to-issues

Breaks plans and PRDs into independently-grabbable vertical-slice implementation issues.

1|2|Updated Nov 25, 2017
One-click install
npx skills add https://github.com/asarchami/dotfiles --skill to-issues-asarchami
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: to-issues
Source: https://github.com/asarchami/dotfiles/tree/main/dot_claude/skills/to-issues
Command: npx skills add https://github.com/asarchami/dotfiles --skill to-issues-asarchami

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a plan, spec, or PRD into actionable work items is hard: horizontal layer-by-layer tickets create dependencies and nothing is demoable until the end. This Skill decomposes source material into thin vertical slices that each cut through all layers and can be implemented, tested, and merged independently. ## Core Features & Use Cases - Vertical Slice Decomposition: Converts PRDs and specs into tracer-bullet issues that are each demoable on their own, with HITL/AFK typing and explicit dependency ordering. - Deep Module Awareness: Respects module boundaries from the PRD, ensuring deep modules are built as isolated early slices and thin binaries compose them afterward. - Interactive Refinement: Interviews the user one question at a time about scope, blockers, user stories, and acceptance criteria before publishing. - Use Case: After writing a PRD for a new service, ask the assistant to break it into issues; you receive a numbered, dependency-ordered issue set with acceptance criteria and a Mermaid dependency graph grouped by phase. ## Quick Start Ask the assistant to break the attached PRD into vertical-slice implementation issues with dependencies and acceptance criteria.

Frequently Asked Questions about to-issues

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I break a PRD into implementation issues?

Provide the PRD as source material and the Skill drafts vertical slices, then interviews you one question at a time about scope, blockers, and acceptance criteria. Approved slices are published in dependency order with a Mermaid dependency graph.

What is a vertical slice issue versus a horizontal slice?

A vertical slice cuts through all integration layers end-to-end, such as schema, API, UI, and tests, so it is demoable on its own. Horizontal slices cover one layer only and cannot be verified independently.

What is the difference between HITL and AFK slices?

HITL slices require human interaction such as an architectural decision or design review. AFK slices can be implemented and merged without human interaction, and the Skill prefers AFK wherever possible.

How does the Skill handle module boundaries when splitting work?

It treats deep modules as their own early slices so they are built and tested before any service depends on them. Shallow modules can bundle with other slices, and thin cmd binaries become slices that compose already-built deep modules.

When should I not use vertical slice decomposition?

Avoid splitting a single deep module across multiple slices, since that exposes internal complexity and undermines its narrow interface. Very small tasks with no integration layers may not benefit from slicing at all.