Can I generate a skill from any session?

Yes. Open any captured session in paper console and generate a skill from it, optionally seeding the name, description, type, and tags with a short hint.

How do versions work?

A skill is either published or not. Publishing creates an immutable version (v1, v2, …) with a changelog. Older versions stay browsable, so you can see how a skill evolved.

How do I use a skill in my own project?

Run paperctl skill sync with the skill's slug — it writes the SKILL.md into a local skills directory your agent reads (use --claude for Claude Code, --local for one project). You can also download the SKILL.md from paper console and place it yourself.

Published skills are visible to everyone on your team, and each skill is attributed to its creator. Use the scope filter in the Skills view to browse all skills, just your own, or your team's.

Skills - Paper Compute Docs

A skill is reusable instruction — a SKILL.md — distilled from real agent work and stored in paper console. When a teammate solves a hard problem well, you don’t have to rediscover how they did it: capture the session, turn it into a skill, and the prompt, tool order, and approach become something the whole team can reuse.

Skills are the step beyond reading session history. History tells you how the work happened; a skill turns the best of that work into something you can apply again.

How skills work

Run an agent through the paperctl CLI so the session is captured to paper console.
Generate a skill from a session that went well.
Review and edit it — name, description, tags, and the SKILL.md content.
Publish a version so teammates can find and reuse it.

Generate a skill from a session

Open a captured session in paper console and generate a skill from it. You can seed it with a short hint — a name, description, type, or tags — and the console extracts a first SKILL.md from the session’s prompts, tool calls, and turns.

Because the skill comes from a real run, it reflects what actually worked, not a best-guess written from memory.

The same works from the terminal: paperctl skill generate <session-id> kicks off generation for one or more sessions (--name pins the name), and paperctl skill list browses your organization’s library.

Recorded session · excerpts

Refine the digest layout

CompletedSep 10, 2026Brian DouglasGPT 5.6 Sol

Context compacted — session continued from a summary

Input · excerpt

*** Update File: src/components/dashboard/dashboard-digest-card-v2.test.tsx@@-  it("renders v2 structure when the headline is absent", () => {-    // headline is optional on the wire and defaults to "" — the structure-    // this branch renders is what makes a digest v2, not the headline.-    const noHeadline = { ...v2Digest, content: { ...v2Digest.content, headline: "" } };-    render(<DashboardDigestCard state={ready(noHeadline)} />);-    expect(screen.getByRole("heading", { name: "Summary" })).toBeInTheDocument();-    expect(screen.getByText("One merge, one blocker.")).toBeInTheDocument();+  it("does not promote a generated headline when the narrative is empty", () => {+    const emptyNarrative = {+      ...v2Digest,+      content: { ...v2Digest.content, headline: "Clearing Digest", narrative: "" },+    };+    render(<DashboardDigestCard state={ready(emptyNarrative)} />);+    expect(screen.queryByRole("heading", { name: "Summary" })).not.toBeInTheDocument();+    expect(screen.queryByText("Clearing Digest")).not.toBeInTheDocument();     expect(screen.getByRole("list", { name: "Highlights" })).toBeInTheDocument();-    expect(screen.getByRole("heading", { name: "Still open" })).toBeInTheDocument();+    expect(screen.getByRole("button", { name: /accomplishments & next steps/i })).toBeInTheDocument();   });

Output · excerpt

Success. Updated the following files:M src/components/dashboard/dashboard-digest-card-v2.test.tsx

content.narrative is now the summary. The generated headline is never promoted. The current cassette narrative is empty, so Highlights lead instead of showing “Clearing Digest.”

we call these accomplishements, but we should call these outcomes.

Changed the digest label from Accomplishments to Outcomes in both current and legacy views. The cassette field remains accomplishments internally. Verified in the live UI; 25 tests and lint pass.

Session Info

Tokens23.64M in · 71.4K out

Cost$15.79

Turns7

Turnsinout

Live demo — click Generate Skill in the Session Info rail

Review, edit, and publish

A generated skill starts unpublished. Edit it to sharpen the result:

Name and description — what the skill does and when to reach for it.
Tags and type — so it’s easy to find later.
Content — the SKILL.md itself.

Publishing creates an immutable version with a changelog, visible to everyone on your team. Versions accumulate as v1, v2, and so on, and older versions stay browsable with a diff against the current version — useful when you want to see how a skill changed or compare against a previous cut.

Edit Skill

Name

Description

Find and reuse skills

The Skills view in paper console is the shared library for your team:

Search by name or description.
Filter by scope — all skills, just yours, or your team’s, with live counts.
Filter by tag and sort by most recent or most downloaded.
Switch between card and table views of the library.
Open any skill to read its content, see the sessions it came from, and browse its version history.

Anyone on the team can duplicate a skill — fork it into an editable copy of their own — copy a link to it, or download its SKILL.md. Editing and deleting a skill are reserved for its creator.

To use a skill, install it — paperctl skill sync <slug> puts the SKILL.md where your agent reads it, and re-running it later picks up new versions. Skills are also served by the tapes Skills API, so agents that pull skills in over HTTP reach the same library.

Skills

Sort

Refine a Responsive Digest Layout

Use when refining a dashboard digest: check the source data, keep the summary focused, and verify the layout at mobile and desktop widths.

Responsive UIAccessibilityReact

BDBrian Douglas(You)· 3m ago

concepts-page

Writing or editing concept pages on papercompute.com (`src/content/concepts/<slug>.mdx`). TRIGGER when a new concept page is requested.

BHBekah HW· 27m ago

Triage and Clean Paper Forest Groves

Use when assessing paper forest groves for cleanup, specifically to identify clean, caveat-laden, and far-from-ready groves.

grove managementcleanuptriage+2

BDBrian Douglas(You)· 9h ago

Implement Lambda MicroVMs with Paper and Agent

Demonstrate the integration of Lambda MicroVMs with the Paper proxy and agent for capturing model turns. Use when wiring MicroVM workloads into tapes.

LambdaMicroVMPaper+2

JCJason Carter· 10h ago

Deploy Skills Feature in Cloud

Use when preparing to release the new skills feature in the cloud, ensuring all necessary updates to the cloud environment land in order.

clouddeploymentversioning+1

JCJason Carter· 12h ago

Set Up and Validate Paper Clearing Environment

Use when creating a new Paper Compute clearing environment from scratch and ensuring its functionality end to end.

environment setupvalidationPaper Compute+1

JCJason Carter· yesterday

Triage and Clean Paper Forest Groves

Use when managing a paper forest of groves to identify which can be safely removed. This skill involves syncing, inspecting, and pruning.

gitcleanuptriage+2

JCJason Carter· yesterday

From Scratch

Making a skill from scratch

JCJason Carter· 2d ago

Live demo — search, switch tabs and views, change the sort

Ways teams use skills

Capture institutional knowledgeWhen someone figures out a tricky workflow, it becomes a reusable skill instead of living in one person’s head.

Standardize how agents workPublish the prompt and tool patterns your team trusts, so everyone’s agent starts from the same proven approach.

Onboard with real workNew teammates pick up skills built from sessions that actually shipped, not stale best-practice docs.

Improve over timeVersioning means a skill gets better as your team learns, with a record of every change.

Skills

How skills work

Generate a skill from a session

Review, edit, and publish

Find and reuse skills

Ways teams use skills

Frequently asked questions