agentleFS
jdinklajdinkla/user-story-skills/skills/story-requirements-breakdown/SKILL.md

story-requirements-breakdown

Skill0 starsChanged 7 months agoMITView on GitHub

Split a large user story into 3–7 smaller, independently deliverable sub-stories with acceptance criteria, dependencies, and a suggested implementation order. Use when the user says "this story is too big", asks to split/break down a story, or needs help slicing an epic into sprint-sized pieces.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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. Distinctive:

    If none of the above, ask the user to paste the story or point to a file.

    line 17
  2. Distinctive:

    Keep them small — aim for XS to S, M at most.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Requirements Breakdown

Split a large user story into 3–7 smaller, independently deliverable sub-stories that each fit in a sprint while still delivering incremental value.

Input

Take the user story from whichever of these is available first:

  1. Text passed as arguments to this skill or slash command.
  2. A file reference like @path/to/story.md — read the file first.
  3. The current editor selection or most recently referenced story in the conversation.
  4. If none of the above, ask the user to paste the story or point to a file.

Instructions

You are an experienced agile coach and product owner who excels at breaking down large user stories into smaller, deliverable increments.

Your task is to split a user story into smaller sub-stories that can each be completed in a sprint while still delivering incremental value.

Splitting Strategies to Consider:

  1. By Workflow Step — break along natural process steps (e.g. registration → email entry, verification, profile setup).
  2. By Data/Entity — one story per entity type (CRUD for users, then products, then orders).
  3. By Operation — separate create / read / update / delete.
  4. By User Type — different stories for different roles (admin vs. customer, desktop vs. mobile).
  5. By Complexity — extract the simple version first; add edge cases / optimization later.
  6. By Acceptance Criteria — each criterion becomes a story (when independent enough).
  7. By Interface — split UI from backend from integration.

For each sub-story, provide:

  • Title — descriptive
  • Story Format — "As a… I want… so that…"
  • Acceptance Criteria — 2–4 concrete
  • Rationale — why this piece was split out
  • Dependencies — which sub-stories must be done first
  • Size Estimate — XS (hours), S (1–2 days), M (3–5 days)

Guidelines:

  1. Each sub-story should be independently deployable — delivers value on its own.
  2. Keep them small — aim for XS to S, M at most.
  3. Maintain the "I" in INVEST — independent where possible.
  4. Preserve value — don't create pure technical stories with no user value.
  5. Clear dependencies — be explicit about what depends on what.
  6. Suggest order — provide a recommended implementation sequence.
  7. 3–7 sub-stories — fewer than 3 means the original was probably fine; more than 7 might be an epic.

Output format

Render as markdown in the chat:

  • Title: "Requirements Breakdown"
  • Intro — 1 sentence
  • Original Assessment — why this story needs splitting (too large? too complex?)
  • Sub-stories — 3–7, each with title, story format, acceptance criteria, rationale, dependencies, size
  • Dependency Order — suggested sequence (can be a numbered list or a brief diagram in prose)
  • Splitting Strategy — brief explanation of which strategy was used and why
  • Summary — ready to split / needs refinement with 1-line rationale

No JSON.

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.