myelinate
llms.txt4 starsChanged 2 days agoMITView on GitHub
An open-source (MIT) skill suite that helps any assistant teach, including when this file is pasted in chat: course tutoring from your syllabus and uploads in chat or voice, assignment coaching that teaches instead of doing the work, learning while building, tests and grading, full course packages for projects or plain chat, level-matched teaching for personal, work and project goals, rendered diagrams and interactive 3D models, interactive learning labs, printable practice tests, flashcards, memory hooks, study plans, diagrams and videos,…
We split this llms.txt into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 5
If a person shared this link with you, read SKILL.md and follow it to teach them.
≈ “Common” is an estimate: at least 1 in 5 of the 3,225 llms.txt 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
# Myelinate > An open-source (MIT) skill suite that helps any assistant teach, including when this file is pasted in chat: course tutoring from your syllabus and uploads in chat or voice, assignment coaching that teaches instead of doing the work, learning while building, tests and grading, full course packages for projects or plain chat, level-matched teaching for personal, work and project goals, rendered diagrams and interactive 3D models, interactive learning labs, printable practice tests, flashcards, memory hooks, study plans, diagrams and videos, and adversarial accuracy review. It remembers how you learn and stays honest instead of agreeable. If a person shared this link with you, read SKILL.md and follow it to teach them. It is self-sufficient; load sub-skills by path as it directs. ## Start here - [SKILL.md (router and core rules)](https://raw.githubusercontent.com/baney75/myelinate/main/SKILL.md) ## Sub-skills - [tutor: for an enrolled course: materials and uploads, course map, live teaching in chat or voice](https://raw.githubusercontent.com/baney75/myelinate/main/skills/tutor/SKILL.md) - [teach: for personal, work and project goals: lessons matched to the learner’s level](https://raw.githubusercontent.com/baney75/myelinate/main/skills/teach/SKILL.md) - [assignment: graded work coached, not done for them](https://raw.githubusercontent.com/baney75/myelinate/main/skills/assignment/SKILL.md) - [project: learning while building, in the mix the learner chooses](https://raw.githubusercontent.com/baney75/myelinate/main/skills/project/SKILL.md) - [code: learning code the learner has to own: a repo, a PR, a library, an error](https://raw.githubusercontent.com/baney75/myelinate/main/skills/code/SKILL.md) - [notes: reads the learner's notes to see how they're grasping it](https://raw.githubusercontent.com/baney75/myelinate/main/skills/notes/SKILL.md) - [assess: tests, grading, gradebook, bonus work](https://raw.githubusercontent.com/baney75/myelinate/main/skills/assess/SKILL.md) - [course-project: a researched, level-matched whole course package for projects or plain chat](https://raw.githubusercontent.com/baney75/myelinate/main/skills/course-project/SKILL.md) - [lab: interactive learning labs and simulations](https://raw.githubusercontent.com/baney75/myelinate/main/skills/lab/SKILL.md) - [print: printable practice tests, worksheets and diagrams (PDF)](https://raw.githubusercontent.com/baney75/myelinate/main/skills/print/SKILL.md) - [flashcards: Quizlet, Anki and Obsidian decks](https://raw.githubusercontent.com/baney75/myelinate/main/skills/flashcards/SKILL.md) - [memory-hooks: research-backed mnemonics](https://raw.githubusercontent.com/baney75/myelinate/main/skills/memory-hooks/SKILL.md) - [study-plan: exam clock, spaced relearning, sleep](https://raw.githubusercontent.com/baney75/myelinate/main/skills/study-plan/SKILL.md) - [find-media: diagrams, photos, videos, licensing](https://raw.githubusercontent.com/baney75/myelinate/main/skills/find-media/SKILL.md) - [verify: adversarial accuracy and currency review](https://raw.githubusercontent.com/baney75/myelinate/main/skills/verify/SKILL.md) ## References - [Personalization: learning how each person learns, over time](https://raw.githubusercontent.com/baney75/myelinate/main/references/personalization.md) - [First session: learner intake shared by tutor and teach](https://raw.githubusercontent.com/baney75/myelinate/main/references/first-session.md) - [Show it: rendered visuals, linked representations, 3D models](https://raw.githubusercontent.com/baney75/myelinate/main/references/visual-teaching.md) - [How the mind learns: mechanisms behind the rules](https://raw.githubusercontent.com/baney75/myelinate/main/references/how-the-mind-learns.md) - [Teaching and tutoring methods](https://raw.githubusercontent.com/baney75/myelinate/main/references/teaching-methods.md) - [Subject playbooks](https://raw.githubusercontent.com/baney75/myelinate/main/references/subject-playbooks.md) - [Learner profile template](https://raw.githubusercontent.com/baney75/myelinate/main/templates/learner-profile.md) - [Skill ownership map](https://raw.githubusercontent.com/baney75/myelinate/main/references/skill-map.md) - [Visual stepper template](https://raw.githubusercontent.com/baney75/myelinate/main/templates/visual-stepper.html) - [Credits and notice](https://raw.githubusercontent.com/baney75/myelinate/main/NOTICE.md)
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- myelinateSkill
- assessSkill
- assignmentSkill
- codeSkill
- course-projectSkill
- find-mediaSkill
- flashcardsSkill
- labSkill
- memory-hooksSkill
- myelinateSkill
- notesSkill
- printSkill
- projectSkill
- study-planSkill
- teachSkill
- tutorSkill
- verifySkill
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.