
An MCP server that enables Claude to maintain persistent long-term and short-term memory across conversations using a local SQLite database. Developers and AI agents benefit from enhanced context retention and conversation continuity.
