to-tickets
๐ฏSkillfrom mattpocock/skills
Installation
npx vibeindex add mattpocock/skills --skill to-ticketsnpx skills add mattpocock/skills --skill to-tickets~/.claude/skills/to-tickets/SKILL.mdA Claude Code skill that breaks any plan, spec, or conversation into tracer-bullet tickets with declared blocking edges, supporting both local files and real issue trackers.
Overview
to-tickets is part of Matt Pocock's "Skills For Real Engineers" collection, a set of composable agent skills built from decades of engineering experience. This skill takes any plan, spec, or conversation and breaks it down into a set of tracer-bullet tickets. Each ticket declares its blocking edges so that work can be sequenced and parallelized correctly. Tickets can be output as text in a local file or as native blocking links on a real issue tracker like GitHub Issues or Linear.
Key Features
- Automatic ticket decomposition: Takes a plan, spec, or ongoing conversation and generates a structured set of implementable tickets with clear scope and deliverables
- Blocking edge declaration: Each ticket explicitly declares what it blocks and what blocks it, enabling proper dependency tracking whether using a local file or a real issue tracker with native blocking links
- Multi-tracker support: Outputs to GitHub Issues, Linear, or local file-based tracking, configured once via /setup-matt-pocock-skills
- Tracer-bullet approach: Tickets are designed as thin, end-to-end slices that prove the architecture works before filling in details, reducing risk in complex implementations
- Composable workflow: Pairs naturally with /to-spec (to create the spec first) and /implement (to execute each ticket), forming a complete plan-to-delivery pipeline
Who is this for?
- Software engineers who want to break large features or refactors into well-scoped, dependency-aware tickets without manual overhead
- Team leads who need structured task breakdowns with clear blocking relationships for sprint planning
- Developers using AI coding agents who want a disciplined ticket-first workflow that prevents the agent from tackling too much at once
Same repository
mattpocock/skills(58 items)
SKILL.md
More from this repository10
Interviews the user relentlessly about every aspect of a plan or design until reaching shared understanding, resolving each branch of the decision tree one by one. Provides recommended answers for each question and explores the codebase when answers can be found there.
A skill that runs a grilling session to challenge your plan against an existing domain model, sharpen terminology by building a shared language in CONTEXT.md, and document architectural decisions in ADRs before coding begins.
An agent skill from Matt Pocock's engineering toolkit that helps improve your codebase architecture. Part of a composable skill set designed to fix common AI coding agent failure modes through structured, experience-based workflows.
Enforces test-driven development with a strict red-green-refactor loop using vertical slices (one test then one implementation at a time), emphasizing behavior verification through public interfaces rather than implementation-coupled testing.
Initial setup skill for Matt Pocock's engineering skills collection that configures your backlog manager, triage labels, and documentation paths for AI coding agents.
A model-invoked productivity skill that interviews users relentlessly about a plan or design until every branch of the decision tree is resolved. It serves as the reusable interview loop behind the grill-me and grill-with-docs skills.
Composable, model-agnostic agent skills for real engineering workflows, featuring /grill-me for requirement alignment, /prototype for rapid iteration, and task management tools designed to fix common failure modes in AI coding agents.
A model-invoked engineering skill that provides shared discipline and vocabulary for designing deep modules: maximizing behavior behind small interfaces, placing code at clean seams, and ensuring testability through public APIs.
A model-invoked skill that guides coding agents through a disciplined diagnosis loop for hard bugs: reproduce, minimise, hypothesise, instrument, fix, and regression-test.
A collection of small, composable engineering skills designed for real development workflows, featuring grilling sessions for requirement alignment, issue tracking integration, and task triage with customizable labels.