skills.rest
rhesis-airhesis-aiOfficial·2 Agent Skills Included

rhesis

Structured feedback, testing, and evaluation for AI applications

Collects structured pass/fail feedback on AI agents from domain experts and turns it into automated tests and metrics. Generates test sets from specs, simulates conversations, runs adversarial probes, and scores results with 60+ evaluation metrics. Connects agents via SDK or REST endpoint so teams review, measure, and improve quality without manual spreadsheet tracking.
386|30
↗
npx skills add rhesis-ai/rhesis --all -g -y
Available:

Gives the AI agent repo-wide operating rules — plain-language answers, absolute Python imports, worktree and testing procedures, and strict commit and PR approval gates — and routes it to scoped sub-guides for the backend, frontend, SDK, docs, and published skill.

All Skills in This Repository (2)

Pure Emerald Level Indicators
📦 In Repo
rhesis-airhesis-ai

python-linting

Apply Ruff linting and formatting to Python files before commits.

Official
Basic
📦 In Repo
rhesis-airhesis-ai

sprint-review

Generate a markdown changelog from GitHub pull requests grouped into Features and Fixes.

Official
Intermediate

Frequently Asked Questions

FAQPage Schema
How to install Rhesis?▼

Run `npx skills add rhesis-ai/rhesis --all -g -y` in your terminal to install the skill globally for your AI agent.

What does Rhesis do for AI agent testing?▼

Rhesis lets domain experts review your agent's answers in a browser, then converts that feedback into test sets and metrics that run automatically on every change.

How do I connect my agent to Rhesis?▼

Use the Python SDK connector, which opens an outbound WebSocket so your agent needs no public URL, or register an existing public REST endpoint directly in the UI.

Does Rhesis work with Claude Code and Cursor?▼

Yes. The Rhesis skill and MCP server let you design test suites, trigger runs, and read feedback directly from Claude Code, Cursor, and other MCP-compatible clients.

Can non-developers review AI agent answers in Rhesis?▼

Yes. Reviewers open a shared link in the browser, chat with the agent in the playground, and leave pass/fail verdicts and comments with no code required.

Related Repositories in Software Engineering

View All in Software Engineering→
openclawopenclaw
388.4k

openclaw

Run a personal AI assistant across your devices and chat apps

Official📦 120 Skills
obraobra
280.0k

superpowers

Gives coding agents a disciplined workflow from idea to merged code

Community📦 15 Skills
facebookfacebook
248.4k

react

AI agent skills for building, testing, and porting React core

Official📦 14 Skills