Wiki
Transcribing Lessons from Tongji Look Platform to Notes with Agent Skill.
npx -y skills add WALKERKILLER/Look-Tongji-Notes --skill wikiAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Build and serve the static course knowledge base locally. Rebuilds from workspace data and starts an HTTP server on port 8765.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
1.8 KB, as published. Nobody here has run it
Wiki
Build and locally serve the course knowledge base.
When to Use
- User says
/wikior "open the course wiki" or "serve the wiki". - After writing notes, to preview the generated site.
Workflow
- Serve (build + start HTTP server):
python "<SKILL_DIR>/../../scripts/look_tongji.py" serve --port 8765
- Build only (no server):
python "<SKILL_DIR>/../../scripts/look_tongji.py" build
Page Structure
Each session page follows this layout (top to bottom):
- Lecture Video (top) — embedded player area when video metadata is available, or a direct video link
- Resources (middle) — supplementary materials, slide download links, and transcript download links
- Note (bottom) — pure Markdown study content without task-oriented meta-descriptions
Duration Check
- Sessions with
duration_seconds < 3600are flagged with a warning indicator in the wiki UI. - The agent should suggest re-transcription for short sessions.
Note Cleanliness
- Notes must be pure knowledge content without task-oriented meta-descriptions.
- See
/noteskill for the full list of forbidden phrases.
Validation
- The generated site uses the vendored llm-wiki frontend.
- UI chrome (language toggle, navigation) is handled by the frontend; content is from workspace data.
Where <SKILL_DIR> Points
<SKILL_DIR> is the directory containing this SKILL.md. Shared scripts (look_tongji.py, timeline_tools.py, tongji_backend/) and references live two levels up in the repository root (<SKILL_DIR>/../../scripts/ and <SKILL_DIR>/../../references/).