Spec to tickets
Splits a spec, plan or conversation into tracer-bullet tickets, vertical slices that each fit one agent session, with blocking edges, and publishes them as local files or tracker issues. Use when work is too big for one session and needs a task graph.
to-tickets- Author
- Matt Pocock
- Source
- mattpocock/skills/skills/engineering/to-tickets @ abeeaf9
- License
- MIT · Copyright (c) 2026 Matt Pocock
About this skill
What it does
To-tickets breaks a spec, a plan or the current conversation into tracer-bullet tickets. Each is a vertical slice through every layer (schema, API, UI, tests) that can be verified on its own and fits one fresh agent context window, and each lists the tickets that block it. Prefactoring goes first: "make the change easy, then make the easy change".
A wide refactor, such as a rename that breaks thousands of call sites at once, becomes expand–contract instead: add the new form beside the old, migrate call sites in batches, one ticket each, then delete the old form in a ticket blocked by every batch.
First the agent shows a numbered list (title, blocked by, what it delivers) and asks about granularity, edges and splits until you approve. On a real tracker it creates one issue per ticket in dependency order, with native blocking links where they exist, as sub-issues of the source issue, labelled ready-for-agent. Otherwise it writes one file per ticket under .scratch/<feature-slug>/issues/. The parent issue is never closed or edited.
When to use it, and when not
Use it when a settled spec is too big for one session, especially if several agents should work unblocked tickets in parallel.
Skip it for a change that fits one session or a spec still in flux. It expects to know the tracker and labels: the author's setup-matt-pocock-skills configures that but is not in our catalog, or you tell the agent to use local files or a tracker you name.
How to run it
The install command below puts the whole folder in place. With disable-model-invocation: true it runs only when called:
- Claude Code: only the
/to-ticketscommand — naming the skill in a message will not start it. - Codex:
$to-tickets. - Cursor: type
/in the Agent chat and pickto-tickets.
Pass a spec path, issue number or URL and the agent reads its body and comments. Example: /to-tickets #214 Split this spec into tickets on GitHub.
Input usually comes from Conversation to spec, and Implement a spec works the resulting ticket graph; install them together.
How it differs from similar skills
Planning and task breakdown also slices vertically and orders tasks by a dependency graph, but writes tasks/plan.md and tasks/todo.md by default, sizes tasks by files touched and adds checkpoints. To-tickets sizes by context window, keeps file paths out and has the expand–contract rule for wide refactors. Writing implementation plans spells out exact files, signatures and test steps instead. Linear issues and projects creates and updates issues only in Linear, through its MCP server, with sample workflows such as release planning but no rules for slicing work. Wayfinder for huge work by the same author is for work not yet understood: its tickets are decisions to make, not slices to build.
Install
Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.
curl -fsSL --create-dirs -o ~/.claude/skills/to-tickets/SKILL.md https://anymodel.org/en/skills/matt-pocock/to-tickets/SKILL.md -o ~/.claude/skills/to-tickets/LICENSE https://anymodel.org/en/skills/matt-pocock/to-tickets/LICENSE -o ~/.claude/skills/to-tickets/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/to-tickets/agents/openai.yaml
curl -fsSL --create-dirs -o ~/.agents/skills/to-tickets/SKILL.md https://anymodel.org/en/skills/matt-pocock/to-tickets/SKILL.md -o ~/.agents/skills/to-tickets/LICENSE https://anymodel.org/en/skills/matt-pocock/to-tickets/LICENSE -o ~/.agents/skills/to-tickets/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/to-tickets/agents/openai.yaml
foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml') { $p = Join-Path "$HOME\.claude\skills\to-tickets" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/to-tickets/$f" -UseBasicParsing -OutFile $p }foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml') { $p = Join-Path "$HOME\.agents\skills\to-tickets" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/to-tickets/$f" -UseBasicParsing -OutFile $p }Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/matt-pocock/to-tickets/SKILL.md
SKILL.md
To Tickets
Break a plan, spec, or conversation into a set of tickets: tracer-bullet vertical slices, each declaring the tickets that block it.
The issue tracker and triage label vocabulary should have been provided to you. If not, tell the user to run /setup-matt-pocock-skills.
Process
1. Gather context
Work from whatever is already in the conversation context. If the user passes a reference (a spec path, an issue number or URL) as an argument, fetch it and read its full body and comments.
2. Explore the codebase (optional)
If you have not already explored the codebase, do so to understand the current state of the code. Ticket titles and descriptions should use the project's domain glossary vocabulary, and respect ADRs in the area you're touching.
Look for opportunities to prefactor the code to make the implementation easier. "Make the change easy, then make the easy change."
3. Draft vertical slices
Break the work into tracer bullet tickets.
<vertical-slice-rules>
- Each slice cuts a narrow but COMPLETE path through every layer (schema, API, UI, tests): vertical, NOT a horizontal slice of one layer
- A completed slice is demoable or verifiable on its own
- Each slice is sized to fit in a single fresh context window
- Any prefactoring should be done first
</vertical-slice-rules>
Give each ticket its blocking edges: the other tickets that must complete before it can start. A ticket with no blockers can start immediately.
Wide refactors are the exception to vertical slicing. A wide refactor is one mechanical change (rename a column, retype a shared symbol) whose blast radius fans across the whole codebase, so a single edit breaks thousands of call sites at once and no vertical slice can land green. Don't force it into a tracer bullet; sequence it as expand–contract. First expand: add the new form beside the old so nothing breaks. Then migrate the call sites over in batches sized by blast radius (per package, per directory), each batch its own ticket blocked by the expand, keeping CI green batch to batch because the old form still exists. Finally contract: delete the old form once no caller remains, in a ticket blocked by every migrate batch. When even the batches can't stay green alone, keep the sequence but let them share an integration branch that all block a final integrate-and-verify ticket; green is promised only there.
4. Quiz the user
Present the proposed breakdown as a numbered list. For each ticket, show:
- Title: short descriptive name
- Blocked by: which other tickets (if any) must complete first
- What it delivers: the end-to-end behaviour this ticket makes work
Ask the user:
- Does the granularity feel right? (too coarse / too fine)
- Are the blocking edges correct: does each ticket only depend on tickets that genuinely gate it?
- Should any tickets be merged or split further?
Iterate until the user approves the breakdown.
5. Publish the tickets to the configured tracker
Publish the approved tickets. How depends on the tracker /setup-matt-pocock-skills configured; the tickets are the same either way, only the shape of the blocking edges changes:
- Local files → write one file per ticket under
.scratch/<feature-slug>/issues/<NN>-<slug>.md, numbered from01in dependency order (blockers first). Each file's "Blocked by" lists the numbers/titles it depends on. Use the per-ticket file template below: one ticket per file, never a single combined file. - A real issue tracker (GitHub, Linear, …) → publish one issue per ticket in dependency order (blockers first) so each ticket's blocking edges can reference real identifiers. Use the platform's native blocking relationship where it has one; otherwise set each ticket's "Blocked by" to the blocking issues. If the source was an existing issue, make each ticket its sub-issue (tracker doc's operation). Apply the
ready-for-agenttriage label unless instructed otherwise; the tickets are agent-grabbable by construction.
Work the frontier: any ticket whose blockers are all done. For a purely linear chain that means top to bottom.
Do NOT close or modify any parent issue.
<local-ticket-template>
<NN>: <Ticket title>
What to build: the end-to-end behaviour this ticket makes work, from the user's perspective, not a layer-by-layer implementation list.
Blocked by: the numbers/titles of the tickets that gate this one, or "None (can start immediately)".
Status: ready-for-agent
- Acceptance criterion 1
- Acceptance criterion 2
</local-ticket-template>
<issue-template>
Parent
A reference to the parent issue on the tracker (if the source was an existing issue, otherwise omit this section).
What to build
The end-to-end behaviour this ticket makes work, from the user's perspective, not layer-by-layer implementation.
Acceptance criteria
- Criterion 1
- Criterion 2
Blocked by
- A reference to each blocking ticket, or "None (can start immediately)". Omit this section when blockers were set as native edges.
</issue-template>
In either form, avoid specific file paths or code snippets: they go stale fast. Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it and note briefly that it came from a prototype. Trim to the decision-rich parts, not a working demo, just the important bits.
Connect through AnyModel API
This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.
AnyModel