to-tickets
GitHub将计划或规格说明拆分为可执行的工单，包含验收标准和阻塞依赖。支持本地起草或发布，确保工单为垂直切片且无循环依赖，适用于任务分解与项目管理场景。
Trigger Scenarios
Install
npx skills add nodetool-ai/nodetool --skill to-tickets -g -y
SKILL.md
Frontmatter
{
"name": "to-tickets",
"description": "Split an agreed plan or spec into actionable tickets with acceptance criteria and blocking dependencies. Draft or publish as requested.",
"disable-model-invocation": true
}
To Tickets
Break a plan, spec, or conversation into a set of tickets — tracer-bullet vertical slices, each declaring the tickets that block it.
Use the configured tracker and existing labels. If the publication destination is missing, prepare the tickets locally before asking where to publish. Do not run repository setup as a prerequisite to drafting.
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.
Include preparatory refactoring only when it is necessary to deliver the requested behavior.
3. Draft vertical slices
Break the work into tracer bullet tickets.
- 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
- Sequence necessary preparation before the slices that depend on it
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. Check the breakdown
Check that every acceptance criterion belongs to a ticket and that blocking edges reflect actual dependencies without cycles. Summarize titles, dependencies, and what each ticket delivers.
Use the agreed scope and granularity. If the user asked to create the tickets, continue to publication without a routine approval round. Ask only about an unresolved choice that materially changes the scope or dependencies. If the user asked to review a draft first, deliver the complete draft and wait for that review.
5. Publish the tickets to the configured tracker
Publish when authorized by the request or session context. How depends on the configured tracker — 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 / sub-issue relationship where it has one; otherwise set each ticket's "Blocked by" to the blocking issues. 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.
Keep parent issue changes outside this task unless the user requested them. Read back created tickets and dependency links, then return their URLs or paths. After a partial failure, check which tickets exist before retrying to avoid duplicates.
<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
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".
Include stable source paths when they make a ticket actionable. Prefer links over copied implementation. 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.
Version History
- 9b979bc Current 2026-09-22 23:26
