Agent skill

Yida Flash Note To Prd

从已有钉钉闪记、会议记录或需求文档内容中提取产品需求，生成结构化 PRD。若用户只给 taskUuid，先用 yida-tingji 读取内容，再进入本技能。

MITAuto-check passedProduct & Project Management

Install Yida Flash Note To Prd

skills CLI

$ npx skills add openyida/openyida --skill yida-flash-note-to-prd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install openyida/openyida yida-flash-note-to-prd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/openyida/openyida.git skills-src && mkdir -p .claude/skills && cp -r skills-src/yida-skills/skills/yida-flash-note-to-prd .claude/skills/yida-flash-note-to-prd && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "yida-flash-note-to-prd" agent skill from https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-flash-note-to-prd into .claude/skills/yida-flash-note-to-prd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yida-flash-note-to-prd", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-flash-note-to-prd

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add openyida/openyida --skill yida-flash-note-to-prd -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install openyida/openyida yida-flash-note-to-prd --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/openyida/openyida.git skills-src && mkdir -p .agents/skills && cp -r skills-src/yida-skills/skills/yida-flash-note-to-prd .agents/skills/yida-flash-note-to-prd && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "yida-flash-note-to-prd" agent skill from https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-flash-note-to-prd into .agents/skills/yida-flash-note-to-prd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yida-flash-note-to-prd", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add openyida/openyida --skill yida-flash-note-to-prd -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install openyida/openyida yida-flash-note-to-prd --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/openyida/openyida.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/yida-skills/skills/yida-flash-note-to-prd .cursor/skills/yida-flash-note-to-prd && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "yida-flash-note-to-prd" agent skill from https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-flash-note-to-prd into .cursor/skills/yida-flash-note-to-prd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yida-flash-note-to-prd", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/openyida/openyida.git --path yida-skills/skills/yida-flash-note-to-prd

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add openyida/openyida --skill yida-flash-note-to-prd -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install openyida/openyida yida-flash-note-to-prd --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/openyida/openyida.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/yida-skills/skills/yida-flash-note-to-prd .gemini/skills/yida-flash-note-to-prd && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "yida-flash-note-to-prd" agent skill from https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-flash-note-to-prd into .gemini/skills/yida-flash-note-to-prd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yida-flash-note-to-prd", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install openyida/openyida yida-flash-note-to-prd

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add openyida/openyida --skill yida-flash-note-to-prd -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/openyida/openyida.git skills-src && mkdir -p .github/skills && cp -r skills-src/yida-skills/skills/yida-flash-note-to-prd .github/skills/yida-flash-note-to-prd && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "yida-flash-note-to-prd" agent skill from https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-flash-note-to-prd into .github/skills/yida-flash-note-to-prd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yida-flash-note-to-prd", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add openyida/openyida --skill yida-flash-note-to-prd -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install openyida/openyida yida-flash-note-to-prd --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/openyida/openyida.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/yida-skills/skills/yida-flash-note-to-prd .opencode/skills/yida-flash-note-to-prd && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "yida-flash-note-to-prd" agent skill from https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-flash-note-to-prd into .opencode/skills/yida-flash-note-to-prd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yida-flash-note-to-prd", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: yida-flash-note-to-prd
GitHub stars: 220
Token cost: ~1.9k tokens
SKILL.md length: 411 words
Files: 5 (incl. references)
Skills in repo: 58
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

从已有钉钉闪记、会议记录或需求文档内容中提取产品需求，生成结构化 PRD。若用户只给 taskUuid，先用 yida-tingji 读取内容，再进入本技能。

Works in 4 steps: 使用视觉能力完整识别图片中的所有文字内容，包括标题、正文、表格、列表等 → 注意识别图片中的结构化布局（如分栏、卡片、流程图等），保留其逻辑关系 → 识别图片中的标签/标注（如 Emoji… → …
Tasks that involve PRD writing
SKILL.md covers 严格禁止 (NEVER DO), 严格要求 (MUST DO), 适用场景 and 触发条件, plus 14 more sections
Reaches shanji.dingtalk.com and alidocs.dingtalk.com

What it does

Yida Flash Note To Prd is an agent skill from openyida/openyida. 从已有钉钉闪记、会议记录或需求文档内容中提取产品需求，生成结构化 PRD。若用户只给 taskUuid，先用 yida-tingji 读取内容，再进入本技能。

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/examples.md`, `references/flash-note-prd-template.md` and `references/flash-note-prompt.md`).

It sits in Product & Project Management, covering PRD writing. The repository describes itself as: Your own personal YiDA AI assistant! The licence is MIT.

When your agent uses it

Tasks that involve PRD writing

Example prompts

“/yida-flash-note-to-prd”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

使用视觉能力完整识别图片中的所有文字内容，包括标题、正文、表格、列表等
注意识别图片中的结构化布局（如分栏、卡片、流程图等），保留其逻辑关系
识别图片中的标签/标注（如 Emoji 标识、颜色标注、高亮文字等），这些通常是重点信息
将识别结果作为闪记文本，进入 Step 2 继续处理

What it can do on your machine

Read from SKILL.md and the folder at commit b52e65e. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- shanji.dingtalk.com
- alidocs.dingtalk.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Yida Flash Note To Prd loads about 1.9k tokens when it runs, and up to ~6.8k if it reads all its reference files. Until then it costs about 26 tokens; SKILL.md has 411 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~26
When it runs · the whole SKILL.md, loaded when a task matches: ~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~6.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from openyida/openyida at commit b52e65e, republished under its MIT licence (© openyida). 411 words, ~1,919 tokens.

Download SKILL.mdSave it as .claude/skills/yida-flash-note-to-prd/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.

name: yida-flash-note-to-prd
description: 从已有钉钉闪记、会议记录或需求文档内容中提取产品需求，生成结构化 PRD。若用户只给 taskUuid，先用 yida-tingji 读取内容，再进入本技能。

闪记和会议内容转 PRD

严格禁止 (NEVER DO)

不要在没有闪记内容的情况下强行生成 PRD，必须等待用户提供闪记文本、图片或链接
不要将生成的 PRD 写入项目根目录，必须写入 prd/<项目名>/prd.md
不要忽略闪记中的 A1 结构化摘要（会议摘要、待办事项、决策结论），这是最高优先级信息
不要生成泛泛的会议纪要，输出必须是可直接驱动宜搭开发的结构化 PRD

严格要求 (MUST DO)

必须自动识别输入类型：文本闪记 / 图片闪记 / 闪记链接，分别处理
用户只提供 taskUuid 且要求转 PRD 时，必须先加载 yida-tingji 读取听记内容，再用读取结果生成 PRD
必须提取会议元信息（标题、参会人、时间）并写入 PRD 上下文
生成的 PRD 必须包含：MVP 边界、用户角色与权限、核心用户旅程、功能模块、字段设计表、流程/状态机、数据关联与约束、交互验收标准、报表需求、OpenYida 落地约束、待确认事项
生成完成后必须提示用户确认 PRD 内容；用户确认要继续搭应用时，交给 yida-app

适用场景

用户意图	触发条件
闪记转需求文档	用户发送闪记文本/图片、提到"闪记"、"会议纪要"、"会议记录"
快速启动开发	从会议记录直接生成可执行的 PRD
taskUuid 转 PRD	先由 `yida-tingji` 读取听记，再处理已有内容

触发条件

正向触发：

用户发送闪记文本/图片
用户提到"闪记"、"会议纪要"、"会议记录"、"闪记转需求"
用户发送钉钉闪记链接（shanji.dingtalk.com 或 alidocs.dingtalk.com）
用户口述会议要点，要求整理成需求

⚠️ PRD 生成后还需 yida-app 流程创建应用；本技能不处理非需求类文档（技术文档、代码文件）。

异常处理

异常场景	处理方式
闪记内容为空或过短	提示用户补充更多会议内容，至少需要包含功能需求描述
图片识别失败	提示用户重新上传清晰图片，或直接粘贴闪记文本
闪记链接无法访问	提示用户在钉钉中打开链接，复制全文后粘贴
PRD 文件写入失败	检查 `prd/` 目录是否存在，确认文件系统权限
生成的 PRD 质量不佳	展示待确认事项，引导用户补充关键信息后重新生成

Agent 错误处理策略

当 Agent 执行本技能遇到错误时，必须遵循以下默认行为：

错误类型	默认处理策略
输入内容为空	停止执行，主动询问用户提供闪记内容（文本/图片/链接）
输入内容过短（<100 字）	提示用户内容可能不足以生成完整 PRD，询问是否继续或补充
图片识别失败	提示用户重新上传清晰图片，或改用文本粘贴方式
闪记链接无法访问	引导用户在钉钉中打开链接，复制全文后粘贴
文件写入失败	检查目录权限，尝试创建 `prd/` 目录后重试
生成结果不完整	展示已生成内容，询问用户是否需要补充或调整
未知错误	停止执行，完整展示错误信息，建议用户反馈问题

概述

本技能将钉钉闪记、会议记录、需求讨论文本或截图转成结构化 PRD。生成结果写入 prd/<项目名>/prd.md，用户确认后再交给 yida-app 执行应用搭建或补齐。

核心理念：PRD 只写业务语义和验收口径，便于后续技能读取并执行；不要在 PRD 中编造 appType、formUuid、fieldId 等真实 ID。

核心能力：

自动识别闪记输入：用户直接发送闪记文本或图片，AI 智能体自动触发本技能
智能识别钉钉 A1 / 闪记生成的结构化摘要（会议摘要、待办事项、决策结论等），作为高优先级信息
自动提取会议元信息（标题、参会人、时间、时长等），丰富 PRD 上下文
识别发言人角色标注（如"张三(产品经理)"），帮助区分不同角色视角
生成可直接驱动开发的结构化 PRD，包含 MVP 边界、角色权限、核心旅程、功能模块、字段设计表、流程/状态机、数据约束、验收标准、报表需求和待确认事项

何时使用

当以下情况发生时，自动触发本技能（无需用户明确说"转 PRD"）：

用户发送了一段会议纪要/闪记文本（包含发言人对话、讨论内容等）
用户发送了闪记截图/图片（钉钉闪记的图文纪要截图）
用户发送了钉钉闪记链接（shanji.dingtalk.com 或 alidocs.dingtalk.com）
用户提到"闪记"、"会议纪要"、"会议记录转PRD"、"闪记转需求"等关键词
用户口述会议要点，要求整理成需求

⚡ AI 智能体自动执行流程（核心）

重要：本技能的主要执行方式是 AI 智能体直接处理，而非调用 CLI 命令。AI 智能体自身就是大模型，可以直接完成闪记内容理解和 PRD 生成。

当识别到用户输入为闪记/会议纪要内容时，按以下流程自动执行：

[Step 1] 识别输入类型
         - 图片 → 用视觉能力识别图片中的所有文字内容
         - 文本 → 直接使用
         - 闪记链接 → 提示用户复制闪记全文后粘贴
           ↓
[Step 2] 内容预处理（AI 智能体自行完成，参照预处理规则）
         - 去除时间戳、口语填充词、重复标点
         - 识别会议元信息（标题、参会人、时间等）
         - 识别 A1 生成的结构化摘要段落（📋 会议摘要、✅ 待办事项、📌 决策结论等）
         - 识别发言人及其角色标注
           ↓
[Step 3] 生成结构化 PRD
         - 按照「PRD 输出模板」和「内容提取规则」生成
         - AI 智能体直接生成，无需调用外部 AI 接口
         - 严格遵循字段设计规则（使用宜搭标准字段类型）
         - 每个模块写清功能描述、交互规则、业务规则、字段设计表和验收标准
         - PRD 必须包含足够的业务语义信息，使后续技能可直接读取执行
           ↓
[Step 4] 写入文件 prd/<项目名>/prd.md
           ↓
[Step 5] 输出摘要，询问用户是否需要调整
         - 展示：项目名称、功能模块数、待确认事项数
         - 询问：是否需要修改或补充
         - 用户确认继续搭建时，交给 `yida-app`

图片输入处理规则

当用户发送图片时：

使用视觉能力完整识别图片中的所有文字内容，包括标题、正文、表格、列表等
注意识别图片中的结构化布局（如分栏、卡片、流程图等），保留其逻辑关系
识别图片中的标签/标注（如 Emoji 标识、颜色标注、高亮文字等），这些通常是重点信息
将识别结果作为闪记文本，进入 Step 2 继续处理

闪记链接处理规则

以下 URL 模式自动识别为钉钉闪记链接：

https://shanji.dingtalk.com/app/transcribes/... — 钉钉闪记（AI 听记）分享链接
https://alidocs.dingtalk.com/... — 钉钉文档中的闪记

钉钉闪记页面是 SPA 应用，需要登录态才能获取数据。当用户提供闪记链接时：

提示用户在钉钉中打开链接，复制闪记全文后粘贴
或导出为 .txt 文件后告知文件路径

CLI 命令（可选的自动化工具）

以下 CLI 命令是可选的自动化工具，适用于批量处理或脚本化场景。日常使用中，直接将闪记内容发给 AI 智能体即可。

flash-to-prd — 闪记转 PRD

bash

# 从文件读取闪记内容并生成 PRD
openyida flash-to-prd --file <闪记文件路径> [--name <项目名>]

# 从标准输入读取闪记内容
cat meeting.txt | openyida flash-to-prd --name <项目名>

参数	必填	说明
`--file`	否	闪记文本文件路径（支持 .txt / .md）
`--name`	否	项目名称，用于生成 PRD 文件名（默认从闪记内容中提取）
`--max-tokens`	否	AI 最大输出 token 数（默认 8000）

输出：生成 prd/<项目名>/prd.md 文件

处理流程

[Step 1] 接收闪记内容（文本/文件/链接）
           ↓
[Step 2] 预处理（preprocessFlashNote）：
         - 去除时间戳、口语填充词、重复标点
         - 合并同一发言人的连续发言
         - 清理多余空行
           ↓
[Step 3] 会议识别（新增能力）：
         - extractMeetingMeta：提取会议元信息（标题、参会人、时间、时长等）
         - extractA1Summary：识别钉钉 A1 生成的结构化摘要段落
         - extractSpeakers：识别发言人及其角色标注
         - buildMeetingContext：组装会议上下文信息
           ↓
[Step 4] 分段判断（splitIntoSegments）：
         - ≤ 6000 字 → 单段模式
         - > 6000 字 → 按段落边界智能分段
           ↓
[Step 5] AI 提取（buildFlashNoteToPrdPrompt）：
         - 会议上下文作为高优先级信息注入 Prompt
         - 单段模式：三层 Prompt 架构，直接输出 Markdown PRD
         - 多段模式：每段输出 JSON 结构化数据
           ↓
[Step 6]（仅多段模式）合并去重（buildMergePrompt）：
         - 合并各段 JSON 结果
         - 去重、解决冲突
         - 生成完整 Markdown PRD
           ↓
[Step 7] 输出到 prd/<项目名>/prd.md
           ↓
[Step 8] 展示 PRD 摘要，询问用户确认或调整

PRD 输出模板

📖 生成的 PRD 文件标准结构详见 references/flash-note-prd-template.md。

生成规则参考

📖 完整的三层 Prompt 架构、Prompt 原文、分段处理策略和调用方式详见 references/flash-note-prompt.md。

Show full SKILL.md (173 more words)Show less

闪记内容预处理规则

在发送给 AI 之前，对闪记原文进行预处理（实现在 build-flash-note-prompt.js 的 preprocessFlashNote 函数中）：

处理步骤	说明	正则/规则
去除时间戳	移除 `[00:01:23]` 等时间标记	`/\[?\d{1,2}:\d{2}(?::\d{2})?\]?\s*/g`
去除口语填充词	移除"嗯"、"那个"、"就是说"、"对对对"等口语化表达	预定义填充词列表匹配
合并连续空行	多个空行合并为单个换行	`/\n{3,}/g` → `\n\n`
去除重复标点	连续重复标点合并为一个	`/([，。！？,\.!?])\1+/g`
合并连续发言	同一人连续多段发言合并为一段（用逗号连接）	按发言人前缀匹配合并
保留发言人标识	保留"张三："等发言人前缀，帮助 AI 理解上下文	支持中英文冒号格式

会议识别能力（v2.0 新增）

预处理完成后，自动执行以下会议识别步骤：

会议元信息提取（extractMeetingMeta）

从闪记头部提取结构化的会议元信息：

识别字段	匹配关键词	示例
会议标题	会议主题/标题/名称、Meeting Title/Topic	`会议主题：产品需求评审会`
会议时间	会议时间/日期、Date/Time	`会议时间：2026-03-24 14:00`
会议时长	会议时长/时长、Duration	`会议时长：45 分钟`
参会人员	参会人/与会人/出席、Participants/Attendees	`参会人员：张三、李四、王五`
主持人	主持人/组织者/发起人、Organizer/Host	`主持人：张三`
会议地点	会议地点/位置、Location	`会议地点：3 号会议室`

钉钉 A1 摘要识别（extractA1Summary）

自动识别钉钉 A1 / 闪记 AI 生成的结构化摘要段落，支持 Emoji 标识和纯文本标识两种格式：

段落类型	Emoji 标识	纯文本标识	说明
会议摘要	📋 / 📝	【会议摘要】	AI 生成的会议内容总结
待办事项	✅ / ☑️	【待办事项】	会议中确定的行动项
决策结论	📌 / 🔑 / 💡	【决策结论】	会议中达成的决策
讨论要点	📊 / 📈	【讨论要点】	关键讨论内容摘要
后续跟进	⏭️ / 👉	【后续跟进】	下一步计划和跟进事项

优先级说明：A1 摘要段落被视为高优先级信息，会优先注入生成上下文，帮助 AI 更准确地提取需求。

发言人角色识别（extractSpeakers）

自动识别闪记中发言人的角色标注，支持以下格式：

张三(产品经理)：...      → 识别为 张三，角色：产品经理
李四（技术负责人）：...   → 识别为 李四，角色：技术负责人
王五[设计师]：...         → 识别为 王五，角色：设计师
赵六：...                → 识别为 赵六，角色：未标注

识别到的发言人角色信息会注入生成上下文，帮助 AI 区分不同角色视角的发言。

PRD 输出要求

生成 prd/<项目名>/prd.md 时，写清以下内容；缺失时写入「待确认事项」，不要假装已经明确：

第一版必须做什么，哪些放到二期。
谁使用主入口，谁维护后台表，谁审批、调度或查看报表。
用户从进入页面到完成关键任务的步骤。
表单之间如何关联，哪些字段唯一，哪些字段只能后台维护。
状态有哪些，谁能改，允许从哪个状态流转到哪个状态。
时间冲突、重复提交、并发提交、取消、退回、失败如何处理。
用可验证标准描述验收口径。
PRD 只写业务语义，不写 appType、formUuid、fieldId；真实 ID 写入 .cache/<项目名>-schema.json。

前置依赖

Node.js ≥ 16
已登录宜搭（存在有效 .cache/auth-token-<env>.json），用于调用 AI 接口

注意事项

闪记质量影响 PRD 质量：如果闪记内容过于碎片化或口语化严重，生成的 PRD 可能需要用户手动补充完善
长文本分段处理：闪记内容超过 6000 字时，建议分段提取后合并，避免超出 AI 模型 token 限制
待确认事项必须处理：PRD 中的"待确认事项"需要用户逐一确认后，才能进入开发阶段
PRD 不记录技术 ID：PRD 文档只记录业务语义信息（字段名、类型、说明），formUuid、fieldId 等技术 ID 写入 .cache/ 临时文件
支持迭代优化：用户可以对生成的 PRD 提出修改意见，AI 会基于反馈重新调整 PRD 内容
本技能不读写 memory：生成的 PRD 输出到 prd/<项目名>/prd.md 文件，不依赖跨会话的 memory 状态

Files

SKILL.md and 4 other files (references) in yida-skills/skills/yida-flash-note-to-prd of openyida/openyida.

SKILL.md
references/examples.md
references/flash-note-prd-template.md
references/flash-note-prompt.md
references/yida-field-types.md

Open the folder on GitHubat commit b52e65e

Compare with similar skills

Yida Flash Note To Prd next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Yida Flash Note To Prd compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Yida Flash Note To Prd this skillopenyida/openyida	220	—	~1.9k	Automated safety check: Pass	MIT	today
CCPM Project Managementautomazeio/ccpm	8.4k	—	~1.1k	Automated safety check: Pass	MIT	6 mo ago
Ralph Tui Create Beadssubsy/ralph-tui	2.5k	1 repos	~2.6k	Automated safety check: Pass	MIT	1 mo ago
Trellis Brainstormanjiemo/SunnyBeach	178	7 repos	~4k	Automated safety check: Pass	Apache-2.0	28 days ago
Ralph Tui Create Beads Rustsubsy/ralph-tui	2.5k	1 repos	~2.8k	Automated safety check: Pass	MIT	1 mo ago
Ralph Tui Create JSONsubsy/ralph-tui	2.5k	1 repos	~2.6k	Automated safety check: Pass	MIT	1 mo ago

Similar skills

CCPM Project Management
automazeio/ccpm
Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.
8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
Product & Project ManagementAuto-check passed
Ralph Tui Create Beads
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.
2.5k GitHub starsUsed in 1 repo~2.6k tokens
Product & Project ManagementAuto-check passed
Trellis Brainstorm
anjiemo/SunnyBeach
Guides collaborative requirements discovery before implementation.
178 GitHub starsUsed in 7 repos~4k tokens
Product & Project ManagementAuto-check passed
Ralph Tui Create Beads Rust
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).
2.5k GitHub starsUsed in 1 repo~2.8k tokens
Product & Project ManagementAuto-check passed
Ralph Tui Create JSON
subsy/ralph-tui
Convert PRDs to prd.json format for ralph-tui execution. An agent skill from subsy/ralph-tui.
2.5k GitHub starsUsed in 1 repo~2.6k tokens
Product & Project ManagementAuto-check passed
Prd Generator
jamesrochabrun/skills
Generate comprehensive Product Requirements Documents (PRDs) for product managers.
216 GitHub starsUsed in 2 repos~3.8k tokens
Product & Project ManagementAuto-check passed

Questions about Yida Flash Note To Prd

What does Yida Flash Note To Prd do?

从已有钉钉闪记、会议记录或需求文档内容中提取产品需求，生成结构化 PRD。若用户只给 taskUuid，先用 yida-tingji 读取内容，再进入本技能。. Yida Flash Note To Prd is an agent skill from openyida/openyida.

When should I use Yida Flash Note To Prd?

Yida Flash Note To Prd fits situations like: tasks that involve PRD writing.

How do I install Yida Flash Note To Prd in Claude Code?

Run `npx skills add openyida/openyida --skill yida-flash-note-to-prd -a claude-code`. Or copy the skill folder (yida-skills/skills/yida-flash-note-to-prd in openyida/openyida) into .claude/skills/yida-flash-note-to-prd in your project. Claude Code loads it when a task matches its description.

How do I install Yida Flash Note To Prd in Codex?

Run `npx skills add openyida/openyida --skill yida-flash-note-to-prd -a codex`. Or copy the skill folder (yida-skills/skills/yida-flash-note-to-prd in openyida/openyida) into .agents/skills/yida-flash-note-to-prd in your project. Codex loads it when a task matches its description.

Can I use Yida Flash Note To Prd in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openyida/openyida --skill yida-flash-note-to-prd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/yida-flash-note-to-prd, .gemini/skills/yida-flash-note-to-prd, .github/skills/yida-flash-note-to-prd and .opencode/skills/yida-flash-note-to-prd in your project.

What does Yida Flash Note To Prd need to run?

SKILL.md names no scripts, command-line tools or credentials: Yida Flash Note To Prd is instructions for the agent only.

Does Yida Flash Note To Prd access the network?

SKILL.md names 2 domains. In commands or code: shanji.dingtalk.com and alidocs.dingtalk.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Yida Flash Note To Prd safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Yida Flash Note To Prd use?

Yida Flash Note To Prd is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Yida Flash Note To Prd use?

About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.9k tokens, read only when the agent opens those files.

What are the alternatives to Yida Flash Note To Prd?

Skills that share tags, products or a category with Yida Flash Note To Prd: CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars) and Ralph Tui Create Beads Rust (subsy/ralph-tui, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Yida Flash Note To Prd?

openyida (a GitHub organization) maintains it in openyida/openyida, which has 220 GitHub stars. The repository holds 58 skills in this directory. The repository was last updated on October 8, 2026.

Source: openyida/openyida on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Yida Flash Note To Prd

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

闪记和会议内容转 PRD

严格禁止 (NEVER DO)

严格要求 (MUST DO)

适用场景

触发条件

异常处理

Agent 错误处理策略

概述

何时使用

⚡ AI 智能体自动执行流程（核心）

图片输入处理规则

闪记链接处理规则

CLI 命令（可选的自动化工具）

flash-to-prd — 闪记转 PRD

处理流程

PRD 输出模板

生成规则参考

闪记内容预处理规则

会议识别能力（v2.0 新增）

会议元信息提取（extractMeetingMeta）

钉钉 A1 摘要识别（extractA1Summary）

发言人角色识别（extractSpeakers）

PRD 输出要求

前置依赖

注意事项

Files

Compare with similar skills

Similar skills

More from openyida/openyida

Related

Questions about Yida Flash Note To Prd