agentsclimarketplace

Prioritization frameworks

Skill Dragoon0x/product-skills/skills/organisation-prioritization/prioritization-frameworks

The product thinking layer for AI agents. 580 skills. 48 commands. 8 domains. - Product strategy, discovery, execution, analytics, growth, experience, conversion, communication and more.

Install
npx -y skills add Dragoon0x/product-skills --skill prioritization-frameworks

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Apply structured prioritization methods to decide what to build and what to cut. Covers RICE, ICE, MoSCoW, and knowing when each framework fits. Use when the backlog is overwhelming, stakeholders disagree on priorities, or when everything feels like P0.

SKILL.md

2.8 KB, 532 tokens by cl100k_base, as published. Nobody here has run it

Prioritization Frameworks (PM Craft)

Decide what to build — and more importantly, what not to build.

How to use

  • /prioritization-frameworks Apply prioritization constraints to this conversation.
  • /prioritization-frameworks <backlog> Prioritize the described set of initiatives.

Constraints

Framework Selection

  • RICE (Reach, Impact, Confidence, Effort): best for large backlogs needing rigorous comparison
  • ICE (Impact, Confidence, Ease): best for quick decisions, smaller teams
  • MoSCoW (Must, Should, Could, Won't): best for scope negotiation within a fixed release
  • MUST pick one framework and use it consistently. Switching methods mid-cycle creates confusion.
  • SHOULD match framework to decision type: strategic decisions need RICE, sprint decisions can use ICE

Scoring Discipline

  • MUST score in batches, not individually. Relative comparison improves accuracy.
  • MUST require evidence for high Impact scores. "This is important" is not evidence.
  • Items within 10% of each other are effectively tied — group into tiers, don't strict-rank
  • MUST include the "won't do" list. Saying no is the most important part of prioritization.
  • NEVER let scoring become a political exercise where everyone inflates their pet project

Prioritization Inputs

  • MUST balance: customer demand, business impact, strategic alignment, and technical investment
  • SHOULD weight recent data higher than old requests
  • MUST consider dependencies: can you build X without building Y first?
  • SHOULD factor in team energy — all infrastructure sprints drain morale; all feature sprints create debt
  • NEVER prioritize based solely on who asked loudest

Decision Quality

  • MUST set a clear decision-maker. Group prioritization produces mediocre outcomes.
  • SHOULD timebox prioritization sessions — spending longer on scoring than building defeats the purpose
  • MUST communicate priorities and rationale to the team after deciding
  • SHOULD reserve 10-20% of capacity for things that don't score well but matter strategically (experiments, debt)
  • MUST re-prioritize when significant new information arrives, not on a fixed schedule

Anti-Patterns

  • The Infinite P0 List: everything is critical, nothing is prioritized
  • The Democratic Backlog: letting everyone vote on priorities regardless of strategic context
  • Priority by Recency: whatever came in last goes to the top
  • The Immovable Roadmap: refusing to re-prioritize when the world changes
  • Prioritization Theater: going through the motions but building what leadership already decided

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.