Rice Agent Skill
RICE prioritization scoring initiatives by Reach, Impact, Confidence, and Effort. Use for feature prioritization, roadmap planning, or when comparing initiatives objectively.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/neurofoo/agent-skills --skill riceThe instruction itself
5 sections, as written by the authorRICE Prioritization Scoring
Score and rank initiatives using Reach, Impact, Confidence, and Effort to make prioritization decisions more objective.
Instructions
For each initiative, estimate the four RICE factors, calculate the score, and rank them. Be explicit about assumptions behind each estimate.
Output Format
Context
What are we prioritizing? What's the time horizon for Reach?
Factor Definitions
- Reach: [Define for this context, e.g., "users affected per quarter"]
- Impact: [Define for this context, e.g., "effect on conversion rate"]
- Effort: [Define unit, e.g., "engineer-weeks"]
Scoring Table
| Initiative | Reach | Impact | Confidence | Effort | RICE Score |
|------------|-------|--------|------------|--------|------------|
| [Name A] | [#] | [0.25-3] | [%] | [#] | [calculated] |
| [Name B] | [#] | [0.25-3] | [%] | [#] | [calculated] |
| [Name C] | [#] | [0.25-3] | [%] | [#] | [calculated] |
Ranked Results
- [Highest score] — RICE: X
- [Second] — RICE: X
- [Third] — RICE: X
Detailed Breakdown
For each initiative:
[Initiative Name]
- Reach: [X] — [Assumption: how did you estimate this?]
- Impact: [X] — [Reasoning for impact level]
- Confidence: [X%] — [What would increase confidence?]
- Effort: [X] — [What's included in this estimate?]
- RICE Score: (R × I × C) / E = [score]
Sensitivity Analysis
Which scores would change significantly if assumptions are wrong?
Recommendation
Based on the scores and analysis:
> [What to prioritize and why, including any caveats]
What RICE Doesn't Capture
- Strategic alignment
- Dependencies
- Team capability gaps
- Technical risk
Scoring Guide
Impact Scale
| Score | Meaning |
|-------|---------|
| 3 | Massive — core value prop |
| 2 | High — significant improvement |
| 1 | Medium — noticeable improvement |
| 0.5 | Low — minor enhancement |
| 0.25 | Minimal — nice to have |
Confidence Scale
| Score | Meaning |
|-------|---------|
| 100% | High — have data |
| 80% | Medium — reasonable estimate |
| 50% | Low — mostly guessing |
$ARGUMENTS
Other skills for the same job
different authors, same section of the catalogue
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
How to use it
Take neurofoo/rice from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.