agent-eval
Benchmarks CodeGraph retrieval on real repositories by comparing agent behavior with and without CodeGraph.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower"..." for exact phrases · Try typography, debugging or spreadsheetBenchmarks CodeGraph retrieval on real repositories by comparing agent behavior with and without CodeGraph.
Evaluate and improve agent commands, skills, prompts, and context engineering through quality measurements.
Evaluate agent behavior against baselines using regression tests, trajectory reviews, quality metrics, cost, latency, and release gates.
Build Python AG-UI servers and clients with Microsoft Agent Framework, including streaming, shared state, tool calls, and human interaction.
Manage agent-fs storage, file search, sharing, access, versions, mounts, and SQL queries over stored data files.
Adds policy controls, trust scoring, audit trails, content filters, and tool restrictions to AI agent systems.
Create and manage directed agent graphs with configuration routing and handoff logic for multi-agent workflows.
Manage shell hooks that run at agent lifecycle events to block, rewrite, or warn about actions.
Analyze Agent Host debug bundles, event exports, and transport logs to diagnose agent issues.
Integrate agent repositories with Veris by configuring CLI access, environments, sandbox files, and deployment settings.
Refactor large agent instruction files into organized, linked documents using progressive disclosure.
Designs agent memory architectures using context windows, long-term vector stores, and cognitive organization.
A growing collection of real, public skills. Descriptions and instructions indexed 22 Sept 2026.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skilly-cli add owner/repo --skill name