# 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 [#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 [#three-tiers]

| Tier             | Who it is for                    | Who can write it       |
| ---------------- | -------------------------------- | ---------------------- |
| **Built in**     | Ships with Plansmith, read-only. | Nobody, they are ours. |
| **Company**      | Everyone in the workspace.       | Owners.                |
| **This project** | Only that project.               | Members and owners.    |

## What ships built in [#what-ships-built-in]

<Cards>
  <Card title="Plan structure">
    Where new work belongs: Specs here, a sub-plan, or beside this plan.
  </Card>

  <Card title="Spec format">
    The shape every Spec is written in.
  </Card>

  <Card title="Epic format">
    How a plan's Epic is written, the body your issue tracker receives.
  </Card>

  <Card title="Readiness review" href="/docs/readiness-review">
    Scores how build-ready one spec is; findings land in a file.
  </Card>

  <Card title="Prototype builder" href="/docs/prototypes">
    Builds a clickable prototype of the plan.
  </Card>

  <Card title="Deep research">
    Sends parallel research agents at a question; the report lands in Context.
  </Card>

  <Card title="Adversarial review">
    Argues the other side of one spec before you commit to it; findings land in its review file.
  </Card>

  <Card title="Push to your issue tracker" href="/docs/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.
  </Card>

  <Card title="Resolve push conflicts" href="/docs/push-to-your-issue-tracker">
    Works through what your team changed, one item at a time, so a stopped push can go.
  </Card>
</Cards>

<Callout>
  **Spec format and Epic format are edited under [Formats](/docs/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.
</Callout>

## Wrapping a built-in skill [#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](/docs/readiness-review) and [Prototypes](/docs/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.

<Callout type="warn">
  **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.
</Callout>

## The agent never writes a skill [#the-agent-never-writes-a-skill]

At any tier. It can propose an [instruction](/docs/agent-instructions) and it can adjust a project
[format](/docs/formats) 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**.