agentsclimarketplace

Math tutor

Skill vikynofebriputra-creator/Orkas-Awesome-AgentSkills/education/skills/math-tutor

Access a curated library of high-quality agents and modular skills for Orkas and other agent frameworks to accelerate task automation and development.

Install
npx -y skills add vikynofebriputra-creator/Orkas-Awesome-AgentSkills --skill math-tutor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

5.5 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it

Math Tutor

When To Use

  • The user asks for K12 math explanation, concept clarification, worked examples, or step-by-step tutoring within a grade/curriculum boundary.
  • The user asks to generate math practice problems, variants, unit exercises, or an exam-paper draft for a grade, chapter, topic, difficulty, and question type.
  • The user asks to check a student's answer, analyze mistakes, grade a solution process, or summarize learning weaknesses.
  • The user provides a math problem image and wants transcription, confirmation, or grading.

Do not use for open-ended mathematical modeling, Python/local expression calculation, Wolfram-style symbolic computation, university-level research math, or generic homework tutoring outside math. Do not promise PDF export, external account sync, persistent error-book storage, or regional textbook coverage unless the current environment actually supports it.

How To Call

  1. Identify the mode: concept_explanation, guided_solution, question_generation, answer_check, error_analysis, exam_draft, learning_report, or image_problem.
  2. Determine grade/stage and topic. If missing, infer cautiously from the math content; if the grade boundary matters, ask one concise question.
  3. Check curriculum boundaries with references/curriculum-boundaries.md. If the requested method is beyond the student's grade, state that and solve using in-scope methods when possible.
  4. For explanations and guided solutions, use references/explanation-workflow.md.
  5. For question generation or exam drafts, use references/question-templates.md and verify every generated answer before showing it.
  6. For grading, answer checking, or error analysis, use references/grading-and-error-analysis.md. Always solve independently first, then compare with the student's work.
  7. For images, use references/attachment-policy.md: transcribe, detect multiple problems, confirm low-confidence text, and ask the user to choose a target problem when needed.
  8. For learning reports, use references/report-templates.md. Use only available data; if data is insufficient, say so.
  9. Before returning math feedback, run the verification checklist in references/verification-protocol.md.

Return Format

Concept explanation:

**Topic**
- Grade/stage:
- Concept:

**Core idea**
- ...

**Key rule or formula**
- ...

**Example**
...

**Common mistake**
- ...

**Your turn**
- ...

Answer check / grading:

**Check Result**
- Correct / partly correct / incorrect:
- Score, if grading:

**Step Review**
1. ...

**First Key Error**
- ...

**Correct Method**
- ...

**Next Practice**
- ...

Question generation:

**Practice Set**
- Grade:
- Topic:
- Difficulty:
- Count:

**Questions**
1. ...

**Answers And Verification**
- Show only when the user asks for answers, or after the user has attempted the problems.

External Dependencies

  • No fixed external dependencies.
  • Image-based math problems require the current environment to read images. If recognition confidence is low, ask the user to paste or confirm the problem text.
  • Exporting PDFs, syncing an error book, or saving long-term learning reports requires explicit user request and available file/storage tooling.

Limits And Known Issues

  • Do not overclaim exact textbook alignment for a region/version unless the user provides the textbook or the current curriculum reference covers it.
  • Do not introduce beyond-grade methods as the main solution unless the user explicitly asks for enrichment.
  • Do not generate copyrighted exam papers from proprietary sources. Generate original practice based on topics and templates.
  • Do not say a student's answer is correct before independently solving and verifying it.
  • Do not collect unnecessary personal information from minors.

Full Examples

User:

帮我批改这道初中数学题:2x + 3 = 11,我算 x = 3。

Reply:

**Check Result**
- Incorrect, but the equation-solving direction is right.

**Step Review**
1. Start from `2x + 3 = 11`.
2. Move `3` to the right side: `2x = 8`.
3. Divide by `2`: `x = 4`.

**First Key Error**
- The last division step should be `8 ÷ 2 = 4`, not `3`.

**Verification**
- Substitute `x = 4`: `2×4 + 3 = 8 + 3 = 11`, so it checks.

**Next Practice**
- Try one similar equation: `3x - 5 = 10`.

User:

出 5 道八年级一次函数中等难度题,先别给答案。

Reply:

**Practice Set**
- Grade: Grade 8
- Topic: Linear functions
- Difficulty: medium
- Count: 5
- Answers: hidden until you finish or ask for them

**Questions**
1. ...

What ships with it: 8 files

477.9 KB alongside SKILL.md

Gives 0 of the 12 instructions most learn study skills give in ~1.1k tokens

Counted across 546 of the 573 authors here whose files we hold, read 2026-08-07

  • Calculate the zone of proximal development before teachingin 25 of 546, across 8 files
  • Produce self-contained HTML lessonsin 24 of 546, across 8 files
  • Record user preferences in a notes filein 23 of 546, across 5 files
  • Maintain a teaching workspace in the current directoryin 21 of 546, across 4 files
  • Find high-quality resources before writing lessonsin 19 of 546, across 5 files
  • Make lessons beautiful, short, and quickly completablein 19 of 546, across 3 files
  • Create reusable components for lessonsin 19 of 546, across 5 files
  • Create compressed reference documents for quick lookupin 19 of 546, across 3 files
  • Update the mission file and records upon mission changesin 16 of 546, across 2 files
  • Set min_dist to 0.0 for clustering preprocessingin 16 of 546, across 6 files
  • Populate the mission file before teachingin 15 of 546, across 1 file
  • Include interactive feedback loops in lessonsin 15 of 546, across 1 file

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 327,132. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.