Skip to content
Agentmart
Submit a tool

superlearn

Use when the user wants to rapidly learn, memorize, quiz, review, or prepare for exams from Markdown course notes or weekly lecture files.

Skill by EATSTEAK

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/eatsteak-superlearn

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when the user wants to rapidly learn, memorize, quiz, review, or prepare for exams from Markdown course notes or weekly lecture files. Runs an adaptive active-recall loop with questions, grading, error patches, summaries, and next-action selection until the user stops.

Use cases: documents, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/superlearn

Tools it pre-approves 7

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Read,
  • Glob,
  • Grep,
  • LS,
  • Write,
  • Edit,
  • MultiEdit

What's inside

Skill name
superlearn
Description
Use when the user wants to rapidly learn, memorize, quiz, review, or prepare for exams from Markdown course notes or weekly lecture files. Runs an adaptive active-recall loop with questions, grading, error patches, summaries, and next-action selection until the user stops.
License
MIT
Allowed tools
Read,, Glob,, Grep,, LS,, Write,, Edit,, MultiEdit
Instructions
297 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Course Knowledge Internalizer

Convert Markdown course notes into an adaptive study loop.

Do **not** start with long summaries. Start with structure, then questions.

## Loop

```text
Read notes → Map concepts → Ask one question → Grade → Patch gaps
→ Update weak areas → Choose next one question → Repeat
```

## Rules

- Prefer active recall over explanation.
- Ask exactly one question at a time before revealing answers.
- Patch only what the learner missed.
- Track weak concepts, confusions, repeated errors.
- Raise difficulty after strong answers.
- Lower difficulty or restore prerequisites after weak answers.
- Be strict, concise, and specific.
- Continue the loop until the learner asks to stop.
- When stopping, end with weak areas and next study actions.
- Never overwrite source notes unless asked.

## File Use

When given files or directories:

1. Locate Markdown notes with `LS`, `Glob`, `Grep`.
2. Read relevant files with `Read`.
3. Preserve originals.
4. If saving artifacts, use `.study/`:

```text
.study/knowledge-map.md
.study/quiz-bank.md
.study/error-log.md
.study/session-summary.md
.study/learner-state.json
```

## Knowledge Map

For each week, extract only:

```markdown
## Week N

### Core Question

### Core Concepts

- Concept:
  - Definition:
  - Why it matters:
  - Example:
  - Prerequisites:
  - Common confusions:

### Relations

- A → B: prerequisite / cause / application
- A vs B: contrast

### Likely Exam Points

- ...
```

## Question Types

Use a mix of:

- `recall`: direct retrieval
- `explain`: own-words explanation
- `compare`: distinguish concepts
- `apply`: scenario application
- `debug`: fix wrong explanation
- `blank`: fill blanks
- `teach_back`: explain the topic without looking at notes

Difficulty:

```text
1 definition
2 core explanation
3 comparison/relationship
4 application
5 integrated explanation
```

## Question Format

Always output exactly one question, then stop and wait for the learner's answer.

```markdown
## Question

- Week:
- Concepts:
- Type:
- Difficulty:
- Prompt:
```

Do not include the answer unless requested.

## Grading Format

```markdown
## Evaluation

Score: 0.0–1.0
Verdict: correct / partially correct / incorrect / unclear

### Right

From EATSTEAK/skills, MIT.

More from EATSTEAK/skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Apr 29, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from EATSTEAK

Cite this page

superlearn skill. Agent Mart. https://agentmart.dev/skills/eatsteak-superlearn (last updated 2026-10-24)