Agent Skills that teach AI coding assistants (Claude Code, Cursor, etc.) how to work with Galtea — the AI product testing and evaluation platform.
| Skill | Description |
|---|---|
| galtea | Interact with the Galtea Platform API. Authenticate, manage products/versions/specifications/tests/metrics/endpoint-connections, run and monitor evaluations, and inspect sessions and traces. |
A Galtea Cursor Plugin that bundles this skill is on the way. Once it is live on the Cursor marketplace, install with:
/add-plugin galtea
Until the plugin is live, use the skills CLI or Manual symlink options below.
Install via the skills CLI:
npx skills add Galtea-AI/skills --skill "galtea"Clone this repo and symlink the skill into your agent's skills directory:
git clone https://github.com/Galtea-AI/skills.git /path/to/galtea-skills
ln -s /path/to/galtea-skills/skills/galtea /path/to/skills-directory/galteaYou need a Galtea account and an API key:
export GALTEA_API_KEY=gsk_...API keys are found in the Galtea dashboard under Settings → API Keys. Each account has a single key; regenerating permanently replaces it.
Once installed, the agent will automatically use this skill when relevant — for example:
- Setting up a new product version with an endpoint connection
- Writing specifications and generating tests + metrics from them
- Running evaluations via
fromVersion,fromSession, orfromInferenceResult - Polling async evaluations and reading their scores
- Tracing agent internals (tool calls, LLM calls) as Trace records
- Querying products, tests, metrics, sessions, and traces
For the full Galtea-side docs page on this skill, see docs.galtea.ai/sdk/integrations/agent-skill.
Something not working as expected, or want a new skill? Open an issue with the skill-feedback label. Your coding agent can also submit feedback for you — just ask.