to-tickets

Files (1)

• SKILL.md

SKILL.md (first lines)

# To Tickets

Break a plan, spec, or conversation into a set of **tickets**: tracer-bullet vertical slices, each declaring the tickets that **block** it.

Default tracker: GitHub Issues, via the `gh` CLI or the `github` MCP. Default triage label: `ready-for-agent`, applied only if that label already exists in the repo — don't create it. If the user names a different tracker (e.g. Linear) for this task, use that instead.

## 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. Sanity/alignment pass

Before publishing, self-check the proposed breakdown against `<vertical-slice-rules>` and the wide-refactor exception above:

- Granularity: no ticket is too coarse (spans more than one context window) or too fine (not independently demoable/verifiable).
- Blocking edges: each ticket depends only on tickets that genuinely gate it — no missing edges, no spurious ones.
- Each slice is vertical (or is correctly sequenced as expand–contract if it's a wide refactor), and prefactoring lands first.

Fix anything the check turns up, then proceed straight to publishing — no need to pause for user approval first. Report the final breakdown to the user as a short numbered list (title, blocked-by, what it delivers) alongside the publish result in step 5, so they see what was created, not a draft to approve.

### 5. Publish the tickets to the configured tracker

Publish the approved tickets. **How** depends on the tracker configured in the user's own `CLAUDE.md`; 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 from `01` in 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 / sub-issue relationship where it has one; otherwise set each ticket's "Blocked by" to the blocking issues. Apply the `ready-for-agent` triage 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)".

</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.

If a ticket needs a credential, reference retrieving it from whatever secrets manager or vault the user's own conventions call for, rather than embedding the value itself or instructing a manual copy-paste.

### 6. Build the frontier

Once tickets are published, work the frontier — any ticket whose blockers are all done — building
in a worktree per the user's own conventions (cap at 2-3 concurrent). For each ticket: build it,
then run your own PR-through-merge/deploy process on it (open a PR, get it reviewed, wait on CI,
merge, deploy, verify) — this skill doesn't assume a specific pipeline command exists in your
setup, so wire in whatever yours is.

If `${user_config.auto_continue}` is true: **canary the first ticket, then run the rest
unattended.** The first frontier ticket built in a given run pauses at your merge-confirmation step
as normal, and after it's merged and verified, report a short status before continuing. Every
subsequent ticket in that same run skips the merge confirmation and proceeds straight through to
merge once CI and review both pass — this is a deliberate, narrower exception to the normal
"confirm before merge" gate, scoped to this loop only.

If `${user_config.auto_continue}` is false (the default): confirm with the user before starting
the build step at all, and confirm again before every merge — no canary/skip behavior.

If review turns up something that isn't a simple local fix — it points to a flaw in the plan or
ticket itself, not just the diff — stop and flag it to the user rather than looping fixes or
merging around it. Move to the next frontier ticket only once the current one is fully merged and
verified, repeating until every ticket is done.

From jpol34/polyak-dev-kit, MIT.

More from jpol34/polyak-dev-kit