ai-prd-lite
Skill2 starsChanged 44 days agoNo licenceView on GitHub
为 AI 产品经理学员(自媒体辅导/陪跑场景)生成或审改精简版 AI PRD:七节主干、3000–4000 字(含表格)、约 5–6 页,对齐 ai-pm-coaching 第三阶段审核口径——业务结合、AI 嵌入点、形态判断(AI Workflow / Agentic Workflow / Agent / Multi-Agent)、功能卡、Harness 九层分析、验收与评测、Bad Case。用户说写 PRD、出一份 AI PRD、测试 PRD、改 PRD、PRD 太长要压缩、按模板写 PRD 时使用。不用于企业正式产品说明文档或几十页长文。
In this repository151 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ab-testingSkill
- ai-pm-coachingSkill
- ai-product-interviewSkill
- ai-product-resume-analysisSkill
- ai-product-suiteSkill
- ai-seoSkill
- analyticsSkill
- autoplanSkill
- awesome-gpt-image-2Skill
- brainstormingSkill
- build-enterprise-ai-prdSkill
- canghe-post-to-wechatSkill
- codexSkill
- cognitive-reviewSkill
- comet-anySkill
- comet-archiveSkill
- comet-buildSkill
- comet-classicSkill
- comet-designSkill
- comet-hotfixSkill
- comet-nativeSkill
- comet-openSkill
- cometSkill
- comet-tweakSkill
- comet-verifySkill
- competitor-profilingSkill
- content-remixSkill
- content-strategySkill
- context-restoreSkill
- context-saveSkill
- copy-editingSkill
- customer-researchSkill
- deep-research-deepSkill
- deep-research-reportSkill
- deep-researchSkill
- dispatching-parallel-agentsSkill
- docxSkill
- docx-to-markdown-fidelitySkill
- excalidraw-canvas-builderSkill
- executing-plansSkill
- find-skillsSkill
- guardSkill
- guizang-social-card-skillSkill
- gx-bus-design-reviewSkill
- gx-bus-implementation-auditSkill
- gx-zhks-frontend-designSkill
- harness-evalSkill
- healthSkill
- huashu-wechat-imageSkill
- hueSkill
- humanizer-zhSkill
- human-writingSkill
- image-assistantSkill
- investigateSkill
- json-canvasSkill
- khazix-writerSkill
- lark-approvalSkill
- lark-attendanceSkill
- lark-baseSkill
- The first 60 shown.
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

