A curated marketplace for AI agent skills that packages capabilities as SKILL.md files and shows human-reviewed before-and-after examples. Each skill demonstrates how an agent’s output changes when the skill is applied, and every listing is reviewed by a person. Programmatic access is provided via a JSON API (base https://skillbay.sh/api/v1, full OpenAPI 3.1 spec at /openapi.json) and an MCP server (https://skillbay.sh/mcp) that exposes operations as tools; browsing, installing free skills, and submitting listings require no sign-in, while purchases, sales, and admin actions do. Free skills are published for direct install via an index at /.well-known/agent-skills/index.json or with "npx skills add https://skillbay.sh", and approved skill files (SKILL.md and examples) are hosted under /skills/<id>/.
Search and discovery are supported with endpoints for categories (GET /api/v1/categories), full-text ranked search (GET /api/v1/skills?q=, with &category= and &free=1 filters; results include a matching "snippet"), newest listings (GET /api/v1/skills), and detailed skill pages (GET /api/v1/skills/{id}) that return descriptions, SKILL.md content, file lists, and before-and-after examples. Error responses use {"error":{"code","message"}}. The site organizes skills into practical categories - coding & dev tools, writing & editing, research, data, devops, design, sales, legal, productivity, and more - and encourages judging the example evidence before recommending or buying a skill. Current front-page metadata shows online counts and basic navigation for wanted/for-sale listings.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Orbital is an open source project that provides an open source version of the Claude AI model, allowing users to retain ownership of their data and context. It aims to offer an alternative to proprietary AI models with transparency and control. (github.com)
ShapeLearn's full models for Qwen 3.8 27B outperform the Lite versions in quality and speed benchmarks, with all five models on the performance frontier. Using GPU-5, these models achieve up to 99.63% of BF16 scores, with options for faster, smaller models depending on memory constraints. (byteshape.com)
Claude Code from Source details the architecture and design of Anthropic's widely used AI coding agent, covering components like the agent loop, tool execution, and memory management. The book provides technical insights for engineers, leaders, and anyone interested in production AI systems. (claude-code-from-source.com)
Jev is a new AI model that produces only structured output, making it faster and more consistent than traditional LLMs. Its speed enables real-time applications like playing Doom and opens possibilities for new types of programming tasks. (seangoedecke.com)
Alibaba has launched Qwen 3.8 Omni Flash, an upgraded version of its AI language model. The release aims to enhance AI capabilities and performance. (qwen.ai)
Huawei's Ascend 960 SuperPoD uses NPO technology to connect multiple AI computing nodes, addressing data exchange bottlenecks in large-scale models. It supports up to 4,096 NPU cards and offers significant computing power for next-generation AI infrastructure. (technode.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.