Agent Skills
Teach your coding agent DeepEval and Confident AI workflows with official Agent Skills.
Overview
Confident AI publishes official Agent Skills that teach your coding agent — Cursor, Claude Code, Codex, Windsurf, or any other Skills-compatible assistant — how to work with DeepEval and Confident AI correctly. A skill is a SKILL.md file plus reference docs and code templates that your agent reads before writing code, so it follows the same workflows our own docs prescribe instead of guessing from training data.
Where the MCP server gives your agent live access to your project's resources (traces, datasets, prompts, dashboards), skills give it knowledge — how to build an eval suite, instrument an app, or provision a project the right way. Most teams use both together.
Official Skills
There are four official skills, each with a deliberately narrow scope so your agent picks the right one automatically:
| Skill | What it teaches | API key it uses |
|---|---|---|
confident-client | Administer your account with the Admin SDK — projects, members, RBAC, governance policies, and API keys | CONFIDENT_ORG_API_KEY |
deepeval | Build pytest eval suites — datasets, goldens, metrics, deepeval test run, and iterating on failures | CONFIDENT_API_KEY |
deepeval-tracing | Instrument an AI app with DeepEval's native tracing — @observe, span types, and framework integrations | CONFIDENT_API_KEY |
deepeval-otel | Export raw OpenTelemetry traces to Confident AI from any language — no deepeval package required | CONFIDENT_API_KEY |
The scopes are mutually exclusive by design. Each skill's trigger description tells the agent when not to fire and which sibling skill to use instead, so "add evals to my agent" activates deepeval, "add tracing" activates deepeval-tracing, and "create a project for the new team" activates confident-client — without you naming a skill.
Where the Skills Live
The skills ship inside the same repositories as the SDKs they teach, so the guidance always matches the code:
- The
deepeval,deepeval-tracing, anddeepeval-otelskills live in theconfident-ai/deepevalrepository underskills/. - The
confident-clientskill lives in theconfident-ai/confident-clientrepository — the same repo as the Python and TypeScript Admin SDKs.
Installation
Every skill installs the same three ways. Each skill's own page lists its exact commands; the shapes are:
Works with Cursor, Claude Code, Codex, Windsurf, OpenCode, and any other assistant that supports the Skills standard:
npx skills add confident-ai/deepeval --skill "deepeval"Swap the repo and skill name for the one you want — for example confident-ai/confident-client --skill "confident-client".
Both repositories double as Claude Code plugin marketplaces. Inside Claude Code:
/plugin marketplace add confident-ai/deepeval
/plugin install deepeval@deepeval-plugins
/reload-pluginsThe deepeval plugin bundles all three deepeval-* skills at once. For the admin skill, add confident-ai/confident-client as the marketplace and install confident-client@confident-ai-plugins. See Plugins for the Cursor and Codex equivalents.
Copy or symlink the skill folder into your agent's skills directory:
git clone https://github.com/confident-ai/deepeval
cp -r deepeval/skills/deepeval .claude/skills/For Claude.ai on the web, zip the skill folder and upload it under Settings → Capabilities → Skills.
Once installed, you don't invoke a skill explicitly — describe what you want and the agent activates the matching skill on its own.
FAQs
Do I need the MCP server if I install the skills?
They solve different problems and work best together. The MCP
server gives your agent live access to your
project's resources — traces, datasets, prompts, dashboards. Skills teach
it the workflows: how to build an eval suite, instrument an app, or
provision a project correctly. An agent with both can, for example, build
an eval suite with the deepeval skill and then inspect the resulting
test run over MCP.
Which coding agents support skills?
Any assistant that implements the Skills standard — Cursor, Claude Code, Codex, Windsurf, OpenCode, and others. Claude.ai on the web also accepts skills as zipped uploads under Settings → Capabilities → Skills.
How do the skills stay up to date?
A Skills CLI install or manual copy is a static snapshot — rerun the install to pick up changes. If you install through a plugin instead, your client tracks the repo as a marketplace source and updates through its own plugin flow.
Are the skills open source?
Yes — all four are Apache-2.0 licensed and live in the same public repositories as the SDKs they teach, so you can read every instruction the skill gives your agent before installing it.
Next Steps
MCP Server
Give your agent live access to your project's traces, datasets, prompts, and evals — skills pair naturally with it.
Custom Agent Skills
Serve your own project-specific onboarding skills to coding agents from Confident AI's git endpoint.
Last updated on