Skip to main content
skill CX Codex

doc-digest — Claude Code skill: what it does and how to install

doc-digest turns lengthy documents, PDFs, spreadsheets, transcripts, and logs into a compact reference for ongoing work with an AI agent. Use it to carry relevant context across messages or into a fresh chat.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add egorfedorov/claude-context-optimizer --skill doc-digest -a claude-code
Open on GitHub

What doc-digest does

The skill creates a working digest of a long source file. It records identifying details about the material, outlines its parts with page or timestamp references, and preserves important claims, decisions, requirements, definitions, and figures. It also flags unresolved questions and inconsistencies, giving the next conversation a useful map back to the original.

The digest is written in the user's language and placed in a single code block. Its target size is roughly one tenth of the source, capped at 800 words. The skill then estimates the token counts of both versions and suggests continuing in the current chat, starting a new conversation with the digest, or pairing the digest with the original in a Claude.ai Project.

The digest is a working aid, not a substitute for the source in legal, financial, or safety-critical work. Check the original sections whenever exact obligations or other consequential details matter. The skill supports Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode.

What it helps with

  • Condense a lengthy PDF into a working reference
  • Preserve report sections with page references
  • Extract decisions and requirements from a transcript
  • Carry document context into a new chat
  • Flag inconsistencies and unresolved questions in a source

Example prompts for the agent

  • Create a working digest of this PDF so we can continue the analysis in another message.
  • Summarize this spreadsheet, keeping sheet names, important values, and suspicious rows.
  • Prepare a digest of this contract that tracks obligations, dates, penalties, and references to the original sections.

How to install doc-digest

1Skills CLI (Vercel)

npx skills add egorfedorov/claude-context-optimizer --skill doc-digest -a claude-code

2Manually: put the files in place

~/.claude/skills/doc-digest/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/doc-digest/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about doc-digest

How do I install doc-digest in Claude Code?

Run npx skills add egorfedorov/claude-context-optimizer --skill doc-digest -a claude-code. The skill file is located at ~/.claude/skills/doc-digest/SKILL.md.

What does the doc-digest skill do?

It condenses a long document into a structured reference containing key information and unresolved issues. You can use that reference to continue the current discussion or carry the work into a new chat.

How long is a doc-digest summary?

The target is about one tenth of the original, with an upper limit of 800 words. For legal, financial, or safety-critical work, consult the original document before relying on consequential details.

Source text

SKILL.md · MIT
---
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.

© egorfedorov · MIT · egorfedorov/claude-context-optimizer

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set6

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor