build-enterprise-ai-prd
Skill2 starsChanged 44 days agoNo licenceView on GitHub
从零创建、续写或重构企业级 AI 产品 PRD、方案决策、项目复盘与面试答辩长文,产出与“AI 合同审查 PRD 方案决策与项目答辩完整版”同等深度的可落地文档。适用于用户要求写完整 AI PRD/项目方案/作品集/项目复盘/合同审查方案,补齐 Why 与 Why not、功能级 PRD、规则+RAG+LLM 全链路、数据知识治理、模型选型、Prompt/Schema、异常降级人工恢复、安全评测、Bad Case、运营归因和面试追问,或把已有短文扩成零基础学员可学习和迁移的企业实战模板。默认以文件为外部记忆分阶段生成,避免一次性长文造成上下文爆炸;也支持审计和批量修订已有 Markdown 文档。
In this repository151 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ab-testingSkill
- ai-pm-coachingSkill
- ai-prd-liteSkill
- ai-product-interviewSkill
- ai-product-resume-analysisSkill
- ai-product-suiteSkill
- ai-seoSkill
- analyticsSkill
- autoplanSkill
- awesome-gpt-image-2Skill
- brainstormingSkill
- 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.

