lecture-notes
Skill0 starsChanged 42 days agoMITView on GitHub
Turn a transcribed lecture, webinar, talk or training session into study notes. Use when the user asks to revise from a recording, wants key terms explained, needs a summary of what was taught, or asks to be tested on it.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- Noam-Marom/academic-studentstheir own version, first seen Nov 8, 2026
- Suryanandx/qvac-uitheir own version, first seen Nov 1, 2026
- ilamanov/skillstheir own version, first seen Oct 13, 2026
- SaB11F/lecture-notes-skilltheir own version, first seen Oct 9, 2026
- lfc070213/slides-to-handouttheir own version, first seen Sep 24, 2026
- ckt520728/claude-skillstheir own version, first seen Jul 1, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- Noam-Marom/academic-students★ 7same name
- orhoncan/lecture-notes-skill★ 6same name
- SaB11F/lecture-notes-skill★ 2same name
- ilamanov/skills★ 1same name
- lfc070213/slides-to-handout★ 1same name
- ckt520728/claude-skills★ 0same name
- Suryanandx/qvac-ui★ 0same 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 repository3 other files it gives its agents.
- find-the-momentSkill
- interview-notesSkill
- meeting-followupSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
4
Distinctive
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 10
Write notes in this order:
- Distinctive: line 15
When the user asks to be tested, ask questions one at a time and wait for the answer.
- Distinctive: line 17
Keep the speaker's definition even when it is loose or unusual.
- Distinctive: line 19
If the user asks about something the lecture never covered, say so rather than filling it in from elsewhere, then offer the general answer …
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
A lecture transcript is a wall of speech. What a student needs from it is structure, terms, and something to test themselves against.
- Find it with
list_transcriptswhen the user names the course or the date, orsearch_transcriptson a term that would have been said in it. - Fetch the full text with
get_transcript. Lectures build an argument from beginning to end, and a search passage taken out of the middle usually misleads. - Write notes in this order:
- the thesis the lecture argues, in one or two sentences
- the sections it moves through, each with what was actually claimed
- the terms that were defined, with the definition the speaker gave rather than the standard one
- the examples used, because they are what gets remembered in an exam
- When the user asks to be tested, ask questions one at a time and wait for the answer. Mark what was wrong against what the lecture said, quoting the line.
Keep the speaker's definition even when it is loose or unusual. If it conflicts with the standard one, note both and say which came from the lecture: that is the one being examined.
If the user asks about something the lecture never covered, say so rather than filling it in from elsewhere, then offer the general answer separately.
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.