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 phanghonghao/THU-Awesome-Skills --skill notesgit clone --depth 1 https://github.com/phanghonghao/THU-Awesome-SkillsWrote 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/phanghonghao/thu-awesome-skills/notes)<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/notes"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/notes/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/phanghonghao/thu-awesome-skills/notes"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/notes.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 | $0.00065 | $0.03445 |
| Opus 5 | $0.00032 | $0.01723 |
| Sonnet 5 | $0.00013 | $0.00689 |
| Haiku 4.5 | $0.00006 | $0.00345 |
Grade A, and why
notes 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 9d 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notes Skill
Transform Markdown notes with proper image naming - without changing the original content.
Overview
This skill helps you:
- Rename and organize images - rename based on content, move to
/sourcesdirectory - Format the layout & add headings (spacing, heading markers, lists) - Add ## ### markers for section titles
- Dual-column layout (OPTIONAL) - Add HTML/CSS flexbox for compact PDF output (left fills first, then right)
- Generate HTML (OPTIONAL) - only when:
- The markdown contains
.gifanimated images - The markdown contains video references
- User explicitly requests HTML output
- The markdown contains
- Recover broken references (automatic) - when images can't be found, match by context to available images in
sources/
Important: Content Preservation Rule
DO NOT change, rewrite, or add to the original content. Only:
- Fix formatting (spacing, indentation)
- Add heading markers (# ## ###) to existing section titles
- Fix list formatting
- Fix table alignment
DO NOT:
- Rewrite sentences
- Add new sections or content that wasn't there
- Summarize or paraphrase
- Add "课堂笔记" or placeholder sections that weren't there
Heading Markers - ALLOWED:
- "概述：" → "## 概述"
- "3.1.2 塑形成形方法" → "## 3.1.2 塑形成形方法"
- "第三章" → "# 第三章"
Workflow
Step 1: Read the Markdown File
Read the target Markdown file to understand:
- Current structure and formatting
- Image references (look for
patterns) - Original content that must be preserved
Step 2: Rename Images Based on Alt Text OR Section Title
For each image reference  in the Markdown:
Priority 1: Use meaningful alt text
If the alt text is descriptive (not alt-text, image, 图片, etc.):
- Extract the alt text from the image reference
- Generate a new filename using the alt text
- Copy the image to
/sourceswith new name (create directory if not exists) - Delete the original unnamed image file (to avoid duplication)
- Update the Markdown reference to
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.
- 9d ago First seen · 380 lines · 65 tokens per session scan A ca88f1702fbe
notes is a skill published in the GitHub repository phanghonghao/THU-Awesome-Skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 3,445 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.