会议纪要+Figma生成PRD skill

SKILL内容创作
内容创作 未标注权限 许可证不明确
安装这个技能

This skill should be used when converting meeting notes, requirement discussions, PRD drafts, incomplete recordings, or Figma source files/links into a professional product requirements document in Markdown. It specializes in extracting Figma file/node data, exporting corresponding frame screenshots, inferring missing product logic from Figma UI flows, and associating Figma screens, components, and interaction states with available requirement notes in a product manager PRD writing style.

一句话选型结论

按资料字段整理

会议纪要+Figma生成PRD skill是内容创作类的 Agent Skill,安装方式未标注,权限级别未标注,许可证不明确,有可直接复制的安装命令。技能本质是给模型读的说明书,效果取决于模型与客户端;装完先用一个小任务验证,再放进正式流程。

分类内容创作 安装方式未标注 权限级别未标注权限 许可证许可证不明确
累计安装 未标注 本周 未标注
GitHub 星标 未标注 仓库 未标注
下载量 未标注 技能市场下载数
权限级别 未标注权限 安装前请确认风险范围
许可证 许可证不明确 未说明

安装

未标注
在支持 Skills 的客户端里执行,装完问一句「你有哪些技能」验证
skillhub install user_d786d32b/writing-figma-prd-skill
  1. 1
    确认客户端支持

    确认你的客户端支持 Skills(Claude、Codex、Cursor 等),并升级到较新的版本。

  2. 2
    拿到技能文件

    执行上面的命令安装;也可以把仓库里的 SKILL.md 手动放进客户端的 skills 目录。

  3. 3
    刷新技能列表

    重新打开客户端,或刷新技能列表,让新放进来的技能被加载。

  4. 4
    验证是否生效

    问一句「你有哪些技能」,确认列表里出现它,再拿一个小任务试跑。

技能档案

内容创作
字段来自技能仓库与公开索引,中文说明由本站标注
作者 / 维护方user_d786d32b仓库 未标注 · 版本 未标注
宿主客户端未标注技能可被这些客户端加载
安装方式未标注安装包 community
权限级别未标注权限安装前请确认风险范围
许可证未说明许可证不明确,商用前请自行确认条款
仓库可用性available技能仓库当前是否可访问
最近核验未标注上游最后核验时间 · 数据更新 1791730598
正文体量9.6 KBSKILL.md 原文大小,越大说明说明书写得越细

典型使用场景

3 类
按分类整理的常见用法,具体以 SKILL.md 为准
写文章与脚本

按主题产出初稿与分镜脚本。

改稿与润色

把草稿改顺、统一语气。

多平台文案改写

同一内容按平台改成长短不同的版本。

选择建议

装之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有可直接复制的安装命令,不用自己翻文档找入口。

先想清楚的地方

  • 没有标注权限级别,实际能做什么要装好后确认。
  • 许可证不明确,商用或二次分发前先到仓库确认条款。
  • 没有做站内核验,内容以作者仓库为准。
  • 技能只是说明书,实际效果取决于模型与客户端,装完先用小任务试一遍。

更适合

  • 需要在内容创作场景里给模型补一套做法的人。
  • 愿意先读一遍 SKILL.md、确认它会让模型做什么的人。

不太适合

  • 对许可证要求很严、必须明确可商用的人。
  • 只想装完就自动变强、不打算看说明书的人。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
技能权限级别安装方式累计安装宿主客户端安装命令
会议纪要+Figma生成PRD skill当前 未标注权限 未标注 未标注 未标注 有
AI 视频生成 调用外部服务 GitHub 仓库 431.3 万 Codex、Claude、Cursor 有
视频帧 联网访问 ClawHub 市场 262.1 万 OpenClaw 有
Markdown 转换器 写入文件 ClawHub 市场 135.3 万 OpenClaw 有
哔哩哔哩全合一 接触敏感数据 ClawHub 市场 64.1 万 OpenClaw 有
Remotion video toolkit 命令行 浏览器控制 ClawHub 市场 63.9 万 OpenClaw 有

SKILL.md 全文

9.6 KB
模型实际读到的说明书原文,来自技能仓库

Meeting Figma PRD

Overview

Convert meeting-note originals and Figma source material into a structured Markdown PRD. Extract facts from the meeting text when available; when recordings or notes are missing or incomplete, use Figma page structure, UI copy, frames, components, states, annotations, and prototype flows to complete the requirement draft. Export corresponding screenshots, associate design evidence with requirements, and write function descriptions as professional product manager PRD tables while clearly marking assumptions and pending confirmations.

Use When

Use this skill for requests such as:

  • “根据会议纪要和Figma生成需求文档/PRD/md”
  • “把设计稿和会议原文整理成需求文档”
  • “根据Figma源文件补全需求详细逻辑”
  • “输出【战绩玩法】需求文档”

Required Inputs

Collect or locate the following inputs:

  1. Meeting-note original text, transcript, minutes, chat log, or raw requirement notes.
  2. Figma source file or Figma URL/link. Accept Figma file links, prototype links, local exported Figma files, or attached design assets.
  3. Optional: expected launch time, development workload, experiment/gray-release strategy, owner, business line, and existing PRD context.

If meeting notes or recordings are missing/incomplete but Figma is available, continue in Figma-first mode: infer product scope, user paths, UI states, and interaction logic from the design, then mark inferred or unverifiable business rules as 基于设计稿推断,待确认. If Figma is missing too, continue with available material and mark unverifiable sections as 暂无 or 待补充 according to the output rules.

Core Workflow

1. Ingest Meeting Notes

Extract the following facts from the meeting-note original:

  • Business context, current pain points, target users, target scenario.
  • Explicit feature scope, non-goals, constraints, dependencies, and risks.
  • Stakeholders, business owners, front-end/back-end workload, timeline, rollout plan.
  • Functional points, interaction rules, copy requirements, data display rules, exceptions, and open questions.
  • Experiment strategy, gray-release percentage, target audience, metrics, and success criteria.

Preserve important wording when it affects product logic. Do not expand vague statements into specific rules unless the design supports them.

2. Inspect and Interpret Figma

When a Figma source file/link is present, load the figma skill before analysis. Use it to inspect file structure, pages, frames, components, variants, auto-layout hierarchy, text layers, annotations, prototypes, and exported assets as needed.

Use scripts/figma_extract.py as the built-in Figma recognition helper when an API token is available. The helper parses Figma URLs, extracts the file key and node id, calls the Figma REST API, and writes a compact JSON file containing file metadata, page/frame inventory, and target node data.

Run pattern:

python scripts/figma_extract.py "<figma-url>" "<output-json>"

Export screenshots for PRD illustrations with scripts/figma_export_images.py. Use the target node id from the Figma URL first; when multiple feature modules map to different frames, pass the mapped node ids explicitly.

python scripts/figma_export_images.py "<figma-url>" "<prd-assets-dir>"
python scripts/figma_export_images.py "<figma-url>" "<prd-assets-dir>" --ids "1086:4328,1086:4330" --format png --scale 2

Screenshot usage rule:

  • Export screenshots for the frames/components that correspond to each core function point.
  • Store screenshots in a PRD-local assets directory such as assets/figma/ or <prd-name>-assets/figma/.
  • Insert screenshots in Markdown with relative paths whenever possible, for example ![入口页](./高光鉴赏团需求文档-assets/figma/figma_1086-4328.png).
  • If Figma cannot be exported, keep the table row and write 待补充截图 in the illustration column.

Authentication rule:

  • Read FIGMA_ACCESS_TOKEN from the environment or from a local .env file in the current working directory.
  • Never request or print tokens in the final PRD.
  • If no token is available or the file is private, continue from meeting notes and mark Figma-derived details as 待补充/待校验.

Identify and record:

  • Design link, file/page/frame names, relevant node/frame identifiers, and exported screenshot paths if available.
  • Main user flows represented by frames.
  • Page modules, entry points, states, data fields, copy, buttons, labels, tabs, cards, popups, empty/loading/error states, and navigation targets.
  • Component variants indicating business states, such as logged-in/out, owned/not owned, ranking states, visibility, permission, success/failure, disabled/enabled, or gray-release exposure.
  • Prototype connections or annotations that imply interaction flows.

If Figma cannot be opened directly, use any provided screenshots/exports and clearly mark design-derived assumptions as based on exported material.

3. Associate Meeting Facts with Figma Evidence

Build a requirement-evidence map before writing:

  • Match meeting requirements to Figma frames by feature module, UI text, entry path, data field, interaction, and state.
  • Use meeting notes as the source of business intent and Figma as the source of screen-level behavior.
  • Prefer explicit meeting-note statements for scope and rollout; prefer Figma for UI structure, page hierarchy, copy, states, and interaction details.
  • When meeting notes and Figma conflict, document the conflict as 待确认 rather than choosing silently.
  • When Figma contains screens not mentioned in meeting notes, include them only if they are part of the same flow, and mark their source as design稿补充.
  • When meeting notes contain logic not represented in Figma, include it as requirement logic and mark UI待补充 if relevant.

4. Produce Markdown PRD

Use assets/prd-template.md as the output structure. Keep headings stable and output a clean .md document. When screenshots are exported, save them beside the PRD in a stable assets directory and reference them from the function-detail table with Markdown image syntax.

The PRD must include these sections in order:

  1. # 需求标题
  2. ## 1. 需求背景和目标
  3. ## 2. 上线时间
  4. ## 3. 设计稿
  5. ## 4. 需求内容详细描述
  6. ## 5. 灰度放量方案
  7. ## 6. 埋点设计

5. Title Rule

Generate a concise requirement title:

  • Format: 【战绩玩法】+ 自总结标题
  • Total title text after the prefix should be concise and product-like.
  • Keep the full title within 20 Chinese characters when possible.
  • Example: 【战绩玩法】经典农场资料卡
  • Avoid vague titles such as 【战绩玩法】需求整理.

6. Output Rules by Section

需求背景和目标

Write background, problem to solve, value, and expected effect. Use 暂无 if not mentioned and cannot be inferred.

上线时间

Include expected launch time and front-end/back-end workload only when mentioned. If all timing/workload information is absent, write 暂无.

设计稿

Place the original Figma/design link directly. If multiple links are provided, list all. If only local files or exports exist, list file names/paths.

需求内容详细描述

Follow the rules in references/prd-writing-rules.md. This section is the core output and must be written as a professional PM PRD, organized by user flow and functional module. For all major function descriptions, use a three-column Markdown table with 示意图、功能场景、需求详情; the illustration column should reference the exported Figma screenshot for the corresponding frame/node whenever available.

灰度放量方案

Translate experiment, gray-release, audience split, whitelist, staged rollout, or full-release strategy from the meeting notes. If no strategy is mentioned, write 暂无 or 默认全量发布(待确认) only when context clearly implies direct full release.

埋点设计

Reserve a placeholder only. Do not invent event names unless separately instructed. Output:

待补充:后续根据埋点规范补齐曝光、点击、转化及关键状态事件。

Quality Bar

Before finalizing, verify:

  • Every important meeting-note requirement appears in the PRD or is explicitly marked 待确认/不在本次范围.
  • When notes are missing or incomplete, every major Figma frame/state is converted into a PRD function row or a 待确认 item.
  • Every major Figma screen/frame in scope is reflected in a function point or state description.
  • Core function descriptions use the 示意图 / 功能场景 / 需求详情 table format and include exported screenshots or 待补充截图.
  • Detailed logic is specific enough for development and QA to understand behavior.
  • Unsupported assumptions are not presented as confirmed facts.
  • Markdown headings match the required structure exactly.
  • The design link is preserved without rewriting or shortening.

常见问题

5 问
答案由本站依据条目字段整理
会议纪要+Figma生成PRD skill怎么安装?

在支持 Skills 的客户端里执行:skillhub install user_d786d32b/writing-figma-prd-skill。安装方式为未标注。装完刷新技能列表或重开客户端。

会议纪要+Figma生成PRD skill支持哪些客户端?

资料没有标注宿主客户端,但只要客户端支持 Skills(Claude、Codex、Cursor 等),一般都能加载。

会议纪要+Figma生成PRD skill权限高吗,安全吗?

权限级别为未标注权限。安装前先看它会读取或写入哪些内容。

会议纪要+Figma生成PRD skill收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于技能本身和所用的模型或客户端,正式使用前按作者说明确认。

会议纪要+Figma生成PRD skill用什么许可证?

许可证标注为 未说明(许可证不明确)。商用或二次分发前请到仓库确认条款原文。

热门专题

按场景挑技能
全部专题 →

技能内容以作者仓库为准;分类、权限级别与许可证状态的中文说明为中文整理,最近核验 未标注。