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 agentmods add skills/webkong/skill-quality-check/bad-skill-examplenpx skills add webkong/skill-quality-check --skill bad-skill-examplegit clone --depth 1 https://github.com/webkong/skill-quality-checkWrote 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/webkong/skill-quality-check/bad-skill-example)<a href="https://agentmods.dev/skills/webkong/skill-quality-check/bad-skill-example"><img src="https://agentmods.dev/badge/skills/webkong/skill-quality-check/bad-skill-example.svg" alt="Measured on agentmods" 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 | $0.00144 | $0.01237 |
| Opus 5 | $0.00072 | $0.00619 |
| Sonnet 5 | $0.00029 | $0.00247 |
| Haiku 4.5 | $0.00014 | $0.00124 |
Grade A, and why
pdf-processing-super-ultimate-edition 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 3d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Processing Super Ultimate Edition v1.2.3
This skill helps with PDF processing tasks. It is made by Some Developer.
Introduction
Claude is an advanced AI assistant created by Anthropic that can help with many tasks including PDF processing. This skill is designed to help Claude help users with PDF tasks. This skill contains detailed instructions for PDF processing.
How to Use This Skill
To use this skill, simply mention PDF or document in your message. The skill will activate and provide guidance. Note that Claude is smart and capable, but this skill provides additional context to help Claude help you better.
Detailed Instructions
Creating PDFs
When creating a PDF, first understand what a PDF is. PDF stands for Portable Document Format and was developed by Adobe. To create a PDF, follow these steps:
Step 1: Understand the document requirements Step 2: Create the content (Claude can help with this) Step 3: Format the content appropriately Step 4: Convert to PDF format Step 5: Review the PDF for errors Step 6: Save the PDF with an appropriate filename
Please note that Claude is a powerful AI and can assist with all of these steps.
Editing PDFs
PDF editing is more complex than creating PDFs. A PDF is a fixed-layout document format, which means content positions are absolute. When editing a PDF, consider the following:
Understanding PDF structure: A PDF consists of objects, pages, and content streams. Objects include text, images, fonts, and graphics. Pages contain these objects. Content streams describe how to render the page.
Text editing in PDFs: Text in PDFs is stored as character codes mapped to glyphs. This means text editing requires understanding the font encoding.
Image handling: Images in PDFs can be compressed using various methods including JPEG, JPEG2000, CCITT, and Flate.
Font considerations: PDFs support many font types including TrueType, OpenType, Type1, and Type3. Font handling is complex.
Merging PDFs
To merge PDFs, you need to combine multiple PDF files into one. Here is the detailed process:
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.
- 3d ago First seen · 153 lines · 144 tokens per session scan A 0db9ef2c2585
pdf-processing-super-ultimate-edition is a skill published in the GitHub repository webkong/skill-quality-check (2 stars, last pushed 5mo ago), licensed MIT. It adds 144 tokens to every session and 1,237 once invoked, about $0.0007 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
nano-pdf
CLI wrapper for nano-pdf binary to edit PDF files. Provides page manipulation capabilities including extraction, rotation, and reordering.
doc-converter
Universal document format converter - DOCX, PDF, Markdown, HTML, TXT.
pdftomd
Convert PDF and office documents (DOCX, PPTX, XLSX, HTML) to Markdown by automatically choosing the best tool among Pandoc, Marker, and MarkItDown based on layout complexity, math/equations, and file format strengths.
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.
paddleocr-doc-parsing
Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表…
paper-reader
Use when user asks to "read paper", "analyze paper", "summarize paper", "读论文", "分析文献", "帮我看一下这篇paper", "论文笔记", or provides a PDF file that appears to be an academic paper. Specialized for CV/DL papers. Also supports Zotero integration: "读一下这篇论文 ...", "快速看一下这篇论文 ...", "批判性分析这篇论文 ...", "读一下 Zotero 里的 XXX", "批量读一下 Zotero…