115 boosters for "har" — open source, verified from GitHub, ready to install
  
Enables concurrent investigation of multiple independent tasks by dispatching separate agents to each problem domain, saving time on parallel debugging and testing workflows.
The xlsx skill enables Claude to work with spreadsheet files—opening, editing, creating, cleaning, and converting .xlsx, .xlsm, .csv, and .tsv files. It's essential for users who need programmatic spreadsheet manipulation without leaving their AI assistant.
Zhihu Strategist is an AI agent that helps marketers and brands build authority on Zhihu (知乎), China's largest knowledge-sharing platform, through expert question-answering and thought leadership strategies. It's ideal for companies and professionals targeting Chinese audiences who want to establish credibility through authentic expertise sharing.
Document Generator is an AI agent that creates professional PDF, PPTX, DOCX, and XLSX files programmatically with proper formatting and data visualization. Developers and business users benefit from automating document creation workflows without manual formatting.
A specialized agent for healthcare companies marketing in China, providing expert review of pharmaceutical, medical device, and health supplement content against Chinese advertising and medical regulations. Ideal for enterprises, agencies, and platforms needing compliance assurance in China's highly regulated healthcare marketing landscape.
Identity Graph Operator ensures all agents in a multi-agent system resolve entities to the same canonical identity deterministically, even with concurrent writes. Developers building multi-agent systems benefit from consistent entity resolution without duplication or conflicts.
Cursor rules that provide AI coding agents with guidance for developing the Streamlit library itself (backend, frontend, protobufs), rather than building Streamlit applications.
Oh My Opencode is an AI agent harness that provides multi-model orchestration, parallel background agents, and advanced code analysis tools for Claude Desktop and Claude Code. It benefits developers building sophisticated AI-powered applications who need orchestrated agent coordination and deep code understanding capabilities.
Matchms enables mass spectrometry data processing and analysis with support for multiple file formats, spectral similarity calculations, and metadata harmonization. This booster is essential for metabolomics researchers, bioinformaticians, and data scientists working with MS/MS datasets.
Use MCP to execute JavaScript in Figma files via the Plugin API. All detailed reference docs live in . Before anything, load plugin-api-standalone.index.md to understand what is possible. When you are asked to write plugin API code, use this context to grep plugin-api-standalone.d.ts for relevant t
Use this skill to create or update full-page screens in Figma by reusing the published design system — components, variables, and styles — rather than drawing primitives with hardcoded values. The key insight: the Figma file likely has a published design system with components, color/spacing variabl
Sora enables Claude Code users to generate, remix, and manage AI videos directly through OpenAI's video API. Developers building products with video content (demos, marketing, UI mocks) benefit from integrated video generation workflows.
Enables AI assistants to programmatically create and edit PowerPoint presentations using PptxGenJS with layout helpers and validation utilities. Developers and content creators benefit from automating slide deck generation, modification, and troubleshooting.
The 'harden' booster helps developers make their interfaces production-ready by systematically addressing error handling, internationalization, text overflow, and edge cases. It's ideal for teams building robust web applications that need to handle real-world usage scenarios.
"name": "baoyu-skills", "name": "Jim Liu (宝玉)", "email": "junminliu@gmail.com"
Deep Agents is a system prompt for building intelligent agent assistants with planning, filesystem, and sub-agent capabilities across Claude and other AI platforms. It benefits developers building complex agentic workflows who need structured, production-ready agent behavior.
Train object detection, image classification, and SAM/SAM2 segmentation models on managed cloud GPUs. No local GPU setup required—results are automatically saved to the Hugging Face Hub. Use this skill when users want to: Helper scripts use PEP 723 inline dependencies. Run them with :
Train language models using TRL (Transformer Reinforcement Learning) on fully managed Hugging Face infrastructure. No local GPU setup required—models train on cloud GPUs and results are automatically saved to the Hugging Face Hub. Use this skill when users want to: Use Unsloth () instead of standard
Hugging Face Paper pages (hf.co/papers) is a platform built on top of arXiv (arxiv.org), specifically for research papers in the field of artificial intelligence (AI) and computer science. Hugging Face users can submit their paper at hf.co/papers/submit, which features it on the Daily Papers feed (h
Run any workload on fully managed Hugging Face infrastructure. No local setup required—jobs run on cloud CPUs, GPUs, or TPUs and can persist results to the Hugging Face Hub. Use this skill when users want to: When assisting with jobs:
This skill is for running evaluations against models on the Hugging Face Hub on local hardware. It does not cover: If the user wants to run the same eval remotely on Hugging Face Jobs, hand off to the skill and pass it one of the local scripts in this skill.
A skill for fine-tuning and training language models on Hugging Face's cloud GPU infrastructure using TRL, supporting SFT, DPO, GRPO methods and GGUF conversion for local deployment. Developers and ML engineers working with cloud-based model training benefit from this comprehensive guidance.
This skill enables users to run Python workloads, Docker jobs, and GPU-intensive tasks on Hugging Face's managed infrastructure without local setup. It's valuable for ML engineers, data scientists, and developers needing cloud compute for training, inference, and batch processing.
