teach-mode
Skill1 starsChanged 11 days agoMITView on GitHub
Appends concise educational notes to LEARNING.md after each completed chunk, turning development into an interactive masterclass.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- rules/AGENTS.mdAGENTS.md
- adapters/claude.mdCLAUDE.md
- asset-intakeSkill
- client-collabSkill
- design-tasteSkill
- diff-guardSkill
- motion-craftSkill
- no-slop-startSkill
- orchestratorSkill
- plannerSkill
- prompt-optimizerSkill
- reference-teardownSkill
- reviewerSkill
- scene-3dSkill
- storyboardSkill
- visual-qaSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Distinctive: line 35
Keep the entire note under 120 words total.
- Distinctive: line 37
Ensure the "Try it yourself" challenge is concrete (e.g., "Pass null to user_id in curl to test the 400 guard").
- Very specific: line 39
If LEARNING.md does not yet exist, create it with a top-level header # Learning Log before appending the first entry.
≈ “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
Teach Mode
Transform autonomous execution into an educational experience for the human developer. After every completed task chunk, capture the technical rationale and underlying computer science principles in LEARNING.md.
Configuration Modes
Teach mode supports three modes, set via user instruction or environment flag:
off: Skip note generation entirely to optimize for maximum throughput.on(default): Concise learning notes. Maximum 120 words per note. Focus on practical understanding.deep: Detailed architectural breakdown, trade-off analysis, alternative patterns, and underlying runtime mechanics.
Note Schema
Append each completed chunk to LEARNING.md in the project root using this structure:
### [Chunk ID]: [Task Title]
- **What we did**: [1 concise sentence describing the change]
- **Why**: [The architectural, performance, or domain reason]
- **Core concept**: [Fundamental concept explained in plain language]
- **Analogy**: [A single vivid real-world metaphor illustrating the concept]
- **Try it yourself**: [One hands-on challenge or experiment the user can run locally]Word Count Guard (for "on" mode)
In standard on mode:
- Keep the entire note under 120 words total.
- Strip preamble, greetings, and transitional filler.
- Ensure the "Try it yourself" challenge is concrete (e.g., "Pass null to user_id in curl to test the 400 guard").
If LEARNING.md does not yet exist, create it with a top-level header # Learning Log before appending the first entry.
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.

