Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add WALKERKILLER/Look-Tongji-Notes --skill transgit clone --depth 1 https://github.com/WALKERKILLER/Look-Tongji-NotesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/walkerkiller/look-tongji-notes/trans)<a href="https://agentmods.dev/skills/walkerkiller/look-tongji-notes/trans"><img src="https://agentmods.dev/badge/skills/walkerkiller/look-tongji-notes/trans/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/walkerkiller/look-tongji-notes/trans"><img src="https://agentmods.dev/badge/skills/walkerkiller/look-tongji-notes/trans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.00872 |
| Opus 5.5 | $0.00010 | $0.00349 |
| Sonnet 5.5 | $0.00005 | $0.00174 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
trans scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transcribe
Transcribe one lecture video from look.tongji.edu.cn and optionally download slide snapshots.
When to Use
- User says
/transor "transcribe this lecture". - User provides a lecture URL or course_id + sub_id.
Workflow
- Resolve lecture with URL or IDs:
python "<SKILL_DIR>/../../scripts/look_tongji.py" transcribe --lecture-url "<LECTURE_URL>"
python "<SKILL_DIR>/../../scripts/look_tongji.py" transcribe --course-id "<ID>" --sub-id "<ID>"
- Transcribe + download slides in one run:
python "<SKILL_DIR>/../../scripts/look_tongji.py" transcribe --course-id "<ID>" --sub-id "<ID>" --slide
- The CLI prints real-time progress. Stdout contains result paths.
Non-Interactive / Batch Usage
When running from an automated pipeline, avoid input() prompts with these flags:
| Flag | Description |
|---|---|
--sub-id |
Specify lecture sub_id directly (skips interactive lecture picker) |
--course-id |
Specify course ID directly (skips interactive course selection) |
--slide |
Download slides after transcription |
--concurrency N |
Slide download concurrency (default 4) |
--retries N |
Slide download retries (default 3) |
manifest.json — Required for Wiki Build
transcribe does NOT automatically create manifest.json. After transcription, you MUST create it manually so the wiki indexer can find this lecture.
Create manifest.json in the session's 原始数据/ directory with this structure:
{
"course_id": "COURSE_ID",
"sub_id": "SUB_ID",
"course_title": "课程名称(真实中文名)",
"session_title": "YYYY-M-D 第X节",
"base_name": "COURSE_ID_SUB_ID",
"artifacts": {
"srt": "F:\\workspace\\raw\\课程名称\\YYYY-M-D 第X节\\原始数据\\COURSE_ID_SUB_ID.srt",
"txt": "F:\\workspace\\raw\\课程名称\\...\\COURSE_ID_SUB_ID.txt",
"notes": "",
"timeline": "",
"slides": "F:\\workspace\\raw\\课程名称\\...\\slides\\index.json"
},
"duration_seconds": 5580
}
Critical path rules:
- Use absolute paths for all artifact paths (relative paths break on Windows)
duration_seconds: must be ≥ 3600 (1 hour); if < 3600, the lecture is marked不合格 and wiki shows it as 缺失- If no slides were downloaded, leave
slidesfield empty ("") - Fields
notesandtimelineare filled by/notecommand later
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 96 lines · 24 tokens per session scan A e64c28c5f5b2
trans is a skill published in the GitHub repository WALKERKILLER/Look-Tongji-Notes (51 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 872 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ai-patient-education-readability-review
A patient-education material review assistant that summarizes supplied healthcare information and checks what needs attention.
pptx-import
A method for adding an uploaded PowerPoint presentation to an existing classroom as extra pages while keeping the slides' original layout. PowerPoint is Microsoft's presentation file format.
moai-workflow-jit-docs
Enhanced Just-In-Time document loading system that discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation on demand.
explain-this
Explain any digital artifact — a paper, PDF, article, code diff, or codebase — so the person actually understands it, not just skims it. Explanations are shaped by a persistent learner profile, gated by comprehension quizzes, and feed a spaced-repetition review loop. USE WHEN: explain this, explain this paper / PDF /…
exam-study-guide
A study-guide builder for a completed exam chapter that has not yet passed its required checks. It creates a structured teaching checklist and, in full mode, a self-contained HTML and printable PDF guide with readable formulas, visible images, explanations, examples, and answers.
slides.convert_to_typst
Convert markdown slides to Typst-compatible format via pandoc.