agentsclimarketplace

Feature prioritization

Skill Dragoon0x/product-skills/skills/strategy/feature-prioritization

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 feature-prioritization

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

Decide what to build next based on impact, not excitement. Applies scoring frameworks to feature backlogs. Use when scope is unclear, when the agent is about to build everything at once, or when deciding what ships in v1 vs v2.

SKILL.md

1.9 KB, 351 tokens by cl100k_base, as published. Nobody here has run it

Feature Prioritization

Decide what to build next based on impact, not excitement.

How to use

  • /feature-prioritization Apply prioritization constraints to feature decisions in this conversation.
  • /feature-prioritization <features> Score and rank a set of features.

Constraints

Scoring Framework

  • MUST evaluate each feature against: reach (how many users), impact (how much it changes behavior), confidence (how sure are we), effort (how long to build)
  • MUST produce a ranked list, not a tier system. Force hard choices.
  • NEVER give two features the same priority. If they feel equal, dig deeper.
  • SHOULD separate "must-have for launch" from "nice to have" from "later"

Decision Rules

  • If a feature serves <10% of users, it probably doesn't belong in v1
  • If you can't explain why a feature matters in one sentence, cut it
  • If a feature requires another feature to make sense, they ship together or not at all
  • Technical debt reduction is a feature. Prioritize it honestly.
  • NEVER build for hypothetical scale. Build for current users first.

Scope Protection

  • MUST define a scope ceiling before starting
  • Every addition requires a subtraction
  • "We'll add it later" is a valid and honest answer
  • SHOULD track deferred features with clear criteria for when they become relevant

Anti-Patterns

  • Building the feature the loudest user requested
  • Prioritizing based on ease of implementation rather than user impact
  • Adding features to match a competitor's checklist
  • Building infrastructure for scale you haven't reached
  • Saying yes to everything and shipping nothing

Gives 0 of the 12 instructions most roadmap strategy skills give in 351 tokens

Counted across 591 of the 672 authors here whose files we hold, read 2026-08-06

  • read product marketing context before asking questionsin 21 of 591, across 10 files
  • base price on perceived value, not costin 15 of 591, across 4 files
  • compact after finalizing a planin 14 of 591, across 9 files
  • differentiate tiers using features, limits, or supportin 14 of 591, across 3 files
  • use Van Westendorp to find acceptable price rangein 13 of 591, across 2 files
  • use MaxDiff to identify highly valued featuresin 13 of 591, across 2 files
  • map topics to buyer journey stagesin 12 of 591, across 6 files
  • Extract domain capabilities and classify subdomainsin 11 of 591, across 1 file
  • Define bounded contexts around consistency and ownershipin 11 of 591, across 1 file
  • Establish a ubiquitous language glossary and anti-termsin 11 of 591, across 1 file
  • Capture context boundaries in ADRs before implementationin 11 of 591, across 1 file
  • Open the strategic design template if neededin 11 of 591, across 1 file

Said here and by no other author read

  • produce a ranked list instead of a tier system
  • define a scope ceiling before starting
  • require a subtraction for every addition
  • track deferred features with clear relevance criteria
  • prioritize technical debt reduction honestly
  • build for current users before hypothetical scale

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

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.