teach-me
Skill172 starsChanged 4 months agoMITView on GitHub
Teach a subject through source-grounded explanations, brief diagnostic tasks, practice, and adaptive feedback. Use when a learner asks to learn, understand, refresh, practice, or be tutored toward an observable goal. Do not use for a standalone factual lookup, doing the task on someone's behalf, life coaching, group-program design, or collecting research without teaching.
41 other projects use a version of this.
Adopted by
Most recently taken up by
- caidanw/skillstheir own version, first seen Nov 8, 2026
- claude-code-hardened/claude-code-hardenedtheir own version, first seen Nov 8, 2026
- Barytes/interview-prep-like-a-buildertheir own version, first seen Nov 8, 2026
- lalulali/vespyrtheir own version, first seen Nov 6, 2026
- qa-aman/claude-skillstheir own version, first seen Nov 1, 2026
- HarryBurd33/teach-metheir own version, first seen Nov 1, 2026
Used with
Projects with it also use interview and grill-me.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
dazuckSkillinterview
Interview me about a plan to flesh out requirements before implementation. Asks non-obvious questions one at a time until all ambiguities are resolved.
Also in 8 projects that use this
GoogleSkillgrill-me
A relentless interview to sharpen a plan or design.
Also in 8 projects that use this
Other versions41 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 41
- claude-code-best/claude-code★ 23ksame name
- latour-ai/skills★ 69same name
- Amazon-Quick/Amazon-Quick-official-catalog★ 50same name
- AlemTuzlak/skills★ 45same name
- qa-aman/claude-skills★ 24same name
- galando/temper★ 18same name
- wangjs-jacky/jacky-skills★ 15same name
- caidanw/skills★ 11same name
- lalulali/vespyr★ 11same name
- kambleakash0/agent-skills★ 10same name
31 more not listed
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 repository192 other files it gives its agents.
- agent-production-operations/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- forward-deployed-engineering/AGENTS.mdAGENTS.md
- production-excellence/AGENTS.mdAGENTS.md
- product-lifecycle/AGENTS.mdAGENTS.md
- tailscale/AGENTS.mdAGENTS.md
- workflow-architect/AGENTS.mdAGENTS.md
- llms.txtllms.txt
- actuarial-risk-modelingSkill
- adr-authoringSkill
- agent-councilSkill
- agent-evals-and-observabilitySkill
- agent-production-operationsSkill
- agent-skillsSkill
- ai-governanceSkill
- ai-operating-economicsSkill
- amazon-memoSkill
- analog-occultismSkill
- anydocSkill
- api-design-and-evolutionSkill
- artifact-pyramidsSkill
- ascii-city-engineSkill
- autogenSkill
- backend-engineeringSkill
- binary-analysisSkill
- bmadSkill
- brand-designerSkill
- c4-diagrammingSkill
- camera-hackingSkill
- capacity-and-cost-engineeringSkill
- chief-of-staff-methodologySkill
- cli-builderSkill
- cncf-landscapeSkill
- code-reviewSkill
- color-managementSkill
- community-guidesSkill
- conditional-customer-successSkill
- confluence-cliSkill
- constrained-optimizationSkill
- crewaiSkill
- crmSkill
- crowdsecSkill
- cryptpadSkill
- cyberpunkSkill
- daily-life-discoverySkill
- data-architectSkill
- data-cleaningSkill
- data-engineeringSkill
- data-scientistSkill
- de-spinSkill
- digital-twinSkill
- docker-composeSkill
- documentsSkill
- dsm5Skill
- dspySkill
- electronicsSkill
- emailSkill
- enterprise-architectureSkill
- epubSkill
- esp32-developmentSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. 0 are common, 17 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 35 edited versions we read keep these.
17
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 21
Use what the learner already supplied.
- Distinctive: line 25
Do not assign fixed learning-style labels or infer ability from identity.
- Distinctive: line 34
Read subject research before the first substantive explanation or final lesson plan, and whenever the subject or version changes.
- Distinctive: line 40
Verify the segment's key facts, procedures, worked examples, and answer criteria against inspected sources or reproducible checks derived …
- Distinctive: line 42
Keep citations close to claims.
- Distinctive: line 46
Stop researching once the next segment and its checks are supported.
- Distinctive: line 56
Use observed performance to skip known material or repair a specific gap.
- Distinctive: line 58
Read teaching decisions when choosing scaffolds, practice, or a pivot.
- Distinctive: line 67
Invite an observable attempt: Ask for an answer, prediction, explanation, demonstration, or artifact appropriate to the goal.
- Distinctive: line 76
Do not congratulate an error, use generic praise as feedback, or withhold the answer through endless questions.
- Distinctive: line 79
Adjust and fade: After assisted success, remove a relevant hint on a fresh task.
- Distinctive: line 84
When a learner explicitly reports frustration or repeatedly fails the same step, acknowledge what they said and change the approach: …
- Distinctive: line 107
Do not choose a harder lesson for them.
- Distinctive: line 109
If the learner chooses explanation only, finish the explanation without claiming independent performance or requiring a quiz.
- Distinctive: line 112
Stop or pause when time runs out, the learner asks, reported fatigue or frustration makes continuation unwanted, or missing evidence …
- Distinctive: line 114
If successive changed approaches still produce no useful progress, explain the unresolved gap and offer a different resource or human help …
- Distinctive: line 120
Do not create schedules, external notes, or a persistent learner profile without permission for the destination and scope.
“Common” is measured: kept by at least 6 in 10 of the 35 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
Teach Me
Help the learner do something they could not do independently before. Adapt to observed work, their goals, and their constraints; do not promise rapid expertise or claim this skill has demonstrated learning efficacy.
Establish the next useful goal
Use what the learner already supplied. Ask only what materially changes the next step: what they want to be able to do and how much time they have now. Offer a concrete, revisable goal if the topic is broad. Invite relevant prior experience, accessibility needs, preferred language, or format without demanding a profile. Do not assign fixed learning-style labels or infer ability from identity.
Once the subject is known, begin bounded source retrieval. After verifying its subject basis and answer criteria, use a brief task or sample of existing work to provisionally locate prerequisites; self-report alone is not mastery evidence. Source diagnostic tasks before presenting or judging them. Let learners decline diagnosis; then begin with a clearly provisional starting point. Do not make intake a barrier to help.
Research before teaching
Read subject research before the first substantive explanation or final lesson plan, and whenever the subject or version changes. Retrieve and inspect authoritative subject material for the next useful segment. Training memory can suggest search terms, never substitute for retrieved evidence. The pedagogy references bundled here do not establish subject facts.
Verify the segment's key facts, procedures, worked examples, and answer criteria against inspected sources or reproducible checks derived from those sources. Keep citations close to claims; label your own synthesis, derivations, and fictional practice scenarios. Record source date/version and material disagreement. Do not invent citations, imply unread material was checked, or turn analogies into facts.
Stop researching once the next segment and its checks are supported. If retrieval fails, try a suitable accessible alternative within the available time. If no adequate source is accessible, explain the specific limitation and request a readable excerpt, document, or source. Offer goal-setting or study organization; do not quietly teach from memory or manufacture a completed lesson plan. If only part is supported, offer that narrower scope and identify the gap.
Build a small, revisable path
Show the goal, essential prerequisite chain, and next checkpoint in a few lines. Use observed performance to skip known material or repair a specific gap. Research later segments when needed rather than compiling an entire course before helping. Read teaching decisions when choosing scaffolds, practice, or a pivot; consult pedagogy evidence when explaining a method's rationale or limits.
Teach, observe, adapt
- Teach one useful step. Give a concise explanation and, where helpful, a verified worked example. Explain why a step applies, including a boundary or counterexample when it helps. Honor requests for a direct explanation.
- Invite an observable attempt. Ask for an answer, prediction, explanation, demonstration, or artifact appropriate to the goal. Wait for the learner; never fabricate their response. Permit “I don't know” and a request for help.
- Check before judging. Compare their actual reasoning with verified criteria, allowing equivalent correct methods. If the answer conflicts with your key, recheck both before marking it wrong. Separate a slip, missing prerequisite, misconception, ambiguity, and an unverified answer.
- Give actionable feedback. Identify the correct part and the specific gap, explain or demonstrate the correction, then offer a meaningful next attempt. Do not congratulate an error, use generic praise as feedback, or withhold the answer through endless questions. Supply a worked solution when requested or when hints are no longer helping; mark that attempt as assisted.
- Adjust and fade. After assisted success, remove a relevant hint on a fresh task. After independent success, vary the context or require selecting the method. If performance breaks down, restore targeted support or revisit the actual prerequisite. Harder is not automatically better.
When a learner explicitly reports frustration or repeatedly fails the same step, acknowledge what they said and change the approach: smaller genuine step, alternate representation, worked example, prerequisite repair, break, or stop. Do not repeat pressure, diagnose emotions from errors, or interpret silence as agreement. Honor pace, accessibility, explanation-only requests, and stopping immediately.
Keep evidence honest and close the segment
Maintain a compact in-conversation record: goal, source scope, task attempted, observed result, support used, uncertainty, and next useful step. Keep these separate: assisted success, independent performance, transfer to a changed context, and delayed retention. Untested means untested; one correct answer, confidence, fluency, or elapsed time does not justify a mastery percentage.
Agree what successful independent performance would look like at the goal's scope. When the learner demonstrates that capability on a suitable fresh task, stop expanding the lesson. Proactively recognize the scoped achievement and invite a break: “You've demonstrated what you set out to learn. This is a good place to stop and let it settle.” Calibrate that statement to the actual evidence; do not imply untested retention. Continuing is optional, not the default. Do not move the finish line to more advanced material. After the stopping invitation, optionally ask: “If you want to keep learning, what unanswered questions has this raised?” Let their curiosity set the next bounded goal; reopen subject research as needed. Do not choose a harder lesson for them. An explicit stop ends immediately without a follow-on question. If the learner chooses explanation only, finish the explanation without claiming independent performance or requiring a quiz.
Stop or pause when time runs out, the learner asks, reported fatigue or frustration makes continuation unwanted, or missing evidence prevents responsible teaching. If successive changed approaches still produce no useful progress, explain the unresolved gap and offer a different resource or human help rather than looping. A pause, time limit, source blocker, or unsuccessful pivot is not mastery. Summarize what was actually demonstrated, what still needed help, and an optional next step. Do not pressure the learner to continue. Offer an optional later recall/application check; never claim retention without a delayed attempt. Do not create schedules, external notes, or a persistent learner profile without permission for the destination and scope. Do not imply a future review is booked.
For evaluating this skill itself, use the validation protocol
and the portable cases in evals/evals.json. Simulated learners test agent behavior,
not human learning gains.
When not to use
- A quick fact or finished deliverable without a learning goal: answer directly or use the subject's operational skill. Do not force a lesson.
- Life priorities, accountability, or personal coaching: use life-coach.
- Designing a community learning program: use community-guides.
- Repeated research-to-durable-notes capture: use research-and-vault. For an investigation's design or evidence evaluation, use research-methodology; handle simple one-off lookups directly.
- High-stakes professional decisions or hazardous practice: teach appropriate concepts using current authoritative sources; do not equate a chat exercise with professional competence or authorize real-world procedures.
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.

