list — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited list (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Discover and select courses from Tongji Look.
/list or "show my courses" or "find a course".python "<SKILL_DIR>/../../scripts/look_tongji.py" listpython "<SKILL_DIR>/../../scripts/look_tongji.py" list --query "<KEYWORD>"python "<SKILL_DIR>/../../scripts/look_tongji.py" list --all| Flag | Description |
|---|---|
--all | List all courses (slower but more complete) |
--limit LIMIT | Number of courses to show (0 = all) |
--query QUERY | Filter by keyword in title/teacher (server-side, case-insensitive) |
--choose CHOOSE | Auto-select course # (1-based) for non-interactive use |
--force-login | Ignore cached JWT and login again |
--query is a server-side keyword search and may not match Chinese course names reliably. If --query "课程名关键词" returns empty:
Workaround: Use --all to fetch all courses, then filter locally:
python "<SKILL_DIR>/../../scripts/look_tongji.py" list --all 2>&1 | grep "课程名关键词"When --choose is set, the CLI auto-selects the course and saves its ID — no input() prompt. Combine with --all for scripted workflows:
python "<SKILL_DIR>/../../scripts/look_tongji.py" list --all --choose 1When run without --choose, the CLI prints a numbered list of courses and prompts the user to select one. The selected course's ID is then available for use with /trans, /note, and other commands.
<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/).
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.