SuperAPI AI Directory
Partner with us中文AI newsFavorites

All AI tools

35,721 results · Page 866 of 993

SkaleAgents

AI coding

SkaleAgents is an AI review tool for infrastructure and pre-deployment scenarios. It can connect to the AI clients you already use, inspect application and infrastructure configurations, and provide suggested changes. It supports integration via MCP (Model Context Protocol) with editors or chat clients such as Cursor, Claude Code, Claude Desktop, ChatGPT, and Codex, allowing review results to return to the same conversation. Users can also browse public bots and a prompt library to bring expert prompts into their own assistants; or submit IaC text as an audit task, view findings in a Watchtower session, and set up scheduled audits by cron expression and time zone, with optional webhooks to receive completion or failure notifications. The website provides interactive examples that require no account, for experiencing how sample checks are updated; the examples do not represent real audit results.

Read more

skill-optimizer

AI agents

skill-optimizer is a tool for benchmarking, evaluating, and optimizing AI agent skills (Agent Skill), developed by fastxyz and open-sourced on GitHub. It offers two usage modes: a Docker workbench and an Agent Skill: you can install the skill-optimizer skill/plugin into an agent so the agent can write and debug evaluation suites itself; or you can run the local CLI to execute test cases and test suites against OpenRouter models in Docker. Its core goal is to ensure that skills perform reliably across different LLMs. The workbench provides the agent with a skill/reference folder, an isolated /work directory, and a deterministic scorer, and is suitable for evaluation scenarios where success can be verified through files, command logs, SQL, generated artifacts, or other local state. A case is a user-like task plus one or more scorers, and a suite is a matrix of cases and OpenRouter models. Scorers run after the agent phase, as an acceptance contract. The repository includes examples such as PDF and MCP. Installation varies by agent and supports Claude Code, OpenAI Codex CLI, Codex App, Cursor, OpenCode, Gemini, and others. The local CLI requires OPENROUTER_API_KEY and only supports openrouter/... model references.

Read more

SkyReels-V2

AI video

SkyReels-V2 is an open-source project by SkyworkAI on GitHub, positioned as an Infinite-length Film Generative model. According to the project description, it is the first open-source video generation model to adopt the AutoRegressive Diffusion-Forcing architecture and achieves SOTA performance among publicly available models. The repository provides model weights and inference code, covering model series such as 1.3B, 5B, and 14B, and supports text-to-video (T2V), image-to-video (I2V), video extension, and start/end frame control, among other features, and includes the video captioning model SkyCaptioner-V1 and a prompt enhancer. The project also provides 720P models, Camera Director models, and Step & Guidance Distill models, among others. Users can download the models from Hugging Face and then set the model path in the generation command, controlling video duration by adjusting the frame count parameter.

Read more

skywork-o1-prm-inference

AI developer platforms

skywork-o1-prm-inference is an open-source inference project by SkyworkAI on GitHub, mainly used for inference tasks of Skywork PRM (Process Reward Model). The project provides a vLLM-based inference solution, including setting up a vLLM server, installing the PRM plugin, and inference request examples. It is suitable for researchers and developers who need to run or test the Skywork PRM model. Specific functional details and complete usage instructions are not yet available.

Read more