AI Prd
Generates a complete, structured AI Product Requirements Document (PRD) in Markdown format, covering background, requirements, model selection, prompt engineering, evaluation system, and stability strategy.
Install
npx skills add Caspian98/ai-prd-skill --skill ai-prdgit clone --depth 1 https://github.com/Caspian98/ai-prd-skill.git /tmp/ai-prd-skill
mkdir -p ~/.claude/skills
cp -r /tmp/ai-prd-skill/. ~/.claude/skills/ai-prdPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# AI PRD Skill ## Overview This skill generates a complete, professional AI Product Requirements Document (PRD) in Markdown format. It follows a standardized template specifically designed for AI/LLM-powered products, covering all phases from business background to model evaluation and rollout strategy. ## Quick Reference | Situation | Action | |-----------|--------| | User provides product name + brief description | Elicit missing key inputs, then generate full PRD | | User provides rich context (users, features, constraints) | Generate full PRD directly | | User wants to fill in a specific section only | Generate that section using the section templates below | --- ## Step 1 — Elicit Required Inputs Before generating, confirm you have the following. If any are missing, ask the user in a single message grouping all gaps. ### Required Inputs | Input | Description | Example | |-------|-------------|---------| | **产品/功能名称** | Full feature name for doc title | 智能营销Push文案生成 | | **版本号** | Semantic version | V1.0.0 | | **业务背景** | Current pain points and business context | 人工撰写push文案效率低，转化率差 | | **目标用户** | Who uses this feature | 电商平台运营人员 | | **核心功能点** | Key capabilities, 3–6 bullet points | 自动生成营销文案、支持多风格切换... | | **业务目标** | Measurable business outcome | Push点击率提升15% | | **模型目标** | Model-level quality target | 格式准确率≥99%，业务准确率≥85% | | **部署约束** | Cloud/private, compliance requirements | 公有云，数据不出境 | | **是否涉及微调** | Fine-tuning needed? | 否 / 是（说明数据来源） |
Details
- Skill name
ai-prd- Repository
- Caspian98/ai-prd-skill
- Repo updated
- 8 June 2026
FAQ
What does the AI Prd skill do?
Generates a complete, structured AI Product Requirements Document (PRD) in Markdown format, covering background, requirements, model selection, prompt engineering, evaluation system, and stability strategy.
How do I install the AI Prd skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Caspian98/ai-prd-skill --skill ai-prd. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is AI Prd popular?
It lives in Caspian98/ai-prd-skill, which has 9 GitHub stars and 0 forks.
Related skills
Anthropic Mind
9bozhouDev/anthropic-mind
用 Anthropic 的判断框架给出一个决策建议——回答「按 Anthropic 会怎么做这个取舍」。基于 428 篇一手材料（Claude's Constitution、工程博客、alignment 研究、两份 postmortem、Dario Amodei / Jack Clark / Amanda Askell / Chris Olah / Boris Cherny 的长文与访谈）蒸馏出的 8 条世界观模型、18 条领域模型和 21 条决策先例。触发场景：(1) 问「Anthropic 会怎么判断这个」「按他们的思路」「Dario / Jack Clark / Amanda 怎么看」；(2) 在做 agent 工程、产品、研究或内容决策时想要一个有出处的判断，而不是通用建议；(3) 要写关于 Anthropic 立场的内容，需要准确观点、英文原文引用和内部分歧。不要用于：Claude API 的用法、定价与模型 ID（用 claude-api）、Claude Code 的功能操作（用 claude-code-guide）、纯事实查询（发布时间、参数、榜单数字）。
AI Collab Bridge
9owgit/ai-collab-bridge
A collaboration protocol for Claude, Codex, and other CLI-capable AI models to review each other's code via CLI handoffs. Use this skill whenever the user mentions AI-to-AI collaboration, Claude-Codex bridge, peer review between AI models, "let Claude check what Codex did", "have Codex verify Claude's work", multi-agent code review, AI handoff, two AIs reviewing each other, or wants two different AI models to verify each other's output before completing a task. Also use whenever you (the running AI) want a second opinion from another model and need a structured way to request that review, even
Aside Free LLM Autopilot
8sojuhub/aside-free-llm-autopilot
Set up and maintain free LLM APIs for Aside first, adapting to other agents when requested: discover providers, onboard eligible accounts, adapt model routing to the user's environment, retire unavailable routes, and register one daily maintenance routine. Use for free-tier setup or maintenance, not every browser task.
A2a
9CtriXin/agent-2-agent
a2a (Agent-to-Agent) — 跨模型对抗式 code review。Claude 写的代码让 Codex 审，Codex 写的让 Claude 审，互相找茬不留死角。
Avoid Over AI Writing
8Wattson-Law/avoid-over-ai-writing-skill
降低论文、技术方案、专利和正式 Word 文稿中的模板化 AI 文风，并把 Word、Markdown 或粘贴文本整理为可交付 DOCX。统一表达、标题编号、字体、段落、黑白表格、分页和目录；保留用户事实、证据、指标与结论，不代替事实核验或技术评审。
Product Decision Agent
6atdy/maoxuan-product-agent
中文产品决策 Agent。用于中国大陆互联网产品、运营、增长、商业化、数据、项目推进和组织协作场景：产品规划、需求分析、PRD、需求优先级、排期、版本规划、Roadmap、MVP、灰度、上线、迭代、增长停滞、拉新、投放、渠道、裂变、CAC、LTV、ROI、留存、转化、DAU/MAU、GMV、漏斗、社区运营、内容供给、创作者、用户运营、活动运营、私域、会员、定价、指标异常、数据口径、埋点、A/B Test、用户反馈、客服/销售反馈、竞品冲击、资源不足、项目延期、需求反复、老板临时插需求、跨部门协作、团队冲突、OKR/KPI、目标拆解、复盘等。触发时像资深互联网产品负责人一样，先判断真实问题、当前阶段、核心阻塞、关键约束、相关方和证据充分性，再给出最值得执行的下一步。默认中文回答，不讲理论、不引用原文、不解释历史、不暴露后台方法来源。
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.