Agent Skill
Use Rhesis from Claude Code, Cursor, or any compatible AI interface — without the Rhesis web UI.
The Rhesis Agent Skill packages the platform’s domain knowledge into a portable skill file. Once installed, your AI interface can explore endpoints, design test suites, generate and run tests, and analyze results using the Rhesis MCP server as its backend.
This is different from Rhesis’s inbound MCP connector (where the platform imports content from Notion, GitHub, or Jira). Here, an external AI agent calls into Rhesis to drive the testing workflow.
Prerequisites
- A Rhesis account at app.rhesis.ai (or a self-hosted backend)
- An API token — generate one at app.rhesis.ai/tokens
Install (any agent)
The fastest way to install across Claude Code, Cursor, Codex, Gemini CLI, and 40+ other AI interfaces:
The CLI detects your installed agents and places the skill accordingly. After installing the skill, connect the MCP server for your specific agent (see below).
Install in Claude Code
Claude Code uses a plugin system that bundles the skill and MCP server configuration together.
Step 1: Add the Rhesis marketplace and install the plugin:
Step 2: Set your API token:
The plugin reads RHESIS_API_KEY automatically. On next session start, the rhesis MCP server is connected and the skill is active.
Self-hosted backend:
Install in Cursor
Connect the MCP server
Add the following to .cursor/mcp.json (project-level) or ~/.cursor/mcp.json (global):
Replace YOUR_RHESIS_API_KEY with your actual token. Restart Cursor after editing.
For self-hosted backends, replace https://api.rhesis.ai/mcp with http://localhost:8080/mcp.
Install the skill
Clone the repo and symlink the skill directory:
Cursor loads the skill automatically on next session.
Usage
Once installed, interact with your AI interface naturally:
"I want to test my travel chatbot. The endpoint is called 'travel-agent-v2'."The skill guides the full workflow:
- Discover — explores what your endpoint can do (Quick or Comprehensive mode)
- Plan — proposes a test suite with behaviors, test sets, and metrics
- Review — waits for your approval before creating anything
- Create — builds entities on the platform following the approved plan
- Execute — runs tests when you confirm
- Analyze — presents pass/fail summary, failure patterns, and links
You can also use it for direct operations:
"List my existing test sets"
"Improve the Safety Compliance metric — make the threshold stricter"
"Compare my last two test runs"
"Link the Accuracy metric to the Provides Accurate Information behavior"Agent Skill vs. native Architect
The Rhesis platform has a built-in Architect agent with a web chat UI. This skill is a complement, not a replacement:
| Native Architect | Agent Skill | |
|---|---|---|
| Access | Rhesis web UI | Your existing AI interface |
| Plan tracking | Structured plan with progress bar | Conversational, host agent context |
| Confirmation guard | Accept/Change UI, auto-approve toggle | Host agent’s native confirmation |
| Write guard | Structural enforcement | Instructional guidance only |
| Mode transitions | Formal phases with events | Informal, guided by skill |
Use the native Architect for maximum structural control. Use this skill when you want to work within Claude Code or Cursor without switching context.
Troubleshooting
MCP server not connecting
- Verify your API token is valid and has not expired — regenerate at app.rhesis.ai/tokens
- Test connectivity:
curl -H "Authorization: Bearer $RHESIS_API_KEY" https://api.rhesis.ai/mcp - In Cursor, restart the IDE after editing
.cursor/mcp.json
Skill not activating (Cursor)
- Verify
~/.cursor/skills/rhesis/SKILL.mdexists - Try explicitly invoking: type
/rhesisin the chat
Claude Code skill loading issues
- There is a known issue with
~/.claude/skills/filesystem discovery in some versions of Claude Code. Use the plugin install path (/plugin install rhesis@rhesis-ai) instead — this uses a supported installation mechanism.
Source
The skill source lives at skills/rhesis/ in the Rhesis repository. Reference files covering all 27 MCP tools, OData query patterns, exploration strategies, and result analysis are in skills/rhesis/references/.