Token导航 LogoToken导航

Agent Skill · 研究检索

digest(digest 工具)

digest 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

digest 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 7,327。

总安装 19,293周安装 812GitHub Stars 11,677下载 6,756核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:digest(digest 工具)
来源仓库:https://github.com/anthropics/knowledge-work-plugins
仓库路径:skills/digest
安装命令:
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill digest
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill digest

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

digest 扫描所有连接的知识源活动记录,生成结构化摘要突出重要更新事项。支持每日或每周时间窗设定,自动整合聊天、邮件、文档等多渠道信息流。适用于周报撰写、进度同步或异常监控场景,提升信息聚合与提炼效率。需提前配置好 CONNECTORS.md 中所列的各类 MCP 数据源接入凭证与权限。

digest 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/digest

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/anthropics/knowledge-work-plugins --skill dige…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

digest 怎么安装?

在终端执行 npx skills add https://github.com/anthropics/knowledge-work-plugins --skill digest。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

digest 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

digest 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

digest 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

digest 用的人多吗?

公开数据是累计安装 19,293 次,近一周安装 812 次,下载 6,756 次,GitHub 11,677 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

digest 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 来源仓库有 11,677 星,维护活跃度相对可查。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
digest

digest 工具 · 本页

19,29311,677调用外部服务未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Digest Command

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Scan recent activity across all connected sources and generate a structured digest highlighting what matters.

Instructions

1. Parse Flags

Determine the time window from the user's input:

  • --daily — Last 24 hours (default if no flag specified)
  • --weekly — Last 7 days

The user may also specify a custom range:

  • --since yesterday
  • --since Monday
  • --since 2025-01-20

2. Check Available Sources

Identify which MCP sources are connected (same approach as the search command):

  • ~~chat — channels, DMs, mentions
  • ~~email — inbox, sent, threads
  • ~~cloud storage — recently modified docs shared with user
  • ~~project tracker — tasks assigned, completed, commented on
  • ~~CRM — opportunity updates, account activity
  • ~~knowledge base — recently updated wiki pages

If no sources are connected, guide the user:

To generate a digest, you'll need at least one source connected.
Check your MCP settings to add ~~chat, ~~email, ~~cloud storage, or other tools.

3. Gather Activity from Each Source

~~chat:

  • Search for messages mentioning the user (to:me)
  • Check channels the user is in for recent activity
  • Look for threads the user participated in
  • Identify new messages in key channels

~~email:

  • Search recent inbox messages
  • Identify threads with new replies
  • Flag emails with action items or questions directed at the user

~~cloud storage:

  • Find documents recently modified or shared with the user
  • Note new comments on docs the user owns or collaborates on

~~project tracker:

  • Tasks assigned to the user (new or updated)
  • Tasks completed by others that the user follows
  • Comments on tasks the user is involved with

~~CRM:

  • Opportunity stage changes
  • New activities logged on accounts the user owns
  • Updated contacts or accounts

~~knowledge base:

  • Recently updated documents in relevant collections
  • New documents created in watched areas

4. Identify Key Items

From all gathered activity, extract and categorize:

Action Items:

  • Direct requests made to the user ("Can you...", "Please...", "@user")
  • Tasks assigned or due soon
  • Questions awaiting the user's response
  • Review requests

Decisions:

  • Conclusions reached in threads or emails
  • Approvals or rejections
  • Policy or direction changes

Mentions:

  • Times the user was mentioned or referenced
  • Discussions about the user's projects or areas

Updates:

  • Status changes on projects the user follows
  • Document updates in the user's domain
  • Completed items the user was waiting on

5. Group by Topic

Organize the digest by topic, project, or theme rather than by source. Merge related activity across sources:

## Project Aurora
- ~~chat: Design review thread concluded — team chose Option B (#design, Tuesday)
- ~~email: Sarah sent updated spec incorporating feedback (Wednesday)
- ~~cloud storage: "Aurora API Spec v3" updated by Sarah (Wednesday)
- ~~project tracker: 3 tasks moved to In Progress, 2 completed

## Budget Planning
- ~~email: Finance team requesting Q2 projections by Friday
- ~~chat: Todd shared template in #finance (Monday)
- ~~cloud storage: "Q2 Budget Template" shared with you (Monday)

6. Format the Digest

Structure the output clearly:

# [Daily/Weekly] Digest — [Date or Date Range]

Sources scanned: ~~chat, ~~email, ~~cloud storage, [others]

## Action Items (X items)
- [ ] [Action item 1] — from [person], [source] ([date])
- [ ] [Action item 2] — from [person], [source] ([date])

## Decisions Made
- [Decision 1] — [context] ([source], [date])
- [Decision 2] — [context] ([source], [date])

## [Topic/Project Group 1]
[Activity summary with source attribution]

## [Topic/Project Group 2]
[Activity summary with source attribution]

## Mentions
- [Mention context] — [source] ([date])

## Documents Updated
- [Doc name] — [who modified, what changed] ([date])

7. Handle Unavailable Sources

If any source fails or is unreachable:

Note: Could not reach [source name] for this digest.
The following sources were included: [list of successful sources].

Do not let one failed source prevent the digest from being generated. Produce the best digest possible from available sources.

8. Summary Stats

End with a quick summary:

---
[X] action items · [Y] decisions · [Z] mentions · [W] doc updates
Across [N] sources · Covering [time range]

Notes

  • Default to --daily if no flag is specified
  • Group by topic/project, not by source — users care about what happened, not where it happened
  • Action items should always be listed first — they are the most actionable part of a digest
  • Deduplicate cross-source activity (same decision in ~~chat and email = one entry)
  • For weekly digests, prioritize significance over completeness — highlight what matters, skip noise
  • If the user has a memory system (CLAUDE.md), use it to decode people names and project references
  • Include enough context in each item that the user can decide whether to dig deeper without clicking through

平台分布

Codex

36.94%
按下载量换算2,496

Claude

29.71%
按下载量换算2,007

Cursor

19.63%
按下载量换算1,326

Gemini CLI

10.66%
按下载量换算720

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills