to-tickets · Skill Details

Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger: User-invoked when a plan/spec or well-developed discussion needs to be broken into actionable tickets. In /ask-matt's main flow, /to-spec is followed by /to-tickets, then each ticket is implemented sequentially via /implement.
Mechanism: 4 steps: (1) Gather context — from conversation or user-provided spec path/issue URL; (2) Optionally explore codebase — understand current state, look for prefactoring opportunities; (3) Draft vertical slices — each slice is a complete schema→API→UI→test path, independently demoable, sized for one context window. Wide refactors use expand→contract pattern instead of vertical slicing; (4) Quiz the user — show the breakdown (title, blocking edges, deliverables), confirm granularity and dependencies, iterate until approved; (5) Publish — local files as .scratch/<feature>/issues/<NN>-<slug>.md, real tracker as issues with native blocking relationships.
Output: A dependency-sorted set of tickets (local files or tracker issues), each declaring exact blocking edges and acceptance criteria. The user works the "frontier" — starting with unblocked tickets.

Use Cases

Two Typical Use Cases

Scenario 01

Breaking a large spec into executable tickets

A PM completes a complex spec with 30 user stories. The developer invokes `/to-tickets` to break it into executable tickets. The skill splits vertically (each ticket spans schema to UI), each independently demoable, with the first unblocked ticket immediately actionable. For wide refactors like database column renames, uses expand → migrate → contract mode. The breakdown is shown to the PM for confirmation before publishing to GitHub Issues.

Scenario 02

Breaking down personal tasks during local development

An indie developer working on a medium-sized feature doesn't want to use GitHub Issues. Invoking `/to-tickets` with "local markdown" as tracker. The skill splits the feature into tickets, each as a file under `.scratch/<feature>/issues/`, numbered from 01 in dependency order. Each file contains "What to build", "Blocked by", and acceptance criteria. The developer works the "frontier" — starting with unblocked tickets.

Skill Relationships

Which Skills I Use · Which Skills Use Me

Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.

Tier 1 · These Skills Use Me

ask-mattWorkflow

Tier 2 · Current Skill

to-ticketsWorkflow

Tier 3 · I Use These Skills

No explicit dependency on other Skills

Full Relationship Graph

Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.

Skill File

SKILL.md

Open in GitHub ↗

SKILL.mdLoading from GitHub…

Skill Composition

Open in GitHub ↗

SKILL.md50.0%
other50.0%

▸skills/to-tickets/
▸to-tickets
- ·SKILL.md
- ▸agents
  - ·openai.yaml

Per the Agent Skills spec, SKILL.md is the only required file. The colored bars classify the rest into the three spec-aligned optional directories (scripts / references / assets) and an 'other' bucket. The full directory tree is below.

Related in Skillset

You May Also Need These Skills

ask-matt

A router skill for the entire skillset: when the user can't remember which skill to use or which flow fits their situation, they invoke this to get a recommendation. It describes the main "idea → ship" flow (grill-with-docs → to-spec/to-tickets → implement), plus on-ramps (triage, diagnosing-bugs, wayfinder), codebase health (improve-codebase-architecture), vocabulary layers (domain-modeling, codebase-design), and standalone skills (grill-me, prototype, research, teach). Following its map leads users to the correct workflow entry point.

Workflow

code-review

A two-axis code review skill: reviews a diff (from a fixed point to HEAD) along both Standards (coding standards + Fowler smell baseline) and Spec (faithful implementation of the originating issue/PRD). Both axes run as parallel sub-agents to avoid context pollution. The report aggregates findings without merging conclusions, ensuring "passes standards but implements the wrong thing" and "implements the right thing but breaks conventions" are both surfaced independently.

Workflow

codebase-design

A shared vocabulary skill for deep module design: provides a precise set of design terms (Module, Interface, Depth, Seam, Adapter, Leverage, Locality) guiding agents and developers to design "deep modules" — a lot of behaviour behind a small interface. Includes design principles (the deletion test, the interface is the test surface) and testability guidelines. A reference skill consumed by other skills (e.g., improve-codebase-architecture, tdd) and invoked directly by engineers.

Style Guide

diagnosing-bugs

A disciplined diagnosis loop for hard bugs and performance regressions. The core idea is to first build a tight feedback loop — no hypothesis phase without one. Six phases: build feedback loop → reproduce + minimise → generate 3-5 falsifiable hypotheses → instrument by prediction → fix + regression test → cleanup + post-mortem. If the codebase architecture can't lock down the bug, it recommends handing off to the improve-codebase-architecture skill.

Workflow