agentskills.codes vs Oqoqo

agentskills.codes indexes public SKILL.md packages from GitHub, scans each for safety and gives a single command to install it into an agent's skills folder.

Run eval experiments at scale in realistic environments on fully managed cloud infrastructure. Define custom task sets to build your private benchmarks, measure how well...

About agentskills.codes

agentskills.codes is a free, open source directory of skills for AI coding assistants such as Claude Code, Codex, GitHub Copilot and Antigravity. A skill is a folder containing a SKILL.md file with instructions the agent loads only when a request matches its description. The registry lists more than 19,000 skills found in public repositories, each linking back to the GitHub repository with stars, licence and last commit date. Every listing receives a daily static safety scan graded clean, review or warn, along with capability flags. Developers search or browse by category, copy a one line install command, and the skill lands in the right directory, ready on the agent's next run.

About Oqoqo

Run eval experiments at scale in realistic environments on fully managed cloud infrastructure. Define custom task sets to build your private benchmarks, measure how well agents can use any product, and find the best agent-model combinations for your use cases. Generate insights on the fly, such as product interface friction, token inefficiencies, performance differences, and so much more. Oqoqo - The easiest way to build evals and custom benchmarks for real-world agentic tasks . A video-style demonstration of building and launching an agent experiment in Oqoqo: describing a task, selecting tasks, configuring agents, treatments, runs and evals, then launching runs on sandboxed machines and reviewing pass and fail results with full step-by-step trajectories.