new-concept-note
Skill0 starsChanged 5 days agoMITView on GitHub
Create or deepen a concept note in 20_Concepts following the study layer spec. Use when a session, paper, book or question introduces a concept worth its own note. Writes files, so only run when asked.
In this repository35 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- llms.txtllms.txt
- adaptive-scaffoldSkill
- calibration-coachSkill
- compression-challengeSkill
- counterfactualSkill
- defuddleSkill
- dependency-checkSkill
- error-recoverySkill
- json-canvasSkill
- memory-palaceSkill
- misconception-drillSkill
- mistake-reviewSkill
- new-trackSkill
- no-ai-checkpointSkill
- obsidian-basesSkill
- obsidian-cliSkill
- obsidian-markdownSkill
- pretestSkill
- process-paperSkill
- process-webSkill
- quizSkill
- record-attemptSkill
- recovery-after-inactivitySkill
- retention-auditSkill
- review-queueSkill
- run-checksSkill
- schedule-reviewSkill
- spoken-mockSkill
- teach-the-agentSkill
- transfer-labSkill
- vault-searchSkill
- visual-reconstructionSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Check 20_Concepts/ first: one idea per note.
- Very specific: line 11
Every claim from a session cites its source (transcript timestamp, chapter or page).
- Very specific: line 12
Add 5 to 8 flashcards question::answer, one cloze with ==gap==.
- Very specific: line 13
Run run-checks and add a line to 90_System/Agent_Log/YYYY-MM.md.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
- Check
20_Concepts/first: one idea per note. If the concept exists, extend it instead of creating another. - File name: the concept name with underscores (
Retrieval_Practice.md); the# Titlekeeps spaces. - Frontmatter:
type: concept,category,tracks,sessions,aliases,tags: [type/concept, flashcards]. - Follow
90_System/Specs/Study_layer.md(headings in90_System/Specs/study_layer.json):> [!tldr] In 3 lines, then the explanation section (400 to 900 words of prose) and the takeaways section, then the rest. Tutor mode: concept notes are the learner's own notes, so create the structure and leave the study layer and the cards for the learner to write. Draft them only when the learner asks, say it is a draft, and have the learner edit every card. - Every claim from a session cites its source (transcript timestamp, chapter or page); every outside claim cites a note in
40_References/. Never invent a reference. - Add 5 to 8 flashcards
question::answer, one cloze with==gap==. - Run
run-checksand add a line to90_System/Agent_Log/YYYY-MM.md.
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.

