153 boosters for "rl" — open source, verified from GitHub, ready to install
A hands-on course teaching developers how to build AI-powered agents using Foundry Local with modern SDK patterns, function calling, and hybrid cloud designs. Benefits beginners and intermediate developers wanting to prototype agentic applications quickly on edge devices.
This folder contains a digital identity. Your job is to embody it. 1. SOUL.md — Identity, worldview, opinions, background 2. STYLE.md — Voice, sentence structure, vocabulary, anti-patterns
"name": "adversarial-spec", "description": "Iteratively refine product specs through multi-model debate until consensus. Claude actively participates alongside GPT, Gemini, Grok, and other models. Includes interview mode, early agreement verification, and optional Telegram integration.", "repository
Web 端视觉设计 SKILL。两阶段工作流：先出规范（DESIGN.md），再出代码。 DESIGN.md 是显式文件产物，保存到项目目录，可跨项目复用、可手动修改、可给其他工具消费。 1. 项目里已经有 DESIGN.md 了吗？→ 有则沿用/修改/重建
Given a URL, return its main content as clean Markdown — headings, links, images, lists, code blocks all preserved. Always try one method per URL — don't cascade blindly. Pick the right one upfront. is the directory where this SKILL.md lives. Resolve it before calling the script.
Automates GitHub pull request reviews by analyzing code for bugs, security issues, performance problems, and test coverage gaps, then posts findings directly to GitHub. Essential for engineering teams using Claude in their development workflow.
"name": "ast-index", "version": "3.48.0", "description": "Fast code search for Android/Kotlin/Java, iOS/Swift/ObjC, Dart/Flutter, TypeScript/JavaScript, Rust, Ruby, C#, PHP, Python, Go, Perl, C++, Protocol Buffers, and WSDL/XSD projects",
PR'i olusturmaktan merge'e kadar tum sureci otonom yonet. CI basarisiz olursa duzelt, review feedback gelirse uygula, butce asarsa dur.
This MCP server enables developers to deploy HTML content directly to EdgeOne Pages and retrieve publicly accessible URLs programmatically. It's ideal for AI assistants and developers who need to quickly publish web content through Claude or automated workflows.
A world-builder's best friend!
A system prompt for training AI agents on terminal/coding tasks using GRPO, enabling autonomous task completion in containerized Linux environments. Ideal for developers building advanced AI coding assistants and automation systems.
Before writing any code, read CONTRIBUTING.md and .github/copilot-instructions.md.
You solve problems by decomposing them: break big tasks into smaller ones, delegate to sub‑agents, combine results. This works for any task — coding, analysis, refactoring, generation, exploration. Your original prompt is also available as a file at — use it when you need to manipulate the question
Manage bookmarks via Raindrop.io REST API. User must have env var set. If not configured, instruct them to: 1. Create app at https://app.raindrop.io/settings/integrations
This skill encodes the complete design specification for professional business presentations — a consultant-grade PowerPoint framework based on McKinsey design principles. It includes: All specifications have been refined through iterative production feedback to ensure visual consistency, profession
"version": "0.10.0", "description": "AI agents on autopilot - define in markdown, run on cron, CI/CD, or serverless", "license": "Apache-2.0",
A fully autonomous AI research agent that ingests sources into Google NotebookLM, runs deep web research, synthesizes knowledge through cited Q&A and 9 downloadable artifact types, creates polished content drafts, and optionally publishes to social platforms.
1. * - Interactive elements, headings (reflects user perception) 2. - Form controls with labels 3. * - Inputs without labels
"name": "tensorlake", "description": "Tensorlake SDK for agent sandboxes and sandbox-native orchestration. Use when building AI agents that need sandboxed execution environments, isolated tool calls, or durable workflow orchestration.", "author": "TensorLake",
uni-cli is a unified command-line interface that enables AI agents to seamlessly interact with 25+ services (messaging, productivity, research, utilities) through a consistent pattern. Developers and AI builders benefit from simplified multi-service integration without learning individual APIs.
A practical guide for deploying serverless Python applications on Modal, enabling developers to run GPU-accelerated AI/ML workloads, web APIs, and batch jobs with minimal infrastructure configuration.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
"name": "matryoshka-rlm", "version": "0.2.17", "description": "Recursive Language Model - Process documents larger than LLM context windows",
Native SQL extensions for GoldenMatch ().
