proposal-playbook
Skill1 starsChanged 3 months agoNo licenceView on GitHub
任何需要别人认可、拍板或审批的方案，怎么立住、怎么呈现、怎么迭代：一图流 + 文档两件套。\n读者可以是 CEO、跨级高管、直属 leader、评审会、合作团队。核心是从读者的问题进、用事实当证据、\n方案分步给、故事线带出系统、价值按对象写、文档一种节奏，并用要求表和多方向草图管住迭代。\n区别于 ealy-pitch（E 哥个人的禁忌和口味）、mexc-infographic（只管把图画出来）、\nprd-writer（需求文档）、okr-report（成果汇报）：这个 skill 管\"方案本身\"和\"怎么被认可\"。\n\n触发时机（宁可多触发也不要漏触发）：\n- 用户说\"做个方案\"、\"方案要过会 / 过老板 / 过 leader / 给管理层看 / 跨级汇报 / 立项 / 审批\"\n- 用户说\"一图流 + 文档\"、\"方案不够专业\"、\"价值没传递出来\"、\"故事不够大\"、\"体现产品力\"、\"从读者的角度\"\n- 用户说\"赢的逻辑\"、\"让他们的 AI 替我们说好话\"、\"三个方向让我选\"、\"你又把我之前提的点忘了\"\n- 一个方案被打回\"不是事实不说\"、\"堆砌\"、\"只是怎么做不是规划\"、\"重点没高亮\"、\"太简单了显得好做\"、\"乱\"\n- 任何\"方案要同时过拍板人、过 leader、过分发对象、过别人的 AI\"的场景\n\n不要用于：日常消息（ego-messenger / group-sync-messenger）、PRD（prd-writer）、只画图不碰方案（mexc-infographic）、\nOKR 和数据汇报（okr-report）、会上讲的 deck 的故事板和讲稿（decision-deck，它从这里取目的和证据）\n
In this repository43 other files it gives its agents.
- alpha-labSkill
- binance-trader-scraperSkill
- chrome-cdpSkill
- codex-auditSkill
- comparison-dashboardSkill
- data-request-kitSkill
- decision-deckSkill
- demo-video-kitSkill
- dev-plannerSkill
- dify-workflow-architectSkill
- docsSkill
- docxSkill
- ealy-pitchSkill
- ego-messengerSkill
- exec-proposalSkill
- friction-playbookSkill
- git-cleanupSkill
- google-workspaceSkill
- group-sync-messengerSkill
- import-memorySkill
- jira-card-kitSkill
- lark-docx-authoringSkill
- mexc-daily-insightSkill
- mexc-infographicSkill
- morningSkill
- okr-reportSkill
- pdfSkill
- pm-interview-prepSkill
- polymarket-execution-auditSkill
- pptxSkill
- prd-authoring-kitSkill
- prd-kit-releaseSkill
- prd-reviewerSkill
- prd-writerSkill
- proposal-deckSkill
- pvp-team-designerSkill
- quant-code-reviewSkill
- session-memorySkill
- showcase-demoSkill
- skill-creatorSkill
- user-research-reportSkill
- video-makingSkill
- xlsxSkill
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.