Look Tongji Notes

Where:

• <SKILL_DIR> is the directory that contains this SKILL.md.

Output + storage conventions

• Credentials: saved to <SKILL_DIR>/.env (and ignored by <SKILL_DIR>/.gitignore).
• Auth cache: saved to <SKILL_DIR>/state/ (JWT token cache and last selection).
• Artifacts (subtitles + transcript + slides + notes): saved to the agent working directory in ./tongji-output/ (relative to where the command is executed).

Never ask the user to paste passwords into chat. Prefer interactive terminal input (or environment variables) and keep .env out of version control.

References

When you need more details, read:

• references/url-guide.md for how to obtain and parse lecture URLs
• references/troubleshooting.md for common setup/login/ASR issues
• references/security.md for credential/cache/output safety notes

Command: look-tongji:setup

Goal: verify basic dependencies and store credentials in <SKILL_DIR>/.env.

Run:

python "<SKILL_DIR>/scripts/look_tongji.py" setup

Non-interactive options (avoid passing passwords via CLI when possible):

python "<SKILL_DIR>/scripts/look_tongji.py" setup --username "<YOUR_ID>" --password "<YOUR_PASSWORD>" --overwrite

If dependencies are missing, install them from <SKILL_DIR>/requirements.txt.

Command: look-tongji:list

Goal: login and list recent courses with indices.

Run:

python "<SKILL_DIR>/scripts/look_tongji.py" list

If you need to search a course by name (and it may not appear in "recent"), use the full course list method TongjiClient.get_all_courses() for higher accuracy.

CLI shortcut:

python "<SKILL_DIR>/scripts/look_tongji.py" list --all --query "<COURSE_NAME_KEYWORD>"

If you already know which course index to choose (for non-interactive runs):

python "<SKILL_DIR>/scripts/look_tongji.py" list --choose 1

This saves the selected course to <SKILL_DIR>/state/last_course.json.

Command: look-tongji:note

Goal: default workflow for one lecture: transcribe + download slides + write notes.

Preferred inputs (ask user for one of these):

• Lecture page URL from look.tongji.edu.cn (best effort parsing for course_id + sub_id)
• course_id + sub_id (most reliable)

Transcript-only command with a lecture URL:

python "<SKILL_DIR>/scripts/look_tongji.py" transcribe --lecture-url "<LECTURE_URL>"

Transcript-only command with IDs:

python "<SKILL_DIR>/scripts/look_tongji.py" transcribe --course-id "<COURSE_ID>" --sub-id "<SUB_ID>"

If only course_id is provided, the CLI can list the latest lectures and let you choose:

python "<SKILL_DIR>/scripts/look_tongji.py" transcribe --course-id "<COURSE_ID>"

Default agent behavior for look-tongji:note

Unless the user explicitly says "不要下载PPT/slide" (or equivalent):

1. Run note command for the same course_id + sub_id (internally does transcript + slide in parallel).
2. After both finish, write notes using both transcript and slide images.
3. If slide download fails but transcript succeeds, still produce notes and mention slide failure briefly.

Default combined command:

python "<SKILL_DIR>/scripts/look_tongji.py" note --course-id "<COURSE_ID>" --sub-id "<SUB_ID>"

If user explicitly requests transcript only:

python "<SKILL_DIR>/scripts/look_tongji.py" note --course-id "<COURSE_ID>" --sub-id "<SUB_ID>" --no-slide
# or:
python "<SKILL_DIR>/scripts/look_tongji.py" transcribe --course-id "<COURSE_ID>" --sub-id "<SUB_ID>"

Artifacts produced by the CLI

The CLI writes to ./tongji-output/ (relative to the current working directory):

• <course_id>_<sub_id>.srt
• <course_id>_<sub_id>.txt
• <course_id>_<sub_id>.json (metadata)
• slide_<course_id>_<sub_id>/ (slide images + index.json)

Important transcript-reading rule:

• For note writing, do not use <course_id>_<sub_id>.json as the main transcript source (JSON ASR payloads are noisy).
• Always prioritize:
  1. <course_id>_<sub_id>.txt (preferred when timestamps are not required),
  2. <course_id>_<sub_id>.srt (use when timeline/timestamp context is needed).

Important slide-reading rule:

• For note writing, do not use slide_<course_id>_<sub_id>/index.json as the main slide timeline source (often noisy).
• Read slide image files directly and parse ordering/time from filenames.
• Filename format example: 0102_t01-32-45_s005565.jpg
  • 0102: slide sequence number
  • t01-32-45: timestamp hh-mm-ss
  • s005565: total seconds from lecture start (1*3600 + 32*60 + 45 = 5565)

Write the Markdown note (by the current agent)

After the CLI finishes, read transcript TXT plus slide metadata/images and write:

• <course_id>_<sub_id>_notes.md in the same tongji-output/ folder.

Important responsibility boundary:

• The CLI only fetches/transcribes/downloads artifacts; it does not generate study-note Markdown content.
• The current AI agent must organize transcript + slides and write the final Markdown notes.

Use the following note prompt and output only Markdown (notes content should be in Simplified Chinese):

You are a professional course TA. Based on the provided ASR transcript and lecture slide snapshots, write detailed study notes in Markdown (notes content in Simplified Chinese).
Requirements:
1) Output notes directly. No polite preface. No "here is the summary" opener.
2) Make the text fluent and logically structured. Fix obvious ASR errors and repetitions, but do not fabricate content not present in transcript/slides.
3) Markdown formatting: only use headings starting from ### (allow ###/####/#####). Do not use # or ##. Use bold/lists/tables when appropriate; avoid overly fragmented bullet-only output.
4) If the lecture mentions assignments/exams/attendance/grouping, put a short "### Course Reminders" section at the very top.
5) Use LaTeX for variables and formulas: inline $...$, block $$...$$. Do not put non-ASCII characters inside LaTeX.
6) Be faithful to transcript/slides and include enough details so that a student can learn from the notes (not just an outline).
7) If transcript and slides conflict, prefer slide text for terminology/spelling and briefly note uncertainty.
Now write the notes from transcript + slides:

Command: look-tongji:slide

Goal: download detected slide snapshots for one lecture.

Run with a lecture URL:

python "<SKILL_DIR>/scripts/look_tongji.py" slide --lecture-url "<LECTURE_URL>"

Run with IDs:

python "<SKILL_DIR>/scripts/look_tongji.py" slide --course-id "<COURSE_ID>" --sub-id "<SUB_ID>"

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