course-learning

Use RAG and knowledge graph tools to answer course-learning questions with sources and related concepts.

IndexedApache-2.0★ 2

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/think520-course-learning

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.

About

Use RAG and knowledge graph tools to answer course-learning questions with sources and related concepts.

Use cases: ml

Reviews

Write a review

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/course-learning

What's inside

Skill name: course-learning
Description: Use RAG and knowledge graph tools to answer course-learning questions with sources and related concepts.
License: Apache-2.0
Instructions: 18 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

# Course Learning Assistant

Use this skill when the user asks about course materials, Obsidian notes, concepts, prerequisites, or learning order.

## Tool choice

- For "是什么", definitions, explanations, summaries, or "在哪里出现过", call `rag_search` first.
- For "和谁有关", tags, source notes, course/chapter placement, or concept relationships, call `graph_query` first.
- For mixed questions, call both `rag_search` and `graph_query`, then separate textual evidence from graph relationships.
- If the user says they added or changed notes, call `obsidian_sync` before searching.

## Answer style

- Always cite sources from `rag_search` when using retrieved text.
- When graph and retrieved text disagree, state the difference instead of forcing one answer.
- Keep answers study-oriented: define the concept, show where it appears, then list related concepts or next steps.

From think520/react-agent, Apache-2.0.

Signals

Stars: 2
Forks: 0
Open issues: 0
Last commit (this folder): May 19, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Apache-2.0
Repository: github.com/think520/react-agent
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from think520

Cite this page

course-learning skill. Agent Mart. https://agentmart.dev/skills/think520-course-learning (last updated 2026-10-24)