linear-cli

Linear CLI (schpet/linear-cli)

Overview

Use this skill to help the user work through a local linear installation from inside NextClaw.

This skill is intentionally decoupled:

• The skill owns explanation, onboarding, readiness checks, workflow choice, and risk handling.
• The linear CLI owns actual execution against Linear’s API and the user’s git or Jujutsu workspace.

From the user’s point of view, the experience should feel complete:

• install the CLI if needed,
• ensure authentication and project configuration,
• verify readiness with observable commands,
• then run the real task.

Do not pretend the environment is ready when it is not.

What This Skill Covers

• Issue workflows: list, view, start, create, update, delete, comments, PR helpers (when gh is available as documented upstream).
• Team, project, milestone, and document commands exposed by the installed CLI.
• Git branch–based “current issue” semantics and Jujutsu Linear-issue trailers when the user uses jj.
• First-use setup: API key, linear auth login, and linear config in the target repository.
• Readiness checks and bounded troubleshooting.

What This Skill Does Not Cover

• Inventing flags or subcommands that do not appear in linear --help or the installed CLI help for the relevant subcommand.
• Claiming Linear workspace permissions or plan limits the user does not have.
• Silently bypassing missing authentication or broken configuration.
• Silently triggering destructive or write actions without explicit user confirmation.
• Treating third-party CLI behavior as native NextClaw behavior.

First-Use Workflow

When the user asks for a linear-powered task, follow this order.

1. Classify the task

Classify the task into one of these:

• read-only (view, list, print id/url/title),
• write (create/update/delete issues, start work, comments, milestones, documents),
• VCS-assisted (branch creation, issue binding).

If the task does not fit what the CLI supports, say so clearly.