agentleFS
pumpkit-iopumpkit-io/sdlc/skills/commands/to-tickets/SKILL.md

to-tickets

Skill2 starsChanged 11 days agoMITView on GitHub

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).

192 other projects use a version of this, 158 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-ts-deep-modules, to-questionnaire and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 43 projects that use this

  • AWSSkill

    to-questionnaire

    Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

    Also in 89 projects that use this

  • ryotaroh180105Skill

    claude-handoff

    Hand the current conversation off to a fresh background agent that picks up the work immediately.

    Also in 40 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 47 projects that use this

  • AWSSkill

    wizard

    Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

    Also in 108 projects that use this

  • sponge-b0bSkill

    to-specs

    Project decision-complete planning into implementation Specs from exact Canonical Contract Ledger semantics while preserving Independent Specs and existing Spec identity.

    Also in 3 projects that use this

  • +1 more from aws

The file

We split this skill into the rules it gives an agent

4 rules. 2 are common, 2 are distinctive, and 0 are very specific to this project.

  • 2

    Common

    Most of the 181 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Common:

    If you have not already explored the codebase, do so to understand the current state of the code.

    line 23
  2. Common:

    Look for opportunities to prefactor the code to make the implementation easier.

    line 25
  3. Distinctive:

    Keep a slice whole when splitting would leave pieces below a floor, where the pull requests would be trivial (a one-line change, a rename …

    line 37
  4. Distinctive:

    Check every ticket against the vertical-slice rules, and check that each blocking edge names a ticket this one cannot start without.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 181 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
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 should have been provided to you. If not, tell the user to run /setup-sdlc.

Load the worktrees skill and resolve the worktree for this work before writing anything.

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 one reviewable behavior change, because each ticket becomes one pull request in the Stack. The soft ceiling is roughly 300 changed lines.
  • Split a slice above the ceiling when a clean seam exists and each piece can still land green on its own.
  • Keep a slice whole when splitting would leave pieces below a floor, where the pull requests would be trivial (a one-line change, a rename on its own).
  • Merge a slice into a neighbor when it cannot land safely alone.
  • Any prefactoring is done first, as its own ticket.
</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.

Give each ticket a Touches: line naming the areas of the code it changes, by area and not by file path (for example "auth middleware, session schema"). Step 5 reads these lines to decide which tickets can be built side by side.

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. The expand, the batches and the contract are tickets in the same Stack, like any others.

4. Check the breakdown

Check every ticket against the vertical-slice rules, and check that each blocking edge names a ticket this one cannot start without. Fix what the check turns up. A question the source left open goes under Open questions in the ticket it affects.

5. Group the tickets into the Implementation flow

Sort the tickets into Groups. Work level by level through the blocking edges: a ticket joins the earliest level in which all its blockers sit in earlier Groups. When tickets of one level have overlapping Touches: lines, split the level into several Groups so that no two tickets in a Group overlap. A Group may hold a single ticket.

The ordered Groups are the Implementation flow. Inside a Group, chain order is ticket-number order. Number the tickets in flow order (Group by Group, then by chain order), so blockers always come first.

Each ticket's Stacks on: line names the ticket before it in the flow. The first ticket stacks on the feature branch, or on main when the grilling wrote no docs and the branch holds none. Check that no two tickets in a Group overlap in Touches: and that every Stacks on: target precedes its ticket in the flow.

6. Publish the tickets to the configured tracker

Load the prose-style skill and write every ticket body in that style. A ticket that builds UI points to the spec's UI Design section instead of restating the design. Every ticket starts with the spec's Feature branch link (Branch: <branch>), copied as it is; without a spec, the link names the branch this session's worktree is on.

Publish the tickets in flow order. How depends on the tracker /setup-sdlc 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 from 01 in flow 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 flow order (blockers first) so each ticket's blocking edges and Stacks on: line 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, with one exception: when the source is a Spec on the tracker, append the Implementation flow to its ## Implementation flow section, replacing the placeholder to-spec left there, and change nothing else in the body. With a local-file Spec, fill the same section in the file. Write the flow as the ordered Groups, each listing its tickets by link or number and title.

<local-ticket-template>

<NN>: <Ticket title>

Branch: <feature branch>

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)".

Touches: the areas of the code this ticket changes.

Stacks on: the ticket before this one in the Implementation flow, or the feature branch (main when there are no grilling docs) for the first ticket.

Status: ready-for-agent

  • Acceptance criterion 1
  • Acceptance criterion 2

Open questions: anything the source left unsettled that the implementer must decide. Omit when there are none.

</local-ticket-template><issue-template>

Branch: <feature branch>

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

Stack

  • Group: the Group's number in the Implementation flow
  • Touches: the areas of the code this ticket changes
  • Stacks on: the ticket before this one in the flow, or the feature branch (main when there are no grilling docs) for the first ticket

Blocked by

  • A reference to each blocking ticket, or "None (can start immediately)".

Open questions

Anything the source left unsettled that the implementer must decide. Omit this section when there are none.

</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.

Finishing

The published tickets and the Implementation flow section are this skill's only output. Close by listing the Implementation flow: each Group in order, and in each Group its tickets with title, link (or file path, for local files), blockers and Stacks on: target. Then name the next step: a fresh session per ticket with implement <ticket>, in flow order, or implement-spec <spec> to run the whole flow unattended. Last, release this session's worktree lock, as the worktrees skill's Release section says.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.