doc-digest
Skill127 starsChanged 5 months agoMITView on GitHub
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.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- antrafa/skillstheir own version, first seen Oct 20, 2026
- duncan-buildroom/freeskillstheir own version, first seen Oct 13, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- duncan-buildroom/freeskills★ 65same name
- antrafa/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- ccoSkill
- fresh-startSkill
- project-contextSkill
- sharpen-promptSkill
- token-checkSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 50
Don't claim the digest replaces the document for anything legal, financial or safety-critical.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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:
- What it is: title, author or source, date, length, purpose, in one or two lines.
- 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.
- 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.
- 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-starthandoff 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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.