Capability · Skills
Skills it learns once — and reuses, still gated
Learned, reusable procedures that make repeat work dependable — and never outrun the approval gate.
The first time monopea does a job, it works out how. The second time it already knows, because what it learned is kept as a skill: the steps, the tools, and the judgement for a specific kind of work, reusable on demand or on a schedule.
Learning does not loosen anything. A skill is a procedure, not a permission: when a reused skill reaches a mutation-capable call, that call meets the same default-deny gate and the same per-tool policies as if the agent were improvising it for the first time.
A library that grows out of your own work
Each time the agent solves a new kind of problem, the solution is captured as a skill in a library scoped to your tenant. Skills are learned from work you supervised and approved — not installed from a public marketplace — so the library’s provenance is your own operating history, end to end.
Routine work stops being improvised: the weekly report, the pipeline cleanup, the monthly reconciliation become known quantities — predictable in steps, cost, and output.
- Learned from your supervised work, not marketplace downloads
- Scoped to your tenant — your plays stay yours
- Routine work becomes dependable instead of improvised
Reused, composed, and scheduled
Skills compose: the agent chains them into larger jobs the way an experienced operator combines known plays, and routines can put them on a schedule so recurring work runs without being asked. Reuse is where delegation pays — deliberation the first time, dependability every time after.
And because skills run against your live memory and current policies, a reused skill reflects what you know and allow today, not a snapshot of the day it was learned.
A skill is not a permission
Whatever a skill has done before, its outward actions are gated now: every mutation-capable call a skill makes passes the same proposal gate and per-tool policies as ad-hoc work. Trusting a procedure and authorising an action stay two separate decisions — the first never quietly implies the second.
That separation is what makes a growing skill library safe. Capability compounds; authority only changes when you change it.
Why it matters
Compounding capability
Every solved problem makes the next one cheaper. The agent gets better at your work.
Dependable repetition
Reused skills behave consistently — known steps, known cost, known output.
No silent authority creep
Skills reuse procedures, not permissions. The gate applies on every run.
FAQ
Skills & routines, in short
- What exactly is a skill?
- A captured, repeatable procedure — the steps, tools, and judgement for a specific kind of work. Once learned, it is reused instead of re-derived, alone or composed with other skills.
- Where do skills come from?
- From your agent’s own supervised work. monopea does not install skills from a public marketplace; the library is built from problems solved in your tenant, under your gate.
- Does a trusted skill skip the approval gate?
- No. Skills reuse procedure, not permission. Mutation-capable calls inside a skill meet the same default-deny gate and per-tool policies on every run.
- Can skills run on a schedule?
- Yes. Routines put skills on a schedule for recurring work, and a scheduled run is governed exactly like an interactive one — same policies, same proposals, same audit trail.
Keep exploring
Long-term memory
A private, persistent memory and knowledge graph — tenant-isolated, stored in Zurich, and never used to train shared models.
MCP tool catalog
Connect any MCP-compatible tool — and every one of them onboards default-deny, with credentials from the write-only vault.
Approval gate
Default-deny control: mutation-capable tool calls become pending proposals and wait for your decision before anything is dispatched.