Impact: Map expected metric change (%) to 0-10 scale
Ease: Map estimated effort (person-weeks) to 10-1 scale
Confidence: Sum weighted evidence contributions with group caps
ICE Score = Impact x Confidence x Ease
Priority buckets
Score
Guidance
>= 250
Consider immediate execution (high expected ROI)
150-249
Promising; recommend additional precision testing
100-149
Proceed with mitigations or phase-two testing
< 100
On hold or needs strengthening
Guardrails
Do not invent or infer evidence
Exclude evidence not directly tied to Impact from Confidence
When uncertain, apply conservative caps
Prevent duplicate counting of the same source
For the full scoring model, evidence types, confidence calculation, and report format, see references/ice-scoring-model.md.
Follow the writing standards in _shared/writing-standards.md for all outputs.
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: mjrtl-agentic-product-manager-ice-score3description: ICE Score4---56# ICE Score78Score an idea on Impact, Confidence, and Ease to propose execution priority.910## When to use1112- To quickly order an idea backlog and select items for exploration13- When you have at least some explicit evidence and a rough effort estimate14- Before drafting experiment plans for a leaf opportunity1516## Input1718- **Idea title and description**: goal, target metric, scope, and working hypothesis19- **Idea analysis and current state**: data/user/market/test evidence, risks, and effort estimate20- Optional: target metric change (%), estimated effort (person-weeks)2122## Output2324- **Format:** Markdown (`.md`)25- **Location:** `initiatives/[initiative]/solutions/`26- **Filename:** `ice-[YYYY-MM-DD]-[slugified-idea-title].md`2728## Scoring quick reference2930- **Impact**: Map expected metric change (%) to 0-10 scale31- **Ease**: Map estimated effort (person-weeks) to 10-1 scale32- **Confidence**: Sum weighted evidence contributions with group caps33- **ICE Score** = Impact x Confidence x Ease3435## Priority buckets3637| Score | Guidance |38|---|---|39| >= 250 | Consider immediate execution (high expected ROI) |40| 150-249 | Promising; recommend additional precision testing |41| 100-149 | Proceed with mitigations or phase-two testing |42| < 100 | On hold or needs strengthening |4344## Guardrails4546- Do not invent or infer evidence47- Exclude evidence not directly tied to Impact from Confidence48- When uncertain, apply conservative caps49- Prevent duplicate counting of the same source5051For the full scoring model, evidence types, confidence calculation, and report format, see `references/ice-scoring-model.md`.5253Follow the writing standards in `_shared/writing-standards.md` for all outputs.5455---56> Converted and distributed by [TomeVault](https://tomevault.io/claim/mjrtl) — claim your Tome and manage your conversions.57<!-- tomevault:4.0:skill_md:2026-04-15 -->
Run npx skillmds@latest add tomevault-io/mjrtl-agentic-product-manager-ice-score in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
ICE Score It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.