agentleFS
Sign inStart free
mikezamayiasmikezamayias/agent-skills/skills/moscow-prioritization/SKILL.md

moscow-prioritization

Skill1 starsChanged 28 days agoBSD-3-ClauseView on GitHub

Cuts a noisy backlog with MoSCoW (Must / Should / Could / Won't). Use when the backlog has more than 30 items, when standups feel pointless, or before any sprint kickoff.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Must is rare: If more than 60% of items are Must, you haven't prioritized — you're hoping.

    line 18
  2. Distinctive:

    Won't is mandatory: Every triage must move at least 3 items into Won't.

    line 19
  3. Distinctive:

    One MoSCoW per cycle: Don't ladder-rank inside a bucket.

    line 21
  4. Distinctive:

    Must = ship this week.

    line 27
  5. Distinctive:

    Should = ship next week.

    line 28
  6. Distinctive:

    Run the triage at the start of each week, before opening any code.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

MoSCoW Prioritization

A backlog with no priority is a graveyard. MoSCoW forces you to commit. Every item lands in exactly one of four buckets:

  • Must — release fails without it. Non-negotiable.
  • Should — important but the release survives. Cut first under pressure.
  • Could — nice if time remains. Default = won't happen.
  • Won't (this cycle) — explicitly deferred. The honesty bucket.

The rules that make it work

  1. Must is rare. If more than 60% of items are Must, you haven't prioritized — you're hoping. Cut Musts until the sum fits in the cycle's capacity.
  2. Won't is mandatory. Every triage must move at least 3 items into Won't. If nothing is dropped, nothing was decided.
  3. Re-rank weekly. Priorities decay. A Must from last week may be a Could now.
  4. One MoSCoW per cycle. Don't ladder-rank inside a bucket. The point is the cut, not the ordering.

Solo founder usage

For one person, the practical mapping:

  • Must = ship this week.
  • Should = ship next week.
  • Could = unscheduled.
  • Won't = archived (with a date — review next quarter).

Run the triage at the start of each week, before opening any code.

Anti-patterns

  • "P0 / P1 / P2 / P3" with no time bound — nothing forces a cut.
  • Endless re-ordering instead of dropping items.
  • Treating MoSCoW as a label instead of a commitment.

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.

Check your setup, free