agentleFS
Sign inStart free
aroyburman-codesaroyburman-codes/pm-skills/skills/prioritization-matrix/SKILL.md

prioritization-matrix

Skill25 starsChanged 9 months agoMITView on GitHub

Score and rank features or initiatives using RICE, ICE, weighted scoring, or custom frameworks. Generates a prioritized backlog with clear rationale. Use for: sprint planning, roadmap decisions, feature trade-offs.

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

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    When prioritizing AI features, also consider:

    line 98
  2. Distinctive:

    Eval coverage: Do we have evals to measure success?

    line 100
  3. Distinctive:

    Data requirements: Do we have the training/eval data?

    line 102

≈ “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

Prioritization Matrix Skill

Score, rank, and prioritize a set of features, initiatives, or ideas using structured scoring frameworks.

When to Use

  • User has a list of features and needs to decide what to build first
  • User needs to justify prioritization to stakeholders
  • User says /prioritization-matrix followed by a list of items
  • Any time competing initiatives need to be ranked

Supported Frameworks

RICE (Reach, Impact, Confidence, Effort)

Best for: Growth-focused teams with measurable reach data.

FactorHow to Score
Reach# of users/customers affected per quarter
Impact0.25 (minimal) / 0.5 (low) / 1 (medium) / 2 (high) / 3 (massive)
Confidence100% (high) / 80% (medium) / 50% (low)
EffortPerson-months of work

Score = (Reach x Impact x Confidence) / Effort

ICE (Impact, Confidence, Ease)

Best for: Fast estimation when detailed reach data isn't available.

FactorHow to Score (1-10)
ImpactHow much will this move the needle?
ConfidenceHow sure are we about impact and effort?
EaseHow easy is this to implement? (10 = trivial)

Score = Impact x Confidence x Ease

Weighted Scoring

Best for: Custom criteria that matter to your team.

Define 4-6 criteria with weights (must sum to 100%):

CriteriaWeightDescription
Strategic alignment25%How well does this support company goals?
User impact25%How much does this improve user experience?
Revenue potential20%Direct or indirect revenue impact
Technical feasibility15%How complex is implementation?
Time sensitivity15%Is there a window of opportunity?

Score each item 1-5 on each criterion. Weighted score = sum of (score x weight).

Value vs. Effort (2x2)

Best for: Quick visual communication to stakeholders.

Plot items on a 2x2 matrix:

  • Quick Wins (High value, Low effort) → Do first
  • Big Bets (High value, High effort) → Plan carefully
  • Fill-ins (Low value, Low effort) → Do if capacity allows
  • Money Pits (Low value, High effort) → Deprioritize

Workflow

Step 1: Clarify

  • What are we prioritizing? (features, bugs, initiatives, experiments)
  • What timeframe? (this sprint, this quarter, this year)
  • What constraints? (team size, dependencies, deadlines)
  • What's the primary goal? (growth, retention, revenue, quality)

Step 2: Choose Framework

Based on the context, recommend the most appropriate framework. If the user doesn't specify, default to RICE for product features and Weighted Scoring for strategic initiatives.

Step 3: Score

For each item:

  • Score on each dimension with reasoning (not just numbers)
  • Flag assumptions and confidence level
  • Note dependencies between items

Step 4: Rank & Recommend

  • Sort by composite score
  • Group into tiers: Must Do / Should Do / Could Do / Won't Do
  • Highlight any items where the score conflicts with your intuition (and explain why)

Step 5: Communicate

Generate a stakeholder-ready summary:

  • Top 3 priorities with one-sentence rationale each
  • What we're NOT doing and why
  • Key assumptions that could change the ranking

Output Format

Generate a clean markdown table with scores, plus a summary paragraph. Include the rationale for the top and bottom items. Flag any close calls where small changes in assumptions would flip the ranking.

AI/ML-Specific Considerations

When prioritizing AI features, also consider:

  • Model readiness: Is the underlying model capable enough?
  • Eval coverage: Do we have evals to measure success?
  • Safety review: Does this need safety/red-team review?
  • Data requirements: Do we have the training/eval data?
  • Cost per query: What's the inference cost impact?

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