.claude/skills/product-judgmentRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
先判断需求,再写 PRD。 我把《俞军产品方法论》中的核心产品判断方法,转化成了 Agent 可以直接执行的需求评审流程。 核心是回答一个问题:这个需求到底值不值得做? 这是一个 Agent Skill(SKILL.md),供产品经理和 AI Agent 在写 PRD 之前评审需求或产品想法;通过 npx skills add 安装,可用于 Claude Code、Codex 或其他支持 Skill 的 Agent 工作流。
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/product-judgmentRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/product-judgmentRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/product-judgmentRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @longfellow1/product-judgment-skillclawhub inspect @longfellow1/product-judgment-skill --version 0.1.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:3a8263e83ea3a7c496eaf67c83cd0cc7d2edf99b8fbacf2808899805cacb28e8assets/hero.webpexamples/ai-meeting-assistant.mdexamples/car-ai-assistant.mdexamples/competitor-feature.mdreferences/fake-demand-patterns.mdreferences/user-value-equation.mdreferences/yu-jun-methodology.mdscripts/demand-check.pyskill-card.mdSKILL.mdtemplates/CLAUDE.mdtemplates/JUDGMENT.mdIntroduces Product Judgment Skill 0.1.0 for evaluating product demands before PRDs or engineering commitments. - Requires anchoring the review in the real user, their specific problem moment, and how they solve it today. - Defines three modes: Quick Judgment, Formal Review, and Direction Setting. - Uses a three-strike protocol for judgments and provides action or direction guidance based on the review.