Epic Breakdown Advisor
Run an interactive epic split using Humanizing Work’s nine patterns so oversized backlog items become vertical, sprint-sized user stories.
Overview
Epic Breakdown Advisor is an agent skill most often used in Validate (also Build) that applies Humanizing Work’s nine story-splitting patterns to turn epics into vertical user stories.
Install
npx skills add https://github.com/deanpeters/product-manager-skills --skill epic-breakdown-advisorWhat is this skill?
- Richard Lawrence Humanizing Work methodology with a systematic flowchart-driven sequence
- 9 splitting patterns applied sequentially to preserve user value and avoid horizontal layers
- Interactive PM skill: choose pattern, split, and evaluate reveals of low-value work to cut
- Vertical slicing emphasis—end-to-end user value per story, not technical layer tickets
- Built for epics too large to estimate, sequence, or deliver safely in one sprint
- 9 Humanizing Work splitting patterns applied sequentially
Adoption & trust: 1.2k installs on skills.sh; 5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have an epic that is too big to estimate or ship safely, and horizontal technical slices hide missing user value.
Who is it for?
Solo builders wearing the PM hat who need a structured, value-preserving split before backlog refinement or agent-driven implementation plans.
Skip if: Single tiny tasks already story-sized, pure engineering refactors with no user-facing narrative, or teams that forbid interactive facilitation-style PM skills.
When should I use this skill?
A backlog item is too large to estimate, sequence, or deliver safely and you need Humanizing Work story splits.
What do I get? / Deliverables
You leave with pattern-selected, vertically sliced user stories and clarity on low-value scope to drop before implementation or sprint planning.
- Set of vertically sliced user stories
- Notes on low-value work revealed by splits
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Validate is the canonical shelf because unscoped epics block estimation and commitment before full build; the same skill repeats at build/pm during sprint planning. Scope subphase covers defining deliverable slices and story size before engineering starts—not after code exists.
Where it fits
Shrink a vague onboarding epic into estimable stories before you approve an implementation plan.
Re-split an oversized reporting epic the night before sprint planning so the agent implements one vertical slice first.
Decide which thin slice of an admin workflow proves the concept without building every permission layer.
Break a retention or lifecycle initiative into shippable experiments instead of one quarter-long epic.
How it compares
Structured epic-splitting facilitator—not a generic writing-plans or task-list generator for already-approved specs.
Common Questions / FAQ
Who is epic-breakdown-advisor for?
Product-minded solo builders and indie PMs breaking large epics into estimable user stories using a proven splitting methodology.
When should I use epic-breakdown-advisor?
In Validate when scoping a feature too large to commit; in Build/pm before sprint planning for onboarding, reporting, or admin workflow epics; whenever splits must stay vertical.
Is epic-breakdown-advisor safe to install?
It is procedural PM guidance with no special system access; still review Prism Security Audits and the upstream skill repo before use.
SKILL.md
READMESKILL.md - Epic Breakdown Advisor
## Purpose Guide product managers through breaking down epics into user stories using Richard Lawrence's complete Humanizing Work methodology—a systematic, flowchart-driven approach that applies 9 splitting patterns sequentially. Use this to identify which pattern applies, split while preserving user value, and evaluate splits based on what they reveal about low-value work you can eliminate. This ensures vertical slicing (end-to-end value) rather than horizontal slicing (technical layers). This is not arbitrary slicing—it's a proven, methodical process that starts with validation, walks through patterns in order, and evaluates results strategically. ## Key Concepts ### Core Principles: Vertical Slices Preserve Value A user story is "a description of a change in system behavior from the perspective of a user." Splitting must maintain **vertical slices**—work that touches multiple architectural layers and delivers observable user value—not horizontal slices addressing single components (e.g., "front-end story" + "back-end story"). ### The Three-Step Process 1. **Pre-Split Validation:** Check if story satisfies INVEST criteria (except "Small") 2. **Apply Splitting Patterns:** Work through 9 patterns sequentially until one fits 3. **Evaluate Splits:** Choose the split that reveals low-value work or produces equal-sized stories ### The 9 Splitting Patterns (In Order) 1. **Workflow Steps** — Thin end-to-end slices, not step-by-step 2. **Operations (CRUD)** — Create, Read, Update, Delete as separate stories 3. **Business Rule Variations** — Different rules = different stories 4. **Data Variations** — Different data types/structures 5. **Data Entry Methods** — Simple UI first, fancy UI later 6. **Major Effort** — "Implement one + add remaining" 7. **Simple/Complex** — Core simplest version first, variations later 8. **Defer Performance** — "Make it work" before "make it fast" 9. **Break Out a Spike** — Time-box investigation when uncertainty blocks splitting ### Meta-Pattern (Applies Across All Patterns) 1. Identify the core complexity 2. List all variations 3. Reduce variations to **one complete slice** 4. Make other variations separate stories ### Why This Works - **Prevents arbitrary splitting:** Methodical checklist prevents guessing - **Preserves user value:** Every story delivers observable value - **Reveals waste:** Good splits expose low-value work you can deprioritize - **Repeatable:** Apply to any epic consistently --- ### Facilitation Source of Truth Use [`workshop-facilitation`](../workshop-facilitation/SKILL.md) as the default interaction protocol for this skill. It defines: - session heads-up + entry mode (Guided, Context dump, Best guess) - one-question turns with plain-language prompts - progress labels (for example, Context Qx/8 and Scoring Qx/5) - interruption handling and pause/resume behavior - numb