Setup
Configure Tongji Look credentials, check system dependencies (Python, Node.js, ffmpeg, vision-support, XeLaTeX), and set up the persistent course-wiki workspace.From its SKILL.md
npx -y skills add WALKERKILLER/Look-Tongji-Notes --skill setupAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- runs commandsInstructs the agent to run 3 commands, including `python "<SKILL_DIR>/../../scripts/look_tongji.py" setup` and 2 more.
What its file declares
Copied from the file, not written here
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
1.9 KB, 427 tokens by cl100k_base, as published. Nobody here has run it
Setup
Configure credentials, dependencies, and workspace for Look Tongji Notes.
When to Use
- User says
/setupor asks to configure the skill. - First-time setup before transcribing lectures.
- User wants to change or migrate the course knowledge-base path.
Workflow
- Run setup:
python "<SKILL_DIR>/../../scripts/look_tongji.py" setup
- Non-interactive workspace options:
python "<SKILL_DIR>/../../scripts/look_tongji.py" setup \
--workspace-root "<COURSE_WIKI_ROOT>" \
--owner-name "<OWNER_NAME>" \
--site-name "<OWNER_NAME>的课程知识库"
-
The CLI checks: Python deps (requests, playwright, python-dotenv, markdown, markitdown), ffmpeg, Node.js, vision-support config, and optionally XeLaTeX.
-
Vision Support setup: If
vision-support/config.jsondoes not exist, the CLI prints the init command. The embedded vision-support is at<SKILL_DIR>/../../vision-support/. Help the user configure a vision provider (OpenAI, Google, Anthropic, deepseek, dashscope, zhipuai, ollama, or custom). -
Verify vision-support: After configuration, test with:
node "<SKILL_DIR>/../../vision-support/scripts/vision.mjs" "<SKILL_DIR>/../../komari.jpg"The agent should correctly identify image content (should mention "red-haired girl" or equivalent).
-
Never ask for passwords in chat. Use interactive terminal input or environment variables.
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/).
What ships with it: 1 file
254 B alongside SKILL.md
- manifest.yaml254 B
Gives 1 of the 12 instructions most project setup skills give in 427 tokens
Counted across 1,553 of the 3,091 authors here whose files we hold, read 2026-09-06
- Write the configuration filein 36 of 1553
- Create the directory structurein 35 of 1553, across 33 files
- Verify the setupin 31 of 1553, across 28 files
- Run the setup scripthere, and in 30 of 1553, across 29 files
- Pre-determine the required sample sizein 29 of 1553, across 12 files
- Check if the configuration already existsin 29 of 1553
- Document every testin 26 of 1553, across 10 files
- Start with a hypothesisin 26 of 1553, across 11 files
- Ask one question at a timein 22 of 1553
- Test a single variable per testin 21 of 1553, across 9 files
- Read product marketing context before asking questionsin 19 of 1553, across 8 files
- Do not peek and stop earlyin 18 of 1553, across 7 files
Said here and by no other author read
- Configure a vision provider
- Test vision support
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.