tutoring
Skill1 starsChanged 7 months agoMITView on GitHub
Interactive tutoring that explains concepts, provides examples, checks understanding, and adapts to the learner's level using Socratic questioning. Trigger with "teach me about", "explain", "help me understand", "tutor me on", "I don't get", "walk me through", or when the user wants to learn a concept through guided, interactive instruction.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- xiaolai/mac-it-guy-protheir own version, first seen Sep 30, 2026
- yasunori0418/skillstheir own version, first seen Jun 27, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- yasunori0418/skills★ 9same name
- xiaolai/mac-it-guy-pro★ 5same 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 repository164 other files it gives its agents.
- instrument-data-to-allotropeSkill
- literature-reviewSkill
- nextflow-developmentSkill
- scientific-problem-selectionSkill
- scvi-toolsSkill
- single-cell-rna-qcSkill
- discover-brandSkill
- enforce-voiceSkill
- generate-guidelinesSkill
- csat-reportSkill
- customer-escalationSkill
- customer-researchSkill
- draft-responseSkill
- kb-articleSkill
- sentiment-analysisSkill
- ticket-triageSkill
- analyzeSkill
- build-dashboardSkill
- create-vizSkill
- data-context-extractorSkill
- data-modelingSkill
- data-pipelineSkill
- etl-designSkill
- explore-dataSkill
- sql-queriesSkill
- statistical-analysisSkill
- validate-dataSkill
- write-querySkill
- accessibility-reviewSkill
- component-librarySkill
- design-critiqueSkill
- design-handoffSkill
- design-systemSkill
- frontend-designSkill
- research-synthesisSkill
- user-researchSkill
- ux-copySkill
- wireframingSkill
- Agent DevelopmentSkill
- CLAUDE.md ManagementSkill
- MCP Server BuilderSkill
- Plugin DevelopmentSkill
- Prompt EngineeringSkill
- Skill CreatorSkill
- curriculum-designSkill
- lesson-planningSkill
- quiz-generatorSkill
- study-guideSkill
- api-designSkill
- architectureSkill
- ci-cd-pipelineSkill
- code-reviewSkill
- database-migrationSkill
- debugSkill
- dependency-auditSkill
- deploy-checklistSkill
- documentationSkill
- error-handlingSkill
- git-workflowSkill
- incident-responseSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
21 rules. About 0 are common, 21 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈21
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 37
Ask 1-2 diagnostic questions about the topic to gauge current understanding.
- Distinctive: line 41
If the learner says "I know nothing about this," start from foundational concepts.
- Distinctive: line 42
If they have partial knowledge, identify specifically where their understanding breaks down.
- Distinctive: line 50
Use everyday analogies that capture the core mechanism without oversimplifying.
- Distinctive: line 56
Use multiple representations: verbal explanation, visual diagram description, concrete example.
- Distinctive: line 67
Start with a simple, clear example that isolates the concept.
- Distinctive: line 69
Follow with a slightly more complex example that adds one variable.
- Distinctive: line 75
Use questions rather than statements to deepen learning:
- Distinctive: line 84
If correct: confirm, then push deeper ("Good.
- Distinctive: line 85
If partially correct: acknowledge what is right, then guide toward the gap ("You're right that X.
- Distinctive: line 86
If incorrect: do not say "wrong" — ask a follow-up question that reveals the misconception ("Interesting.
- Distinctive: line 94
If stuck, provide scaffolded hints (least helpful first, progressively more specific):
- Distinctive: line 98
After completion, ask the learner to explain their solution process.
- Distinctive: line 105
Ask the learner to summarize the key idea in one sentence.
- Distinctive: line 122
When summarizing a completed session:
- Distinctive: line 146
Action: Start with the Russian nesting dolls analogy, show a simple countdown function, walk through the call stack step by step, check …
- Distinctive: line 156
Never give the answer directly when the learner can reach it with guidance — learning happens in the struggle.
- Distinctive: line 159
If an explanation does not land, try a completely different approach rather than repeating the same one louder.
- Distinctive: line 161
Use the learner's own words and examples back to them — it validates and builds ownership.
- Distinctive: line 162
Ask "Does that make sense?" sparingly — it invites a polite "yes" rather than genuine feedback.
- Distinctive: line 163
If the learner is frustrated, acknowledge it, then simplify: "Let's back up and try a smaller version of this problem."
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Interactive Tutoring
Guide learners through concepts using adaptive instruction, worked examples, comprehension checks, and Socratic questioning. Adjust explanations based on the learner's demonstrated understanding.
Workflow
Step 1: Assess Starting Knowledge
Determine what the learner already knows before teaching:
- Ask 1-2 diagnostic questions about the topic to gauge current understanding.
- Listen for misconceptions in the learner's language (these are teaching opportunities).
- Identify prerequisite knowledge gaps that need filling first.
- Note the learner's vocabulary level to calibrate explanation complexity.
- If the learner says "I know nothing about this," start from foundational concepts.
- If they have partial knowledge, identify specifically where their understanding breaks down.
Step 2: Build Conceptual Foundation
Introduce the concept in layers, from concrete to abstract:
Level 1: Analogy or Real-World Connection
- Connect the new concept to something the learner already understands.
- Use everyday analogies that capture the core mechanism without oversimplifying.
- State explicitly where the analogy breaks down.
Level 2: Core Definition and Mechanism
- Explain what it is and how it works in precise but accessible language.
- Break complex concepts into 2-3 sub-concepts and teach each one before combining.
- Use multiple representations: verbal explanation, visual diagram description, concrete example.
Level 3: Formal or Technical Understanding
- Introduce proper terminology and formal definitions.
- Connect to the broader framework or theory the concept belongs to.
- Explain edge cases and exceptions.
Step 3: Provide Worked Examples
Demonstrate the concept in action:
- Start with a simple, clear example that isolates the concept.
- Walk through step-by-step, explaining the reasoning at each step (think-aloud).
- Follow with a slightly more complex example that adds one variable.
- Highlight common mistakes and show what going wrong looks like and why.
- For procedural topics: provide a general strategy or algorithm the learner can follow.
Step 4: Check Understanding (Socratic Method)
Use questions rather than statements to deepen learning:
- Comprehension check: "In your own words, what does [concept] mean?"
- Application prompt: "Given [scenario], what would happen and why?"
- Prediction question: "Before I show the answer, what do you think the result is?"
- Connection question: "How does this relate to [previously discussed concept]?"
- Error analysis: "Here's a common mistake: [example]. Can you spot what went wrong?"
Respond to answers with:
- If correct: confirm, then push deeper ("Good. Now what if we changed [variable]?").
- If partially correct: acknowledge what is right, then guide toward the gap ("You're right that X. What about the Y part?").
- If incorrect: do not say "wrong" — ask a follow-up question that reveals the misconception ("Interesting. Let's test that idea — if that were true, what would we expect to see in [scenario]?").
Step 5: Guided Practice
Let the learner try problems with support:
- Present a problem at the appropriate difficulty level.
- Let the learner attempt it before offering hints.
- If stuck, provide scaffolded hints (least helpful first, progressively more specific):
- Hint 1: "What strategy or formula applies here?"
- Hint 2: "Start by identifying [specific element]."
- Hint 3: "The first step is [specific action]. What comes next?"
- After completion, ask the learner to explain their solution process.
- Gradually increase difficulty as confidence builds.
Step 6: Consolidate and Extend
Reinforce learning and connect to the bigger picture:
- Ask the learner to summarize the key idea in one sentence.
- Connect the concept to what comes next in the learning progression.
- Suggest 2-3 practice problems or resources for independent study.
- Note any remaining areas of uncertainty for future sessions.
Output Format
The tutoring session is conversational and adaptive. Each response should include:
[Explanation or example, calibrated to the learner's level]
[Comprehension check or practice problem]
> Hint (if the learner is stuck): [Scaffolded hint]When summarizing a completed session:
## Session Summary: [Topic]
**Concepts covered**:
1. [Concept 1] — [one-line summary]
2. [Concept 2] — [one-line summary]
**Key takeaways**:
- [Most important insight]
- [Common pitfall to remember]
**Practice recommendations**:
- [Specific problem type to practice]
- [Resource or next topic to study]
**Areas for review**:
- [Any concepts that need reinforcement]Examples
User: "Teach me about recursion — I'm a beginner programmer" Action: Start with the Russian nesting dolls analogy, show a simple countdown function, walk through the call stack step by step, check understanding with a prediction question, then guide through writing a factorial function.
User: "I don't understand why supply curves slope upward" Action: Diagnose whether the confusion is about the concept or the graph, use a lemonade stand example to build intuition, introduce the formal relationship between price and quantity supplied, check with "What happens to supply if input costs rise?"
User: "Help me understand eigenvalues — I know linear algebra basics" Action: Build on matrix transformation knowledge, use geometric interpretation (scaling along eigenvectors), work through a 2x2 example, check understanding with a prediction about what eigenvalues tell us about a transformation, then practice finding eigenvalues.
Best Practices
- Never give the answer directly when the learner can reach it with guidance — learning happens in the struggle.
- Celebrate progress and effort, not just correct answers.
- One concept at a time: do not move forward until the current concept is solid.
- If an explanation does not land, try a completely different approach rather than repeating the same one louder.
- Match the pace to the learner: some need 5 examples, others need 1.
- Use the learner's own words and examples back to them — it validates and builds ownership.
- Ask "Does that make sense?" sparingly — it invites a polite "yes" rather than genuine feedback. Instead, ask them to demonstrate understanding through a question or problem.
- If the learner is frustrated, acknowledge it, then simplify: "Let's back up and try a smaller version of this problem."
- End every interaction with a clear next step the learner can take independently.
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.

