Skills are packaged, reusable capabilities your connected agent can run — scripts and
procedures for concrete tasks (for example, setting up cloud IAM). Rather than
improvising every time, the agent reaches for the right skill, which makes its
work more reliable and repeatable.
How the agent uses skills
When a task matches a skill, your agent loads and runs it as part of a session —
you’ll see it in the tool activity. Skills run with the credentials you’ve
selected for the session, under the same guardrails as any
other agent action: changes still surface as plans for approval.
The set of built-in skills evolves as the product grows. You don’t install
built-in skills manually — Nuphos makes the relevant registry available to
the runtime automatically.
Your team’s own skills
Built-in skills are not the whole set. A team can author its own under Skills
in the sidebar — the runbook you would otherwise paste into every session, stored
once and matched like any built-in. The agent can also write one for you at the
end of a session, when you have just walked it through something it should
remember how to do.
Team skills are made available to the workspace runtime alongside Nuphos’s
built-ins. They obey the same rules: they run with the credentials
selected for the session, and anything they change still surfaces as a
plan.
Across supported agent runtimes
Claude Code connected through Agent runtime uses these skills
inside its hosted OpenAB environment.
As their runtime adapters are enabled, other terminal coding agents supported by
OpenAB will keep their own native harness
while Nuphos supplies the same Skills, MCP servers, memory, credentials, and
DevOps context around them. 
