Skip to content

To-Tickets skill

Split a specification into demonstrable vertical slices with explicit blocking dependencies.

Community · Matt Pocock
AuthorMatt Pocock
LicenceMIT
Sourcemattpocock/skills · SKILL.md on GitHub
Project websitewww.aihero.dev/skills-to-tickets
Works inClaude Code · Codex, Gemini CLI, Cursor, Copilot
Read from the source on

The to-tickets skill converts a plan, specification or current conversation into tickets sized for a fresh agent session. Each ticket is a thin end-to-end behavior, rather than an isolated database or UI layer.

It proposes the breakdown for approval before publication and declares blocking dependencies. Local mode writes separate Markdown files; remote mode uses tracker relationships where available.

From the skill's SKILL.md: ## Acceptance criteria

This is a community skill by Matt Pocock, not checked by us or by Anthropic. Skills can tell the agent to run code, read files or call the network. Before installing, read its SKILL.md and every script in the folder, and look for anything that does not match what it says it does.

What it does

  1. Read the source context and identify prefactoring and vertical slices.
  2. Present numbered tickets and blockers for review before publication.
  3. Create approved tickets in dependency order without implementing them.

What you get

  • Local files under .scratch/<feature>/issues/<NN>-<slug>.md or remote tracker tickets with blocking relationships.

When to use it

  • Divide an agreed multi-session feature into independently demonstrable work.

When not to use it

  • A tiny change that does not benefit from a ticket graph.

What it needs

  • A file-capable coding agent and the setup-matt-pocock-skills tracker configuration.
  • Remote publication requires authenticated tracker tools and authorization; local mode needs write access only.

Files in the skill

File or folderWhat it is for
SKILL.mdVertical slicing, approval, ticket template and dependency publication.

Licence as found in the repository on 2026-11-19: MIT.

Example prompts

Type one of these after installing; naming the skill makes sure it is used.

  • /to-tickets — split this spec into end-to-end slices and show blockers before publishing.
  • /to-tickets #42 — make every acceptance criterion independently observable.
  • /to-tickets — plan this wide rename using expand, migrate and contract stages.

How to install to-tickets

Installation and permissions

Install the skill and set up the tracker configuration. Refresh older tracker templates if native blocking links or parent relationships are missing.

Invocation is manual. Review ticket size and acceptance criteria at the approval step; the skill publishes artifacts but does not dispatch implementers.

A skill is a folder with a SKILL.md file. You install it once; the agent reads its short description at the start of each session and loads the full instructions only when a request matches. Pick the place you use:

Claude Code: copy the folder into your skills folder

Put the skill's folder in ~/.claude/skills/ to use it in every project on this computer, or in .claude/skills/ inside a repository to share it with everyone who works there (commit it).

git clone --depth 1 https://github.com/mattpocock/skills.git
mkdir -p ~/.claude/skills
cp -R skills/skills/engineering/to-tickets ~/.claude/skills/

Claude Code notices new or changed skills in these folders during the session. If the skills folder did not exist when the session started, run /reload-skills once. Then type /to-tickets or just describe the task.

On Windows, run the commands in Git Bash or WSL, or copy the folder into the same place with File Explorer.

Codex, Gemini CLI, Cursor and GitHub Copilot

These agents read the same SKILL.md folders. The one folder all four accept inside a project is .agents/skills/, so this copies the skill there:

git clone --depth 1 https://github.com/mattpocock/skills.git
mkdir -p .agents/skills
cp -R skills/skills/engineering/to-tickets .agents/skills/
AgentProject folderYour user folderNotes
OpenAI Codex
.agents/skills/
~/.agents/skills/
Type $ or run /skills to pick a skill; Codex also chooses one when your task matches.
Gemini CLI
.agents/skills/
.gemini/skills/
~/.agents/skills/
~/.gemini/skills/
Or install from Git with gemini skills install <git URL> --path <folder> --consent. Google replaced Gemini CLI with Antigravity CLI for free-tier and Google One users on 18 June 2026; Antigravity uses .agents/skills/ in a project and ~/.gemini/config/skills/ for you.
Cursor
.agents/skills/
.cursor/skills/
~/.agents/skills/
~/.cursor/skills/
Type / in Agent chat to pick a skill. Cursor also reads Claude Code's .claude/skills/ folders.
GitHub Copilot
.github/skills/
.agents/skills/
.claude/skills/
~/.copilot/skills/
~/.agents/skills/
Works in Copilot CLI, the cloud agent, and agent mode in VS Code, Visual Studio and JetBrains (IDE support depends on the version). Or run gh skill install OWNER/REPOSITORY SKILL (public preview, GitHub CLI 2.90.0 or later).
Only install skills you trust. Anthropic's advice is to use skills only from trusted sources, and to read every file of any other skill before using it: a skill can direct the agent to run commands, read files or send data in ways its description does not mention.

Sources for these steps

Checked against each vendor's documentation on 2026-11-14:

Review the graph before publishing

Ask what can be demonstrated when each ticket finishes. Merge excessive fragments and confirm that blockers reflect real dependencies.

Check that each acceptance criterion can fail before implementation. A criterion already satisfied at the starting commit provides weak completion evidence.

Questions about to-tickets

Does it implement the tickets?

No. It produces the ticket graph. Execution is a separate step.

Can it use local files?

Yes. Local mode writes one numbered Markdown file per ticket in dependency order.

What makes a vertical slice useful?

It delivers a thin path across the required layers that can be demonstrated and verified on its own.

How does it handle wide refactors?

The source allows expand–migrate–contract sequencing, or an integration branch with final verification when individual batches cannot stay green.

More AI skills

Related skills

Skill categories