ticket-builder

Creates and sequences grounded Linear tickets using MCP relations, labels, and priority conventions.

1|Updated Jun 30, 2026
One-click install
npx skills add https://github.com/Lia-Creative/lia-plugins --skill ticket-builder-lia-creative
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ticket-builder
Source: https://github.com/Lia-Creative/lia-plugins/tree/main/lia-tools/skills/ticket-builder
Command: npx skills add https://github.com/Lia-Creative/lia-plugins --skill ticket-builder-lia-creative

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Writing Linear tickets that are grounded in real sources, correctly sequenced, and consistent with team conventions is hard to do by hand. This Skill encodes Lia's shared ticket-writing mechanics — grounding, ordering, labels, statuses, and the Linear MCP calls — so every ticket reads clearly and the board reflects reality. ## Core Features & Use Cases - Grounded ticket creation: Locates real vault sources and sibling tickets before writing, wiring links as blocked-by/related relations instead of prose clutter. - Sequencing and board integrity: Orders work with priority plus blocked-by relations, enforces the rule that parents never enter Review/QA before their sub-issues finish, and routes work to the correct Linear team (Lia Build vs Lia). - Conventions and mechanics: Applies the six type labels, two-scale priority model, noun-phrase title rule, and the save_issue MCP workflow, then verifies results with get_issue and logs the build. - Use Case: Ask it to break a new workstream into Linear tickets — it grounds each one in strategy docs, creates the epic and sub-issues with parentage and dependencies wired, and logs the result. ## Quick Start Ask the agent to build the tickets for a new Lia workstream or feature and it will ground, shape, sequence, and create them in Linear.

Frequently Asked Questions about ticket-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create well-structured Linear tickets with an AI agent?▼

Ground each ticket in a real source document first, then create the epic followed by sub-issues with parentId set, and wire dependencies as blocked-by relations. Finish by calling get_issue with includeRelations to verify everything landed correctly.

How should Linear tickets be sequenced without story points?▼

Sequence tickets with priority plus blocked-by relations rather than estimates or numbered titles. Build the dependency graph deliberately so the board self-orders, and use relatedTo for non-blocking associations like research references.

What labels and priority conventions does this workflow use?▼

It uses exactly six type labels (Bug, Feature, Improvement, Decision, Research, Foundation) on leaf tickets only, never on epics. Priority is two-scale: a parent's priority ranks it against other parents, a child's ranks it within its own bucket.

When should something be a doc instead of a Linear ticket?▼

A ticket has a finish line; a doc holds durable knowledge. If you would want to read it again in three months it is a doc living in the vault, while work with a done-state becomes a ticket, often one that produces or updates a doc.

Why should links live in Linear relations instead of ticket prose?▼

Pasting issue IDs into descriptions clutters the prose and duplicates what the relation panel shows. Wiring blockedBy, blocks, and relatedTo relations keeps the description human-readable while the sidebar carries the dependency graph.