Superlearn plugin
Plugin and skill for Claude Code, Codex and Kilo that researches a topic on the web and builds a local learning board
- 124 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The agent browses the web, starts a local web server and runs Python scripts.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/superlearnDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The agent browses the web, starts a local web server and runs Python scripts.
This is third-party code. Review the repository files before installing.
What it does
Superlearn runs with `/superlearn <topic>`. The agent searches the web itself, pulls real YouTube videos and arXiv papers, repeats a research loop until the topic is covered and assembles the result into a learning board. Then it launches a local web app where the board opens for study. The board holds research notes, concept deep-dives, diagrams and mind maps, curated papers, working code and learning roadmaps. Blocks are as long as the teaching requires and are not trimmed. There are no quizzes, streaks or game mechanics. The conversation with the same agent continues: requests such as «go deeper on X» or «add the original papers» update the page in place within seconds. The page design adapts to the subject. Everything is stored on disk.
Who it is for. People who want to master a topic and not read a short summary, and who already pay for Claude Code, Codex or Kilo.
Good fit when
- You want to learn internals such as Postgres, with diagrams and primary sources.
- Material should be gathered on one board with videos, papers and code.
- After the first version the board is extended with requests in the same session.
- Data must stay on your disk with no separate API keys.
Not a fit when
- You need quizzes, flashcards and gamification.
- You need a quick two-paragraph answer.
- Python 3.9 or later is missing on the machine.
Example request
/superlearn how Postgres internals work: build a board with diagrams, papers and code.Limitations
Claude Code, OpenAI Codex or Kilo are required, along with Python 3.9 or later; scripts use only the standard library, so nothing is installed through `pip`. Research runs over the live web through the chosen agent, so it consumes your subscription limits and time. Quality depends on the sources found, and videos and papers deserve a check. The board opens as a local web app launched by the agent. For Codex and Kilo it connects as a standard Agent Skill from `.agents/skills/superlearn`.
How to disable. In Claude Code run `/plugin uninstall superlearn@superlearn-marketplace`. For Codex and Kilo delete the skill folder. Saved boards stay on disk and are deleted by hand.
FAQ
How do I install Superlearn in Claude Code?
Run `/plugin marketplace add raiyanyahya/superlearn`, then `/plugin install superlearn@superlearn-marketplace`.
Are API keys required?
No. The plugin runs on the agent subscription you already have and saves everything to disk.
Which agents does it work with?
Claude Code as a plugin, and OpenAI Codex and Kilo as a standard Agent Skill.
What is on the board?
Notes, concept deep-dives, diagrams, mind maps, papers, working code and roadmaps. The Postgres example has 38 blocks.
Can the board be extended later?
Yes. In the same session tell the agent to go deeper or add papers and the page updates in place.
Discussion
No questions or reviews yet.
Related
PluginsClaude Code plugin that builds a study plan for any topic, runs adaptive quizzes and schedules reviews with the SM-2 algorithm.
Five skills turn Claude Code or Codex into a tutor: a knowledge probe, a topic map, one step of teaching and a lock-in quiz.
A Claude Code plugin that builds a knowledge system of markdown files from a conversation with you: folder structure, note templates, a processing pipeline and
About a hundred skills for Claude Code: meetings, research, publishing, TDD, Telegram, email and personal analytics
A skill that analyzes materials and subtitles, checks facts against sources and keeps a personal library in a local folder.
Deep Research Skills
Deep Research Skill
A structured deep-research skill for Claude Code, OpenCode and Codex with human control at every step
README in short
The plugin runs a research loop, assembles the board and launches a local viewer. Python standard library, MIT license, and an example screenshot shows a full board.
README badge
Original SKILL.md
---
name: superlearn
description: Build an interactive learning board on any topic. Use when the user wants to learn, study, or research a subject and get a curated, visual learning experience — researches the live web with the agent's own web search, scrapes YouTube and arXiv for real IDs and papers, runs an iterative research loop into a scratch workspace, authors a validated board JSON, and serves the Superlearn web app locally. Triggers on "/superlearn", "$superlearn", "I want to learn", "teach me", "help me study", "make me a learning board".
---
This is the Superlearn playbook packaged as a standard Agent Skill — the same
pipeline that ships as a Claude Code plugin, usable from OpenAI Codex, Kilo
(formerly Kilo Code), and any agent that reads `SKILL.md`. The playbook below
is written with Claude Code's names for things; resolve these three
differences first, then follow it exactly.
**1. The Superlearn root.** The commands below run bundled scripts as
`"${CLAUDE_PLUGIN_ROOT}/scripts/…"`. Claude Code sets that variable
automatically; elsewhere, define it once in every shell you use:
```bash
export CLAUDE_PLUGIN_ROOT="{{SUPERLEARN_ROOT}}"
```
If the value above is still an unstamped placeholder in curly braces, this
file is inside the Superlearn repo itself: the root is three directories up —
the directory that contains `scripts/validate_board.py` and `app/index.html`.
(`scripts/install.py` stamps the real path when it copies this file into a
global skills directory.)
**2. Tool names.** Map the playbook's tool names to your environment:
| The playbook says | OpenAI Codex | Kilo |
|---|---|---|
| WebSearch | built-in web search (on by default; `--search` for live results) | `websearch` — enable Web Search for non-Kilo providers, or fall back to `webfetch` on known good sources |
| WebFetch | fetch the page from the shell, e.g. `curl -sL <url>` | `webfetch` |
| `superlearn-researcher` agent (Task tool) | spawn sub-agents, one per subtopic, in parallel; a `superlearn-researcher` role ships in `.codex/agents/` | the `task` tool with the `superlearn-researcher` subagent, several concurrently |
If your environment has no subagent support, research the subtopics
sequentially yourself — same steps, same files, one at a time.
**3. Network access.** The scrapers call the YouTube and arXiv APIs and the
app serves on `http://localhost:4321`, so the sandbox needs real network
access. In Codex, that means:
```toml
# ~/.codex/config.toml
[sandbox_workspace_write]
network_access = true
```
In Kilo, allow the `python3` script invocations when prompted (or add a
`permission` rule for them).
Everything else — the phases, the board schema, the quality bar — applies