Prioritization logo

Prioritization

Community
yonatangross
prioritization

Prioritization frameworks — RICE, WSJF, ICE, MoSCoW, and opportunity cost scoring for backlog ranking. Use when prioritizing features, comparing initiatives, justifying roadmap decisions, or evaluating trade-offs between competing work items.

Overview

Publisheryonatangross
Repositoryorchestkit
Skill nameprioritization
Stars
298
Forks
35
Bundled files
7
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by yonatangross on GitHub. Read the source before you install it.

Installation

Install the Prioritization AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/yonatangross/orchestkit/tree/main/plugins/ork/skills/prioritization
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/yonatangross/orchestkit.git /tmp/orchestkit
mkdir -p .claude/skills
cp -r /tmp/orchestkit/plugins/ork/skills/prioritization .claude/skills/prioritization
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prioritization in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Prioritization on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Prioritization is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Prioritization Frameworks

Score, rank, and justify backlog decisions using the right framework for the situation.

Decision Tree: Which Framework to Use

Do you have a hard deadline or regulatory pressure?
  YES → WSJF (Cost of Delay drives sequencing)
  NO  → Do you have reach/usage data?
          YES → RICE (data-driven, accounts for user reach)
          NO  → Are you in a time-boxed planning session?
                  YES → ICE (fast, 1-10 scales, no data required)
                  NO  → Is this a scope negotiation with stakeholders?
                          YES → MoSCoW (bucket features, control scope creep)
                          NO  → Value-Effort Matrix (quick 2x2 triage)
FrameworkBest ForData RequiredTime to Score
RICEData-rich teams, steady-state prioritizationAnalytics, user counts30-60 min
WSJFSAFe orgs, time-sensitive or regulated workRelative estimates only15-30 min
ICEStartup speed, early validation, quick triageNone5-10 min
MoSCoWScope negotiation, release planningStakeholder input1-2 hours
Value-Effort2x2 visual, quick team alignmentNone10-15 min

RICE

RICE Score = (Reach × Impact × Confidence) / Effort
FactorScaleNotes
ReachActual users/quarterUse analytics; do not estimate
Impact0.25 / 0.5 / 1 / 2 / 3Minimal → Massive per user
Confidence0.3 / 0.5 / 0.8 / 1.0Moonshot → Strong data
EffortPerson-monthsInclude design, eng, QA
markdown
## RICE Scoring: [Feature Name]

| Feature     | Reach  | Impact | Confidence | Effort | Score  |
|-------------|--------|--------|------------|--------|--------|
| Smart search| 50,000 | 2      | 0.8        | 3      | 26,667 |
| CSV export  | 10,000 | 0.5    | 1.0        | 0.5    | 10,000 |
| Dark mode   | 30,000 | 0.25   | 1.0        | 1      |  7,500 |

See rules/prioritize-rice.md for ICE, Kano, and full scale tables.


WSJF

WSJF = Cost of Delay / Job Size
Cost of Delay = User Value + Time Criticality + Risk Reduction  (1-21 Fibonacci each)

Higher WSJF = do first. Fibonacci scale (1, 2, 3, 5, 8, 13, 21) forces relative sizing.

markdown
## WSJF: GDPR Compliance Update

User Value:       8   (required for EU customers)
Time Criticality: 21  (regulatory deadline this quarter)
Risk Reduction:   13  (avoids significant fines)
Job Size:          8  (medium complexity)

Cost of Delay = 8 + 21 + 13 = 42
WSJF = 42 / 8 = 5.25

See rules/prioritize-wsjf.md for MoSCoW buckets and practical tips. See references/wsjf-guide.md for the full scoring guide.


ICE

ICE Score = Impact × Confidence × Ease    (all factors 1-10)

No user data required. Score relative to other backlog items. Useful for early-stage products and rapid triage sessions.


MoSCoW

Bucket features before estimation. Must-Haves alone should ship a viable product.

markdown
## Release 1.0 MoSCoW

### Must Have (~60% of effort)
- [ ] User authentication
- [ ] Core CRUD operations

### Should Have (~20%)
- [ ] Search, export, notifications

### Could Have (~20%)
- [ ] Dark mode, keyboard shortcuts

### Won't Have (documented out-of-scope)
- Mobile app (Release 2.0)
- AI features (Release 2.0)

Opportunity Cost & Trade-Off Analysis

When two items compete for the same team capacity, quantify what delaying each item costs per month.

markdown
## Trade-Off: AI Search vs Platform Migration (Q2 eng team)

### Option A: AI Search
- Cost of Delay: $25K/month (competitive risk)
- RICE Score: 18,000
- Effort: 6 weeks

### Option B: Platform Migration
- Cost of Delay: $5K/month (tech debt interest)
- RICE Score: 4,000
- Effort: 8 weeks

### Recommendation
Human decides. Key factors:
1. Q2 OKR: Increase trial-to-paid conversion (favors AI Search)
2. Engineering capacity: Only one team, sequential not parallel
3. Customer commitment: No contractual deadline for either

See rules/prioritize-opportunity-cost.md for the Value-Effort Matrix and full trade-off template. See references/rice-scoring-guide.md for detailed RICE calibration.


Common Pitfalls

PitfallMitigation
Gaming scores to justify pre-decided workCalibrate as a team; document assumptions
Mixing frameworks in one tablePick one framework per planning session
Only tracking high-RICE items; ignoring cost of delayCombine RICE with explicit delay cost analysis
MoSCoW Must-Have bloat (>70% of scope)Must-Haves alone must ship a viable product
Comparing RICE scores across different goalsOnly compare within the same objective

Related Skills

  • product-frameworks — Full PM toolkit (value prop, market sizing, competitive analysis, user research, business case)
  • write-prd — Convert prioritized features into product requirements documents
  • product-analytics — Define and instrument the metrics that feed RICE reach/impact scores
  • okr-design — Set the objectives that determine which KPIs drive RICE impact scoring
  • market-sizing — TAM/SAM/SOM analysis that informs strategic priority
  • competitive-analysis — Competitor context that raises or lowers WSJF time criticality scores

Version: 1.0.0

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Prioritization AI skill do?

Prioritization frameworks — RICE, WSJF, ICE, MoSCoW, and opportunity cost scoring for backlog ranking. Use when prioritizing features, comparing initiatives, justifying roadmap decisions, or evaluating trade-offs between competing work items.

Why use Prioritization on TypingMind?

Because you install it once and use it with any model. Prioritization is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Prioritization in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yonatangross/orchestkit/tree/main/plugins/ork/skills/prioritization. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Prioritization?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Prioritization?

As many as you like. As long as a model supports skills, you can use Prioritization with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Prioritization AI skill free?

Yes. It is published on GitHub by yonatangross under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇