893 boosters for "ci" — open source, verified from GitHub, ready to install
Finds the best models for a task by querying official HF benchmark leaderboards, enriching results with model size data, filtering for what fits on the user's device, and returning a comparison table with benchmark scores.
Trackio is an experiment tracking library for logging and visualizing ML training metrics. It syncs to Hugging Face Spaces for real-time monitoring dashboards. Use in your training scripts to log metrics: → See references/logging_metrics.md for setup, TRL integration, and configuration options.
Rules and patterns for ML demos on Hugging Face Spaces with ZeroGPU hardware. Covers , duration and quota tuning, process isolation, the CUDA availability model, concurrency safety, and CUDA build constraints. This skill is for Gradio SDK Spaces using ZeroGPU hardware. Docker and Static Spaces canno
Fast, calibration-free weight quantization supporting 8/4/3/2/1-bit precision with multiple optimized backends. HQQ uses to define quantization parameters: The core quantized layer that replaces :
A system prompt for Claude Code that enforces defensive security practices and provides CLI guidance, designed to help developers safely use Claude for software engineering tasks while preventing misuse.
This skill automates the process of adding, extracting, and managing evaluation results in Hugging Face model cards, supporting multiple data sources including Artificial Analysis API and custom evaluations with vLLM/lighteval. It's valuable for ML practitioners and model maintainers who need to track and display model performance metrics.
Trackio is an ML experiment tracking library that integrates with Hugging Face to log metrics, visualize training progress, and trigger alerts during model development. It's useful for ML engineers and researchers who need real-time monitoring and experiment management.
A skill that generates reusable command-line scripts for automating Hugging Face API interactions, useful for developers who need to repeatedly fetch, process, or chain API calls.
1. Fetch homepage HTML (curl or WebFetch) 2. Detect business type (SaaS, Local, E-commerce, Publisher, Agency, Other) 3. Extract key pages from sitemap.xml or internal links (up to 50 pages)
Heuristic scoring (no AI key configured).
You are the ZCF Template Engine Specialist for the ZCF (Zero-Config Code Flow) project.
You are the ZCF i18n Specialist for the ZCF (Zero-Config Code Flow) project.
You are the ZCF DevOps Engineer for the ZCF (Zero-Config Code Flow) project.
You are the ZCF Testing Specialist for the ZCF (Zero-Config Code Flow) project.
You are the TypeScript CLI Architecture Specialist for the ZCF (Zero-Config Code Flow) project.
You are the ZCF Tools Integration Specialist for the ZCF (Zero-Config Code Flow) project.
Post the following two comments to the PR specified by the user ($ARGUMENTS), in the repository on GitHub. They need to be posted separately because otherwise it gets too long and fails to trigger correctly.
当用户对已有前任 Skill 说以下内容时，进入进化模式： 本 Skill 运行在 Claude Code 环境，使用以下工具： 本 Skill 在生成和运行过程中严格遵守以下规则：
ByteRover CLI () - Interactive REPL with React/Ink TUI oclif v4, TypeScript (ES2022, Node16 modules, strict), React/Ink (TUI), Zustand, axios, socket.io, Mocha + Chai + Sinon + Nock
Official MCP server enabling Claude to interact directly with Notion workspaces through the Model Context Protocol. Essential for developers and knowledge workers who want to automate Notion operations or integrate Notion data into AI-powered workflows.
When reviewing code, focus on: Always prioritize security vulnerabilities and performance issues that could impact users. Always suggest changes to improve readability and testability. For example, this suggestion seeks to make the code more readable, reusable, and testable:
A Bash CLI wrapper for the EODHD financial data API designed for OpenClaw agents, with built-in secrets management and secure deployment practices. Useful for developers building open-source integrations that need stateless API access without credential exposure.
Yielding Bear provides a single unified API that routes every LLM request to the cheapest capable model across 16+ providers — saving 60-80% vs calling OpenAI, Anthropic, or Google directly. 1. Get an API key at https://yieldingbear.com/api 2. Set environment variable:
