Digest logo

Digest

OrganizationPopular
anthropics
digest

Generate a daily or weekly digest of activity across all connected sources. Use when catching up after time away, starting the day and wanting a summary of mentions and action items, or reviewing a week's decisions and document updates grouped by project.

Overview

Publisheranthropics
Repositoryknowledge-work-plugins
Skill namedigest
Stars
24.9K
Forks
3K
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by anthropics on GitHub. Read the source before you install it.

Installation

Install the Digest AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/anthropics/knowledge-work-plugins.git /tmp/knowledge-work-plugins
mkdir -p .claude/skills
cp -r /tmp/knowledge-work-plugins/enterprise-search/skills/digest .claude/skills/digest
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Digest in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Digest on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Digest is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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

Frequently asked questions

What does the Digest AI skill do?

Generate a daily or weekly digest of activity across all connected sources. Use when catching up after time away, starting the day and wanting a summary of mentions and action items, or reviewing a week's decisions and document updates grouped by project.

Why use Digest on TypingMind?

Because you install it once and use it with any model. Digest is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Digest in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/anthropics/knowledge-work-plugins/tree/main/enterprise-search/skills/digest. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Digest?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Digest?

As many as you like. As long as a model supports skills, you can use Digest with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Digest AI skill free?

Yes. It is published on GitHub by anthropics under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇