to-tickets

Files (2)

• SKILL.md
• openai.yaml · agents/

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.

The issue tracker and triage label vocabulary should have been provided to you — run `/setup-skills` if not.

## 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>
**Formal Specifications (`docs/formal-specs/`):**
When decomposing a Formal Spec:
- **Preserve Invariants**: Explicitly assign relevant `INV-1..N` identifiers to each ticket's acceptance criteria (e.g. `- [ ] Satisfies INV-1 (Data integrity)`).
- **Include Edge Cases**: Map corresponding `EDGE-1..N` fail-safe behaviors to the slice handling that boundary.
- **Dedicated Adversarial Slice**: For complex race conditions or property-based tests (`ADV-1..N`), introduce a verification ticket blocked by the core implementation slices.

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 are large, expand, migrate per-package, contract.

### 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 in dependency order (blockers first).

1. **Fetch Repository Labels & Templates**:
   - Read `docs/standards/issue-tracker.md` (or fallback to `docs/agents/issue-tracker.md`) to resolve the repository's active label vocabulary (`status:triage`, `type:*`, `area:*`). If no standard file exists, fallback to common defaults (`type:feat`, `status:triage`).
   - Check if the repository defines custom issue forms in `.github/ISSUE_TEMPLATE/` (e.g. `feature_request.yml`, `task.yml`). If present, structure the ticket body to align with those fields.

2. **Publish Mechanism**:
   - **GitHub Issues via `create-issue.mjs` (Recommended)**:
     ```bash
     node skills/engineering/git-flow/scripts/create-issue.mjs \
       --type task \
       --title "task(<scope>): <summary>" \
       --parent <parent_id> \
       --blocked-by <blocked_by_id> \
       --body-file <ticket_body_file> \
       --execute
     ```
     Automatically validates Conventional Commit title, verifies the single-noun body schema, creates the issue, and attaches it via the GitHub Native Sub-Issues API.
   - **Manual CLI Fallback**: Execute `gh issue create --title "task(<scope>): <summary>" --body "..." --label "type:task"`.
   - **Local files**: Write one file per ticket under `.scratch/<feature-slug>/issues/<NN>-<slug>.md`, numbered from `01` in dependency order.

Work the **frontier**: any ticket whose blockers are all done. Do NOT close or modify any parent issue.
<local-ticket-template>

# <NN> — <type>(<scope>): <Ticket title>

## Context

- Parent: None
- Blocked by: None

## Scope

The end-to-end behaviour this ticket makes work, from the user's perspective — not a layer-by-layer implementation list.

## Acceptance

- [ ] Criterion 1
- [ ] Criterion 2

</local-ticket-template>

<issue-template>

## Context

- Parent: #<parent_number> <!-- Or None if root task -->
- Blocked by: #<blocking_number> <!-- Or None if ready immediately -->

## Scope

The end-to-end behaviour this ticket makes work, from the user's perspective — not a layer-by-layer implementation list.

## Acceptance

- [ ] Criterion 1
- [ ] Criterion 2

</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.

From ngxccc/engineered-skills, MIT.

More from ngxccc/engineered-skills