Skip to content
Development
Skill

/doc-digest

Turn a long document, PDF, transcript, spreadsheet or log into a compact working digest the conversation can continue from. Use when the user shares or pastes something long (several pages or more) and wants to discuss, analyze, compare or use it over more than one message, or

BOOST
From plugin
context-optimizer
1166 skills3 agents6 hooks
Install
$ npx -y skills add egorfedorov/claude-context-optimizer --skill doc-digest --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/doc-digest

Context preview

The summary Claude sees to decide when to auto-load this skill.

Turn a long document, PDF, transcript, spreadsheet or log into a compact working digest the conversation can continue from. Use when the user shares or pastes something long (several pages or more) and wants to discuss, analyze, compare or use it over more than one message, or

SKILL.md

doc-digest.SKILL.md
name: doc-digest
description: Turn a long document, PDF, transcript, spreadsheet or log into a compact working digest the conversation can continue from. Use when the user shares or pastes something long (several pages or more) and wants to discuss, analyze, compare or use it over more than one message, or asks to summarize a document so they can keep working with it.
license: MIT

Document digest

A long attachment is re-sent with every later message of the conversation. A digest that keeps what the work needs lets the rest of the work run on a fraction of it, most of all in a fresh conversation that starts from the digest instead of the file.

Write the digest

In the user's language, inside one code block so it copies cleanly, at most about a tenth of the source and never more than 800 words:

1. **What it is**: title, author or source, date, length, purpose, in one or two lines. 2. **Map**: the sections or parts in order, one line each, with page, slide, sheet or timestamp references, so a later question can go straight to the right place. 3. **Key content**: the claims, decisions, requirements, figures and definitions the user is likely to need, each with its reference. Quote exact wording only where it matters: legal terms, numbers, names, error messages. 4. **Gaps and doubts**: what the document leaves open, contradicts or gets wrong, in a line each.

Fit the digest to what the user said they want to do with the document: a contract review keeps obligations, dates and penalties; a dataset keeps the columns, units and odd values; a log keeps the first error and what led to it. Never pad it with general background.

Then

Give the size in one line, as an estimate: "The document is about 40K tokens; the digest is about 1.5K." Then offer one of these, whichever fits:

  • **Keep going here** and answer from the digest, opening the original only

for a detail the digest lacks.

  • **Continue in a new conversation**: open it, paste the digest and the

question. Every later message then costs a few percent of what it does here. Offer the `fresh-start` handoff if there is more than the document to carry over.

  • **In a Project** (claude.ai): add the original to the Project's knowledge

and the digest to its instructions, so new chats in it start with both.

Don't claim the digest replaces the document for anything legal, financial or safety-critical; point to the original sections for those.

Read more
Ships withcontext-optimizer

See what Claude costs you, and spend less of it. Every message re-sends the whole conversation, so long chats and long coding sessions use up limits fast and recall early details worse.

Get the whole plugin

Other skills on context-optimizer.