agentleFS
tarikhamiltontarikhamilton/claude-skills/skills/work-breakdown/SKILL.md

work-breakdown

Skill0 starsChanged 5 months agoMITView on GitHub

Work breakdown and scoping. Use when the user asks to break down a feature, plan implementation, scope work, create milestones, write tickets, decompose a task, or assess feature parity for planning. Triggers on "break down", "plan", "scope", "milestones", "tickets", "work breakdown", "feature parity", "break this into", "decompose".

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 3 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. Distinctive:

    Before breaking anything down:

    line 12
  2. Distinctive:

    If a ticket requires shared infrastructure (new API endpoint, shared types), that ticket comes first.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 3 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

Work Breakdown

You are producing a structured work breakdown for a feature or project. Follow every section in order.

Scope Discovery

Before breaking anything down:

  1. Clarify the goal — restate the objective in one sentence. Confirm with the user.
  2. Identify boundaries — what apps/packages/areas are in scope? (e.g., mobile only, web + mobile, API + web)
  3. Detect project structure — scan for monorepo layout (apps/, packages/), shared code, platform-specific dirs.
  4. Inventory existing work — grep for partial implementations, TODOs, and related features already built.

Output: Breakdown Document

Produce a structured breakdown with these sections:

Milestones

Ordered phases, each independently shippable. Format:

### M1: <milestone name>
> <1-sentence goal>
> Depends on: none | M<N>

Tickets

Under each milestone, small mergeable units. Format:

#### T1.1: <ticket title>
- **Files**: list of files likely touched
- **Acceptance criteria**: bullet list of "it should..." statements
- **Verify**: how to confirm it works (test command, manual check, screenshot)
- **Estimate**: S / M / L (relative complexity)

Out of Scope

Explicit list of things NOT included. This prevents scope creep. Format as a bullet list with a brief reason for each exclusion.

Rules

  • Tickets must be small enough to complete in a single session (prefer S/M, flag L tickets as candidates for further splitting).
  • Each ticket should be independently mergeable — no ticket leaves the app in a broken state.
  • Order tickets by dependency, not priority.
  • If a ticket requires shared infrastructure (new API endpoint, shared types), that ticket comes first.
  • Reference existing skills: use refactor-and-safety-pass if a ticket involves renaming/moving, release-helper for version bumps.

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.