jlu1023/learning-stack
A Socratic tutor plugin for Claude Code: learn from your own notes, in Obsidian or any folder of PDFs, slides and Markdown, with spaced retrieval quizzes and roadmaps.
stack: Python
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/jlu1023/learning-stack MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit jlu1023/learning-stack/plugin/skills/connect .claude/skills/connect $ npx degit jlu1023/learning-stack/plugin/skills/ingest .claude/skills/ingest $ npx degit jlu1023/learning-stack/plugin/skills/lecture .claude/skills/lecture $ npx degit jlu1023/learning-stack/plugin/skills/lint .claude/skills/lint $ npx degit jlu1023/learning-stack/plugin/skills/method .claude/skills/method $ npx degit jlu1023/learning-stack/plugin/skills/primer .claude/skills/primer $ npx degit jlu1023/learning-stack/plugin/skills/query .claude/skills/query $ npx degit jlu1023/learning-stack/plugin/skills/quiz .claude/skills/quiz $ npx degit jlu1023/learning-stack/plugin/skills/roadmap .claude/skills/roadmap $ npx degit jlu1023/learning-stack/plugin/skills/setup .claude/skills/setup $ npx degit jlu1023/learning-stack/plugin/skills/teach .claude/skills/teach
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (11)
Similar rigs
MetamusicX/zissa-wiki
Zissa Wiki — an LLM-maintained research knowledge base in plain markdown, maintained by any AI agent (Claude, Codex, Gemini, DeepSeek, Kimi, Grok, Mistral or any chat app). Implements Karpathy's LLM Wiki pattern; checks every quote against
Pragmatist 4.4k tok · · Q18
vagmcs/dots
My dotfiles
YOLO Cowboy 1.3k tok · · Q5
minanyang/brain
A pattern for letting an LLM agent build a persistent, compounding understanding of you and your work from its own sessions and your work logs
Pragmatist 2.3k tok · · Q5
tim-kaa-py/ai-wiki
LLM-maintained AI knowledge wiki (Karpathy pattern, OKF v0.1) — Claude Code ingests sources, synthesizes wiki pages, and surfaces contradictions instead of silently merging them
Skill Collector 3.6k tok · · Q33