prioritization-advisor
Skill0 starsChanged 8 months agoMITView on GitHub
Guide PMs in choosing the right prioritization framework by asking adaptive questions about product stage, team context, decision-making needs, and data availability. Triggers: "prioritize", "which framework", "RICE vs ICE", "how to prioritize".
5 other projects use a version of this, 4 of them edited.
Adopted by
Most recently taken up by
- deanpeters/Product-Manager-Skillsedited, first seen Oct 25, 2026
- ZeroTokenClaw/agents-skillsedited, first seen Sep 21, 2026
- agrivisionai/claude-skillsedited, first seen Jul 14, 2026
- DIAL-Studio/pm-agent-harness-kitedited, first seen Jul 8, 2026
- nandanosql/all_in_one_pm_skillstheir own version, first seen Feb 28, 2026
Used with
Projects with it also use derisk-measurement-advisor, organic-growth-advisor and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
DIAL-StudioSkillderisk-measurement-advisor
Identify what to measure, test, or track to de-risk a product or AI idea. Use when stress-testing an idea across internal (DUFV) and external (PESTEL) dimensions.
Also in 3 projects that use this
DIAL-StudioSkillorganic-growth-advisor
Identify which organic growth path to pursue — new segments, geographies, channels, or products. Use when diagnosing where a growth constraint lives and which McKinsey growth level to act\
Also in 3 projects that use this
ian-lawrence423Skillskill-authoring-workflow
Create or update repo skills with compliant metadata, dependency contracts, package sync, marketplace descriptions, and validation workflow.
Also in 3 projects that use this
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 4
- deanpeters/Product-Manager-Skills★ 7.7k25% same
- DIAL-Studio/pm-agent-harness-kit★ 1225% same
- agrivisionai/claude-skills★ 125% same
- ZeroTokenClaw/agents-skills★ 125% same
Wrote their own version · 1
- nandanosql/all_in_one_pm_skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ci-watchSkill
- commitSkill
- discovery-interview-prepSkill
- doc-generateSkill
- incident-responseSkill
- opportunity-solution-treeSkill
- polarisSkill
- prd-developmentSkill
- reviewSkill
- roadmapSkill
- security-auditSkill
- session-wrapSkill
- spec-updateSkill
- tddSkill
- tech-debt-auditSkill
- test-runnerSkill
- user-storySkill
- uxSkill
- workshop-facilitationSkill
The file
We split this skill into the rules it gives an agent
4 rules. 1 is common, 2 are distinctive, and 1 is very specific to this project.
1
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 43
Use workshop-facilitation as the default interaction protocol for this skill.
- Distinctive: line 90
After collecting responses, recommend a framework with:
- Distinctive: line 108
Why NOT RICE: No usage data for Reach, overhead kills speed at pre-PMF stage
- Common: line 122
Fix: Use frameworks as input, not automation.
“Common” is measured: kept by at least 6 in 10 of the 4 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.
Files
Purpose
Guide product managers in choosing the right prioritization framework by asking adaptive questions about product stage, team context, decision-making needs, and stakeholder dynamics. Use this to avoid "framework whiplash" (switching frameworks constantly) or applying the wrong framework (e.g., using RICE for strategic bets or ICE for data-driven decisions). Outputs a recommended framework with implementation guidance tailored to your context.
This is not a scoring calculator -- it's a decision guide that matches prioritization frameworks to your specific situation.
Key Concepts
The Prioritization Framework Landscape
Scoring frameworks:
- RICE (Reach, Impact, Confidence, Effort) -- Data-driven, requires metrics
- ICE (Impact, Confidence, Ease) -- Lightweight, gut-check scoring
- Value vs. Effort (2x2 matrix) -- Quick wins vs. strategic bets
- Weighted Scoring -- Custom criteria with stakeholder input
Strategic frameworks:
- Kano Model -- Classify features by customer delight (basic, performance, delight)
- Opportunity Scoring -- Rate importance vs. satisfaction gap
- Buy-a-Feature -- Customer budget allocation exercise
- Moscow (Must, Should, Could, Won't) -- Forcing function for hard choices
Contextual frameworks:
- Cost of Delay -- Urgency-based (time-sensitive features)
- Impact Mapping -- Goal-driven (tie features to outcomes)
- Story Mapping -- User journey-based (narrative flow)
Anti-Patterns
- Not a universal ranking: Frameworks aren't "better" or "worse" -- they fit different contexts
- Not a replacement for strategy: Frameworks execute strategy; they don't create it
- Not set-it-and-forget-it: Reassess frameworks as your product matures
Facilitation Source of Truth
Use workshop-facilitation as the default interaction protocol for this skill.
It defines: session heads-up + entry mode (Guided, Context dump, Best guess), one-question turns, progress labels, interruption handling, numbered recommendations at decision points, quick-select options.
This file defines the domain-specific assessment content. If there is a conflict, follow this file's domain logic.
Application
This interactive skill asks up to 4 adaptive questions, offering 3-4 enumerated options at each step.
Question 1: Product Stage
"What stage is your product in?"
- Pre-product/market fit -- Searching for PMF; experimenting rapidly; unclear what customers want
- Early PMF, scaling -- Found initial PMF; growing fast; adding features to retain/expand
- Mature product, optimization -- Established market; incremental improvements; competing on quality
- Multiple products/platform -- Portfolio of products; cross-product dependencies
Question 2: Team Context
"What's your team and stakeholder environment like?"
- Small team, limited resources -- 3-5 engineers, 1 PM, need to focus ruthlessly
- Cross-functional team, aligned -- Product, design, engineering aligned; clear goals
- Multiple stakeholders, misaligned -- Execs, sales, customers all have opinions; need transparent process
- Large org, complex dependencies -- Multiple teams, shared roadmap
Question 3: Decision-Making Needs
"What's the primary challenge you're trying to solve with prioritization?"
- Too many ideas, unclear which to pursue -- Backlog is 100+ items; need to narrow to top 10
- Stakeholders disagree on priorities -- Sales wants features, execs want strategic bets
- Lack of data-driven decisions -- Prioritizing by gut feel; want metrics-based process
- Hard tradeoffs between strategic bets vs. quick wins
Question 4: Data Availability
"How much data do you have to inform prioritization?"
- Minimal data -- New product, no usage metrics, few customers to survey
- Some data -- Basic analytics, customer feedback, but no rigorous data collection
- Rich data -- Usage metrics, A/B tests, customer surveys, clear success metrics
Output: Framework Recommendation
After collecting responses, recommend a framework with:
- Rationale: Why this framework fits (linked to Q1-Q4 answers)
- Implementation steps: Concrete how-to (4 steps)
- Example scoring template: Filled-in example table
- Alternative framework: Second choice with tradeoffs
- Pitfalls: Common mistakes with this framework
- Reassess when: Triggers to reconsider the framework choice
Examples
Example 1: Good Match (Early PMF + RICE)
- Context: Early PMF, aligned cross-functional team, some data, wants metrics-based decisions
- Recommendation: RICE -- has data for Reach/Impact, team can agree on scoring, structured without being heavy
- Why NOT ICE: Too subjective for a team that wants data-driven process
Example 2: Bad Match (Pre-PMF + RICE = Wrong Fit)
- Context: Pre-PMF, small team, minimal data, too many ideas
- Recommendation: ICE or Value/Effort Matrix -- lightweight, fast, no data required
- Why NOT RICE: No usage data for Reach, overhead kills speed at pre-PMF stage
Common Pitfalls
Pitfall 1: Using the Wrong Framework for Your Stage
Symptom: Pre-PMF startup using weighted scoring with 10 criteria Fix: Match framework to stage. Pre-PMF = ICE. Scaling = RICE. Mature = Opportunity Scoring or Kano.
Pitfall 2: Framework Whiplash
Symptom: Switching frameworks every quarter Fix: Stick with one framework for 6-12 months. Reassess only when stage/context changes.
Pitfall 3: Treating Scores as Gospel
Symptom: "Feature A scored 8,000, Feature B scored 7,999, so A wins" Fix: Use frameworks as input, not automation. PM judgment overrides scores when needed.
Pitfall 4: Solo PM Scoring
Symptom: PM scores features alone, presents to team Fix: Collaborative scoring sessions. PM, design, engineering score together.
Pitfall 5: No Framework at All
Symptom: "We prioritize by who shouts loudest" Fix: Pick any framework. Even imperfect structure beats chaos.
References
External Frameworks
- Intercom, RICE Prioritization (2016)
- Sean McBride, ICE Scoring (2012)
- Luke Hohmann, Innovation Games (2006) -- Buy-a-Feature
- Noriaki Kano, Kano Model (1984)
Credit
- Adapted from Dean Peters, Product Manager Skills (CC BY-NC-SA 4.0).
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
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.

