AGENT SKILL

to-tickets

Break a plan, spec, or the current conversation into tracer-bullet tickets, each declaring its blocking edges, published to the project's issue tracker. Use when the user asks to split a spec or plan into tickets or issues.

License 许可
MIT
所属仓库
drsh4dow/pi-setup
最近更新
2026-11-03
Stars
★ 10
Forks
2

01 前言 Front Matter

name
to-tickets
description
Break a plan, spec, or the current conversation into tracer-bullet tickets, each declaring its blocking edges, published to the project's issue tracker. Use when the user asks to split a spec or plan into tickets or issues.
user-invokable
true
disable-model-invocation
false

03 SKILL.md 正文

To Tickets

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

Read the project's issue tracker record, docs/agents/issue-tracker.md. If it is missing, stop and tell the user to run the setup-sh4dow-skills skill.

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, as docs/agents/domain.md describes.

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 one ticket per approved slice, in dependency order (blockers first), so each ticket's blocking edges can reference real identifiers. Use the issue tracker record's operations: Publish for each ticket, Block for each edge (or its fallback where the tracker has none), and Nest under a parent when the source was an existing issue. The record says how each maps onto its tracker, including a local one.

Write each ticket's body per the writing-good-tickets skill, and pass its body check before you publish. The body's sections carry the breakdown:

  • ## Problem: the story of what the user cannot do today and what that costs them, end to end, not a layer-by-layer implementation list.
  • ## Done when: the behavior this slice delivers, each item with the check that shows it.

Relate the parent issue and the blocking tickets through the tracker record's Nest under a parent and Block operations, so the body carries no list of issues.

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.

Tell the user each ticket's identifier or URL, with its blocking edges.

04 同仓库更多 Skills