ai-feature-prd
仓库创建 2026年1月29日最近提交 12 小时前SkillHot 收录 20 天前
▸ 精选理由
把概率性与错误场景写进产品设计,减少上线失败风险
这个 Skill 做什么
生成包含评估与护栏的 AI 功能产品需求文档(PRD)
帮你把 AI 功能的产品需求写成可执行的 PRD,不只是写场景和交互,还把模型会出错的地方、评估标准、护栏和兜底流程都写清楚。适合在要设计或上线用到 model/LLM 的功能时用,避免上线后才发现模型“瞎答”带来的风险。特别之处是把产品 UX(不确定性的展示)和工程指标(eval、成本/延迟预算、fallback)同时落地。
▸ 展开 SKILL.md 英文原文
Write a PRD for an AI-powered feature, covering the things normal PRDs miss. Use when asked to spec an AI/LLM feature, write a PRD for a feature that uses a model, or plan an AI capability (assistant, summarizer, generator, classifier). Produces an AI feature PRD — problem & UX of uncertainty, model approach, eval criteria, guardrails, fallback behaviour, the data flywheel, and cost/latency budget.
1.2k
Stars
220
Forks
40
仓库内 Skill
+74
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/mohitagw15856/pm-claude-skills/main/skills/ai-feature-prd/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/mohitagw15856/pm-claude-skills/main/skills/ai-feature-prd/SKILL.md"SKILL.MD 节选查看完整文件 ↗
# AI Feature PRD Skill AI features break the normal PRD because the system is probabilistic: it will be wrong sometimes, and the product must be designed around that, not in denial of it. This skill extends a standard PRD with the AI-specific sections that decide whether the feature is trustworthy — the UX of uncertainty, the eval bar, guardrails, and what happens when the model is wrong. ## Required Inputs Ask for these only if they aren't already provided: - **The user problem** and why an AI/probabilistic approach fits it (vs. deterministic rules). - **What "good" looks like** to the user, and the cost of a wrong answer (low-stakes vs. high-stakes). - **Inputs available** — context/da
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有