Skip to content

Commit 98c7c66

Browse files
sebastiancrossasebastiancrossa
committed
include new integration sections
1 parent 08bb107 commit 98c7c66

File tree

9 files changed

+187
-0
lines changed

9 files changed

+187
-0
lines changed

‎docs.json‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -72,6 +72,15 @@
7272
"judges/submit-feedback",
7373
"judges/pull-evaluations"
7474
]
75+
},
76+
{
77+
"group": "Integrations",
78+
"pages": [
79+
"integrations/introduction",
80+
"integrations/skills",
81+
"integrations/mcp",
82+
"integrations/cli"
83+
]
7584
}
7685
]
7786
}

‎index.mdx‎

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -31,6 +31,16 @@ description: "Start improving your AI applications with ZeroEval"
3131
</Card>
3232
</CardGroup>
3333

34+
<CardGroup cols={1}>
35+
<Card
36+
title="Integrations"
37+
icon="puzzle-piece"
38+
href="/integrations/introduction"
39+
>
40+
Set up ZeroEval from your coding agent, or manage it from the terminal
41+
</Card>
42+
</CardGroup>
43+
3444
## Next Steps
3545

3646
<CardGroup cols={2}>

‎integrations/cli.mdx‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
---
2+
title: "CLI"
3+
description: "Manage ZeroEval from your terminal"
4+
---
5+
6+
<Note>
7+
The CLI is coming soon.
8+
</Note>
9+
10+
We're building a CLI for managing traces, prompts, and judges from the terminal. Useful for CI/CD pipelines, scripted workflows, and quick lookups when you don't want to open the console.
11+
12+
Want to know when it ships? Email [founders@zeroeval.com](mailto:founders@zeroeval.com).

‎integrations/introduction.mdx‎

Lines changed: 35 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,35 @@
1+
---
2+
title: "Introduction"
3+
description: "Ways to integrate ZeroEval beyond the core SDKs"
4+
---
5+
6+
Besides the Python and TypeScript SDKs, there are a few other ways to get ZeroEval into your workflow.
7+
8+
<CardGroup cols={3}>
9+
<Card
10+
title="Skills"
11+
icon="wand-magic-sparkles"
12+
href="/integrations/skills"
13+
>
14+
Install and configure ZeroEval from inside Cursor, Claude Code, or any coding agent
15+
</Card>
16+
<Card
17+
title="MCP"
18+
icon="plug"
19+
href="/integrations/mcp"
20+
>
21+
Connect ZeroEval to AI agents via Model Context Protocol (coming soon)
22+
</Card>
23+
<Card
24+
title="CLI"
25+
icon="terminal"
26+
href="/integrations/cli"
27+
>
28+
Manage traces, prompts, and judges from your terminal (coming soon)
29+
</Card>
30+
</CardGroup>
31+
32+
## Where to start
33+
34+
- **If you use Cursor, Claude Code, or Codex**, try [Skills](/integrations/skills). Your coding agent handles SDK install, first trace, prompt migration, and judge setup for you.
35+
- **If you prefer doing it yourself**, head to the [Quickstart Guide](/tracing/quickstart) and pick the [Python](/tracing/sdks/python/setup) or [TypeScript](/tracing/sdks/typescript/setup) SDK.

‎integrations/mcp.mdx‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
---
2+
title: "MCP"
3+
description: "Model Context Protocol server for ZeroEval"
4+
---
5+
6+
<Note>
7+
MCP integration is coming soon.
8+
</Note>
9+
10+
We're building an MCP server so AI agents can query traces, manage prompts, and run evaluations through ZeroEval without leaving the agent context.
11+
12+
Want to know when it ships? Email [founders@zeroeval.com](mailto:founders@zeroeval.com).

‎integrations/skills.mdx‎

Lines changed: 97 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,97 @@
1+
---
2+
title: "Skills"
3+
description: "Set up ZeroEval from inside Cursor, Claude Code, Codex, and other coding agents"
4+
---
5+
6+
Skills let your coding agent do the ZeroEval setup work for you. Instead of flipping between docs and your editor, you tell your agent "install zeroeval" or "create a judge" and the skill handles the rest in-context. The source lives at [zeroeval/zeroeval-skills](https://github.com/zeroeval/zeroeval-skills) on GitHub.
7+
8+
They work with Cursor, Claude Code, Codex, and 30+ other agents that support the skills format.
9+
10+
## Available skills
11+
12+
<CardGroup cols={2}>
13+
<Card title="zeroeval-install" icon="download">
14+
Installs the SDK (Python or TypeScript), verifies your first trace, migrates prompts to `ze.prompt`, and recommends starter judges.
15+
</Card>
16+
<Card title="create-judge" icon="gavel">
17+
Helps you pick an evaluation type (binary or scored), write a judge template, define criteria, and create the judge via dashboard or API.
18+
</Card>
19+
</CardGroup>
20+
21+
## Install
22+
23+
<CodeGroup>
24+
25+
```bash CLI (recommended)
26+
# Install all skills
27+
npx skills add zeroeval/zeroeval-skills
28+
29+
# Install a specific skill
30+
npx skills add zeroeval/zeroeval-skills --skill zeroeval-install
31+
32+
# List available skills
33+
npx skills add zeroeval/zeroeval-skills --list
34+
```
35+
36+
```bash Claude Code plugin
37+
# Add the marketplace
38+
/plugin marketplace add zeroeval/zeroeval-skills
39+
40+
# Install a specific plugin
41+
/plugin install zeroeval-install@zeroeval-skills
42+
/plugin install create-judge@zeroeval-skills
43+
44+
# Reload plugins if the new commands do not appear immediately
45+
/reload-plugins
46+
```
47+
48+
```bash Manual copy (Cursor / Claude Code)
49+
git clone https://github.com/zeroeval/zeroeval-skills.git
50+
51+
# Cursor
52+
mkdir -p .cursor/skills
53+
cp -r zeroeval-skills/skills/zeroeval-install .cursor/skills/zeroeval-install
54+
cp -r zeroeval-skills/skills/create-judge .cursor/skills/create-judge
55+
56+
# Claude Code
57+
mkdir -p .claude/skills
58+
cp -r zeroeval-skills/skills/zeroeval-install .claude/skills/zeroeval-install
59+
cp -r zeroeval-skills/skills/create-judge .claude/skills/create-judge
60+
```
61+
62+
</CodeGroup>
63+
64+
<Note>
65+
On Windows without symlink support, use `npx skills` or the manual copy method. The `plugins/` directory in the repo contains symlinks that may not resolve on Windows.
66+
</Note>
67+
68+
## Requirements
69+
70+
- A ZeroEval account and API key — [zeroeval.com](https://zeroeval.com)
71+
- Python 3.8+ or Node 18+
72+
- An LLM provider SDK (OpenAI, Vercel AI, LangChain, etc.)
73+
74+
<Tip>
75+
The [zeroeval-skills GitHub repo](https://github.com/zeroeval/zeroeval-skills) has the latest skill content and deeper reference playbooks. This page covers discovery and install only.
76+
</Tip>
77+
78+
## After installation
79+
80+
Once installed, your coding agent picks up the skills automatically. Ask it to "set up zeroeval" or "create a judge" and it will use them.
81+
82+
If you want to read the product docs directly:
83+
84+
<CardGroup cols={2}>
85+
<Card title="Tracing quickstart" icon="rocket" href="/tracing/quickstart">
86+
Get your first trace in under 5 minutes
87+
</Card>
88+
<Card title="Prompt setup" icon="wrench" href="/autotune/setup">
89+
Add ze.prompt() to your Python or TypeScript codebase
90+
</Card>
91+
<Card title="Judges" icon="gavel" href="/judges/introduction">
92+
How calibrated judges evaluate your production traffic
93+
</Card>
94+
<Card title="Judge setup" icon="sliders" href="/judges/setup">
95+
Create and calibrate a judge
96+
</Card>
97+
</CardGroup>

‎judges/introduction.mdx‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -14,3 +14,7 @@ Use a judge when you want consistent, scalable evaluation of:
1414
- Hallucinations, safety/policy violations
1515
- Response quality (helpfulness, tone, structure)
1616
- Latency, cost, and error patterns tied to specific criteria
17+
18+
<Tip>
19+
Not sure where to start? The [create-judge skill](/integrations/skills) can help you pick an evaluation type, write a template, and set up criteria from inside your coding agent.
20+
</Tip>

‎judges/setup.mdx‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -20,3 +20,7 @@ For each evaluated item you have the option to mark it as correct or incorrect.
2020

2121
<img src="/images/calibrated-judge-2.png" alt="Calibrating your judge" />
2222

23+
<Tip>
24+
Using Cursor, Claude Code, or another coding agent? The [`create-judge` skill](/integrations/skills) can help you pick an evaluation type, write the template, and create the judge without leaving your editor.
25+
</Tip>
26+

‎tracing/quickstart.mdx‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -19,3 +19,7 @@ Get started with one of our SDKs:
1919
For TypeScript and JavaScript applications using Node.js or Bun
2020
</Card>
2121
</CardGroup>
22+
23+
<Tip>
24+
Using Cursor, Claude Code, or another coding agent? The [`zeroeval-install` skill](/integrations/skills) can handle SDK setup, first trace, and prompt migration for you.
25+
</Tip>

0 commit comments

Comments
 (0)