rice-prioritization — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited rice-prioritization (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
RICE Score = (Reach × Impact × Confidence) / Effort| 维度 | 含义 | 单位 / 范围 |
|---|---|---|
| Reach | 一个时间窗口内会被影响的用户数 | 具体数字(每月触达人数) |
| Impact | 命中后单用户的影响程度 | 3 = 大量影响 / 2 = 高 / 1 = 中 / 0.5 = 低 / 0.25 = 极低 |
| Confidence | 你对前三项估计的自信度 | 100% 高 / 80% 中 / 50% 低 / < 50% 不要做 |
| Effort | 团队投入(person-month) | 具体数字 |
输出:每个候选项一个 RICE 分数,按分数降序排列。不允许只看分数,必须列出 Confidence < 80% 的项哪些假设需要验证。
ICE Score = Impact × Confidence × Ease适合早期阶段、没 reach 数据、需要快速排序。
WSJF = Cost of Delay / Job Size
Cost of Delay = Business Value + Time Criticality + Risk Reduction / Opportunity适合多 epic 跨团队竞争资源、季度规划、年度路线图。
适合 MVP 范围定义、版本边界划定。
| 项目 | Reach | Impact | Confidence | Effort | RICE 分 | 假设需验证 |
|---|---|---|---|---|---|---|
| <项目 1> | 5000/月 | 2 | 80% | 2 | 4000 | - |
| <项目 2> | 1000/月 | 3 | 50% ⚠️ | 1 | 1500 | "用户真的会用"未验证 |
| <项目 3> | 10000/月 | 1 | 100% | 3 | 3333 | - |排序后给:top 3 do-list / 中段 hold-list / 底部 kill-list。
| 逃逸路径 | 为什么不行 |
|---|---|
| "凭直觉排个序就行了" | 直觉排序 = 隐藏的"我觉得"。强迫维度拆分会暴露被低估 / 高估的假设 |
| "Reach 没数据就跳过 RICE" | 没 reach 数据用 ICE。完全跳过评分 = 回到 gut-feel = 决策不可追溯 |
| "Confidence 全填 80%" | 80% 是默认偷懒值。必须按具体维度想:reach 数据可信度?impact 估算可信度?effort 估算可信度?三者同 80% 概率极低 |
| "Effort 估不准就不估" | 估不准也要估。估错可调整,不估整张表就废了 |
| "排出来分高的不是我想做的,那 RICE 是错的" | RICE 没错,是你想做的项假设没列清。回 step 5 把"我想做"的真实理由列出来——可能是战略 / 个人偏好 / 老板压力——这些是另外的输入维度,不该让 RICE 背锅 |
| "Impact 全打 3 反映这些都很重要" | Impact = 3 上限是 20% 候选项。全 3 = 没认真区分 = 评分失效 |
| "MoSCoW 比 RICE 简单先用 MoSCoW" | MoSCoW 是 MVP 范围工具不是优先级工具。Must have 之间还要 RICE 排,Could have 也要 RICE 评。框架场景不同 |
story-splitting 拆故事 → pre-mortem 失败推演gtm-ops:growth-engine 设 A/B 验证product-management:sprint-planningv1.0 — 2026-05-08 product-thinking plugin v0.1.0 首发。
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.