English | 中文
This is an agent skill + CLI for Tongji Look (look.tongji.edu.cn):
- login via Tongji IAM SSO (Playwright),
- list courses (recent list or full search),
- transcribe a lecture to
SRT + TXT,
- generate a lecture timeline outline (
*_timeline.txt) from SRT (agent-generated, Simplified Chinese),
- download lecture slide snapshots (filename includes snapshot time),
- then let the current agent write a Markdown study note from transcript + slide images.
Install
Method 1
Copy the repo link to your agent and say: help me install this skill.
Method 2
Copy the whole look-tongji-notes/ folder into your skills directory:
- Codex:
~/.codex/skills/look-tongji-notes
- Claude Code:
~/.claude/skills/look-tongji-notes
Method 3 (Codex)
Open Codex and run:
$skill-installer install https://github.com/walkerkiller/look-tongji-notes
Method 4 (Claude Code)
Open Claude Code and run:
/plugin marketplace add https://github.com/walkerkiller/look-tongji-notes
/plugin install look-tongji-notes
Usage (CLI)
<SKILL_DIR> is the folder that contains SKILL.md.
Setup credentials (recommended):
python "<SKILL_DIR>/scripts/look_tongji.py" setup
List recent courses:
python "<SKILL_DIR>/scripts/look_tongji.py" list
Search courses by name (recommended for accuracy, calls get_all_courses internally):
python "<SKILL_DIR>/scripts/look_tongji.py" list --all --query "<COURSE_NAME_KEYWORD>"
Transcript only (transcribe, aliases transcript / trans):
python "<SKILL_DIR>/scripts/look_tongji.py" transcribe --lecture-url "<LECTURE_URL>"
Combined mode (note, runs transcript + slide in parallel by default):
python "<SKILL_DIR>/scripts/look_tongji.py" note --lecture-url "<LECTURE_URL>"
Download slide snapshots for a lecture:
python "<SKILL_DIR>/scripts/look_tongji.py" slide --lecture-url "<LECTURE_URL>"
If throttling is suspected, reduce concurrency:
python "<SKILL_DIR>/scripts/look_tongji.py" slide --course-id "<COURSE_ID>" --sub-id "<SUB_ID>" --concurrency 2 --retries 5
In the look-tongji:note workflow, the agent generates a timeline outline after the SRT subtitle file is produced:
- File:
./tongji-output/<course_id>_<sub_id>_timeline.txt
- One line per segment (Simplified Chinese), format:
Start-Over：Stage Main Content
- Example:
00:00-05:30：Course Orientation and Assessment Description
- Skip only if the user explicitly says:
no outline / no timeline.
Artifacts are written to ./tongji-output/ under your current working directory.
Agent Note
When a user says look-tongji:setup / look-tongji:list / look-tongji:note, follow SKILL.md and run the matching CLI commands in scripts/look_tongji.py.
For look-tongji:note, default to running transcript + slide download in parallel; only skip slide download when the user explicitly asks not to download slides/PPT.
When writing notes, use both transcript output and slide images by default.
If the user provides a course name, prefer list --all --query ... to avoid missing courses that are not in the recent list.
Notice / Compliance
[!CAUTION]
It is strongly recommended to set your Tongji account/password via the CLI (setup) before asking the agent to generate notes. Do not paste passwords into chat.
[!NOTE]
- Inspiration and parts of the code are from: Fudan_iCourse_Subscriber
- This project is intended for personal learning and review only, and for technical communication. It does not save full video files by default.
- Users must comply with the relevant platform rules and school policies. Any misuse (including re-distribution of copyrighted course videos/audios) is the user's responsibility.
- When logging in outside the campus network (or without Tongji VPN), enhanced authentication may be triggered. Keep this in mind if you run the agent remotely.
ToDo
Best practices
