Skills

Short playbooks that teach the agent how your team does a particular job, read when they are relevant.

A skill is a short guide that teaches the agent how your team does something: how you write release notes, how you size work, what your readiness review covers.

Each one has a name, a line describing when it should be used, and a body. The agent only sees that one line until it decides the skill is relevant, then it opens it. So a skill can be as long as it needs to be without slowing down every conversation.

Using one

Type / in the message box and pick a skill to apply it deliberately. Otherwise the agent reaches for one on its own when the situation matches its description.

That description is the whole interface. "Whenever drafting release notes or launch announcements" gets opened at the right moment; "notes" does not.

Three tiers

TierWho it is forWho can write it
Built inShips with Plansmith, read-only.Nobody, they are ours.
CompanyEveryone in the workspace.Owners.
This projectOnly that project.Members and owners.

What ships built in

Plan structure

Where new work belongs: Specs here, a sub-plan, or beside this plan.

Spec format

The shape every Spec is written in.

Epic format

How a plan's Epic is written, the body your issue tracker receives.

Readiness review

Scores how build-ready one spec is; findings land in a file.

Prototype builder

Builds a clickable prototype of the plan.

Deep research

Sends parallel research agents at a question; the report lands in Context.

Adversarial review

Argues the other side of one spec before you commit to it; findings land in its review file.

Push to your issue tracker

Sends the plan to your issue tracker, and stops without writing if a teammate changed one of the issues first.

Resolve push conflicts

Works through what your team changed, one item at a time, so a stopped push can go.

Spec format and Epic format are edited under Formats, not here. They appear in this list because that is how the agent reaches them, and if your team customizes either one, the agent reads your version instead of ours.

Wrapping a built-in skill

A company or project skill can extend a built-in one instead of replacing it. Your wrapper adds your team's own rules; the built-in pass, its output and its safeguards stay exactly as they are.

Two skills can be wrapped today: Readiness review and Prototype builder.

A wrapper names the built-in skill's hooks rather than copying its steps, so it keeps working when we reword one. Each skill's page lists its hooks and carries a worked wrapper you can copy: Readiness review and Prototypes.

A wrapper can add rules and raise the bar. It cannot lower one. If a wrapper asks the agent to relax something the built-in skill states, the agent follows the built-in skill and tells you it did.

Paste the body only. The settings form writes the header for you. Pasting a whole file that carries its own header gives you two, and the inner one quietly becomes body text.

The agent never writes a skill

At any tier. It can propose an instruction and it can adjust a project format when you ask it to in conversation, but a skill is always written by a person.

That is deliberate: skills are procedures the agent then follows, so a skill it could write itself would be a loop with nobody in it.

Write one under Settings → Skills.