Documents
zhongkaifu/TensorSharp
Read and write real documents on the device - PDF, XLSX, DOCX, PPTX and CSV.
A skill your agent uses whenever the user wants to extract text or data from documents using Toxy (the .NET text extraction library).
$ npx skills add nissl-lab/toxy --skill toxy -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nissl-lab/toxy toxy --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nissl-lab/toxy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/toxy .claude/skills/toxy && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "toxy" agent skill from https://github.com/nissl-lab/toxy/tree/master/.claude/skills/toxy into .claude/skills/toxy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "toxy", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/nissl-lab/toxy/tree/master/.claude/skills/toxyType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add nissl-lab/toxy --skill toxy -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nissl-lab/toxy toxy --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nissl-lab/toxy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/toxy .agents/skills/toxy && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "toxy" agent skill from https://github.com/nissl-lab/toxy/tree/master/.claude/skills/toxy into .agents/skills/toxy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "toxy", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nissl-lab/toxy --skill toxy -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nissl-lab/toxy toxy --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nissl-lab/toxy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/toxy .cursor/skills/toxy && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "toxy" agent skill from https://github.com/nissl-lab/toxy/tree/master/.claude/skills/toxy into .cursor/skills/toxy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "toxy", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/nissl-lab/toxy.git --path .claude/skills/toxy--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nissl-lab/toxy --skill toxy -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nissl-lab/toxy toxy --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nissl-lab/toxy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/toxy .gemini/skills/toxy && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "toxy" agent skill from https://github.com/nissl-lab/toxy/tree/master/.claude/skills/toxy into .gemini/skills/toxy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "toxy", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install nissl-lab/toxy toxyInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add nissl-lab/toxy --skill toxy -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nissl-lab/toxy.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/toxy .github/skills/toxy && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "toxy" agent skill from https://github.com/nissl-lab/toxy/tree/master/.claude/skills/toxy into .github/skills/toxy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "toxy", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nissl-lab/toxy --skill toxy -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nissl-lab/toxy toxy --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nissl-lab/toxy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/toxy .opencode/skills/toxy && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "toxy" agent skill from https://github.com/nissl-lab/toxy/tree/master/.claude/skills/toxy into .opencode/skills/toxy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "toxy", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
toxyA skill your agent uses whenever the user wants to extract text or data from documents using Toxy (the .NET text extraction library).
Toxy is an agent skill from nissl-lab/toxy. Use this skill whenever the user wants to extract text or data from documents using Toxy (the .NET text extraction library). Trigger when the user mentions reading, parsing, or extracting content from files like docx, xlsx, xls, pdf, csv, txt, epub, html, eml, vcf using C or .NET. Also trigger when the user asks about Toxy NuGet package, ToxyDocument, ToxySpreadsheet, ToxyEmail, stream parsing, or any Toxy API usage. Use this skill for any Toxy 2.6 code generation, migration from older Toxy versions, or…
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/api.md`).
It sits in Documents & Office, covering Excel spreadsheets, Word documents and CSV and tabular files. It works with Microsoft Excel, Microsoft Word, .NET and C#. The repository describes itself as: .net text extraction & export framework. The licence is Apache-2.0.
Read from SKILL.md and the folder at commit 99ca266. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
dotnetFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Toxy loads about 1.7k tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 136 tokens; SKILL.md has 356 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from nissl-lab/toxy at commit 99ca266, republished under its Apache-2.0 licence (© nissl-lab). 356 words, ~1,662 tokens.
.claude/skills/toxy/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Toxy is a .NET data/text extraction framework (similar to Apache Tika for Java). It supports cross-platform text and data extraction from many popular file formats. Always use Toxy 2.6.0 (NuGet package Toxy, targeting netstandard2.0 or netstandard2.1).
.NET Standard 2.1 support (in addition to 2.0)ParserContext now accepts Stream directly)IDocumentParser)StreamReader references (cleaner API)Toxy namespace<!-- .csproj -->
<PackageReference Include="Toxy" Version="2.6.0" />Or via CLI:
dotnet add package Toxy --version 2.6.0The entry point for all parsing. Accepts either a file path or a Stream (new in 2.6):
// From file path
var context = new ParserContext("path/to/file.docx");
// From stream (new in 2.6)
using var stream = File.OpenRead("path/to/file.docx");
var context = new ParserContext(stream, "docx"); // must supply format hintUse ParserFactory to auto-detect format and return the correct parser:
var parser = ParserFactory.CreateDocument(context); // for document types
var parser = ParserFactory.CreateSpreadsheet(context); // for spreadsheet types
var parser = ParserFactory.CreateEmail(context); // for email/contact types| Object | Description | Formats |
|---|---|---|
ToxyDocument | Paragraphs + metadata | docx, pdf, txt, epub, html, rtf, odt |
ToxySpreadsheet | Rows/cells per sheet | xlsx, xls, csv, ods |
ToxyEmail | Email fields | eml, msg |
ToxyBusinessCard | Contact fields | vcf |
ToxyDom | DOM tree | html, xml |
ToxyMetadata | Key/value metadata | any file |
using Toxy;
var context = new ParserContext("report.docx");
var parser = ParserFactory.CreateDocument(context);
ToxyDocument doc = parser.Parse();
foreach (var paragraph in doc.Paragraphs)
{
Console.WriteLine(paragraph.Text);
}using Toxy;
var context = new ParserContext("data.xlsx");
var parser = ParserFactory.CreateSpreadsheet(context);
ToxySpreadsheet sheet = parser.Parse();
foreach (var table in sheet.Tables)
{
Console.WriteLine($"Sheet: {table.Name}");
foreach (var row in table.Rows)
{
foreach (var cell in row.Cells)
{
Console.Write($"{cell.Value}\t");
}
Console.WriteLine();
}
}using Toxy;
// Works with any stream source (MemoryStream, HttpResponseStream, etc.)
using var stream = File.OpenRead("document.pdf");
var context = new ParserContext(stream, "pdf");
var parser = ParserFactory.CreateDocument(context);
ToxyDocument doc = parser.Parse();
Console.WriteLine(doc.Paragraphs[0].Text);using Toxy;
var context = new ParserContext("file.pdf");
var parser = ParserFactory.CreateDocument(context);
ToxyDocument doc = parser.Parse();
foreach (var para in doc.Paragraphs)
Console.WriteLine(para.Text);using Toxy;
var context = new ParserContext("book.epub");
var parser = ParserFactory.CreateDocument(context);
ToxyDocument doc = parser.Parse();
foreach (var para in doc.Paragraphs)
Console.WriteLine(para.Text);using Toxy;
var context = new ParserContext("message.eml");
var parser = ParserFactory.CreateEmail(context);
ToxyEmail email = parser.Parse();
Console.WriteLine($"From: {email.From}");
Console.WriteLine($"Subject: {email.Subject}");
Console.WriteLine($"Body: {email.Body}");using Toxy;
var context = new ParserContext("contact.vcf");
var parser = ParserFactory.CreateEmail(context); // VCF uses email parser factory
ToxyBusinessCard card = (ToxyBusinessCard)parser.Parse();
Console.WriteLine(card.FullName);
Console.WriteLine(card.Email);using Toxy;
var context = new ParserContext("file.pdf");
var parser = ParserFactory.CreateMetadata(context);
ToxyMetadata meta = parser.Parse();
foreach (var key in meta.Keys)
Console.WriteLine($"{key}: {meta[key]}");using Toxy;
var context = new ParserContext("page.html");
var parser = ParserFactory.CreateDom(context);
ToxyDom dom = parser.Parse();
// Access DOM nodes
Console.WriteLine(dom.Root.InnerText);| Format | Extension(s) | Parser Type |
|---|---|---|
| Word (Open XML) | .docx | Document |
| Word (Legacy) | .doc | Document |
.pdf | Document | |
| Plain Text | .txt | Document |
| Rich Text | .rtf | Document |
| EPUB | .epub | Document (new in 2.6) |
| HTML | .html, .htm | Document / Dom |
| OpenDocument Text | .odt | Document |
| Excel (Open XML) | .xlsx | Spreadsheet |
| Excel (Legacy) | .xls | Spreadsheet |
| CSV | .csv | Spreadsheet |
| OpenDocument Sheet | .ods | Spreadsheet |
.eml, .msg | ||
| Business Card | .vcf | Email (returns ToxyBusinessCard) |
| Any | * | Metadata |
"pdf", "docx").NotSupportedException.For deeper reference on specific parsers and the class hierarchy, see references/api.md.
© nissl-lab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in .claude/skills/toxy of nissl-lab/toxy.
Open the folder on GitHubat commit 99ca266
Toxy next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Toxy this skillnissl-lab/toxy | 463 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Documentszhongkaifu/TensorSharp | 559 | — | ~4.2k | Automated safety check: Pass | BSD-3-Clause | |
| Markdown Exporterbowenliang123/markdown-exporter | 272 | 1 repos | ~5.3k | Automated safety check: Pass | Apache-2.0 | |
| Office ArtifactsPrismer-AI/PrismerCloud | 1.6k | — | ~2.6k | Automated safety check: Pass | MIT | |
| MinerU Document Readeropendatalab/MinerU | 81k | — | ~9.4k | Automated safety check: Warn | Custom licence | |
| File ReadingWide-Moat/open-computer-use | 126 | 1 repos | ~3.1k | Automated safety check: Pass | Proprietary |
zhongkaifu/TensorSharp
Read and write real documents on the device - PDF, XLSX, DOCX, PPTX and CSV.
bowenliang123/markdown-exporter
Convert Markdown text to DOCX, PPTX, XLSX, PDF, PNG, SVG, HTML, IPYNB, MD, CSV, JSON, JSONL, XML files, and extract code blocks in Markdown to Python, Bash,JS and etc files.
Prismer-AI/PrismerCloud
Generate real DOCX, PPTX, XLSX, PDF, CSV files using python-docx / python-pptx / openpyxl / reportlab by writing them into the dispatch artifacts dir, then explicitly deliver each one with cloud…
opendatalab/MinerU
Reads, OCRs, searches and cites local documents through the mineru CLI, covering PDF, images, Office files, EPUB, HTML and CSV.
Wide-Moat/open-computer-use
A skill your agent uses when a file has been uploaded but its content is NOT in your context — only its path at /mnt/user-data/uploads/ is listed in an uploadedfiles block.
Light0305/Light-skills
Light 多格式文件深度理解常驻技能:强大地读 Word / PDF / PPTX / Excel / CSV / 图片 / 视频 / 代码 / 压缩包,不只提取文字,而是理解结构 / 图表 / 数据 / 格式要求 / 隐含意图,产结构化"理解笔记"五面 (结构逻辑·关键内容·格式约束·视觉风格·可复用)并映射到下游技能动作(这个文件→接下来能做什么)。
Works with
Categories
A skill your agent uses whenever the user wants to extract text or data from documents using Toxy (the .NET text extraction library). Toxy is an agent skill from nissl-lab/toxy.NET text extraction library).
Toxy fits situations like: the user wants to extract text; data from documents using Toxy (the .NET text extraction library); the user mentions reading; extracting content from files like docx.
Run `npx skills add nissl-lab/toxy --skill toxy -a claude-code`. Or copy the skill folder (.claude/skills/toxy in nissl-lab/toxy) into .claude/skills/toxy in your project. Claude Code loads it when a task matches its description.
Run `npx skills add nissl-lab/toxy --skill toxy -a codex`. Or copy the skill folder (.claude/skills/toxy in nissl-lab/toxy) into .agents/skills/toxy in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nissl-lab/toxy --skill toxy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/toxy, .gemini/skills/toxy, .github/skills/toxy and .opencode/skills/toxy in your project.
Going by SKILL.md and its folder, Toxy needs the command-line tools its instructions call (dotnet).
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Toxy is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.7k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.4k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Toxy: Documents (zhongkaifu/TensorSharp, 559 stars), Markdown Exporter (bowenliang123/markdown-exporter, 272 stars), Office Artifacts (Prismer-AI/PrismerCloud, 1.6k stars) and MinerU Document Reader (opendatalab/MinerU, 81k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
nissl-lab (a GitHub organization) maintains it in nissl-lab/toxy, which has 463 GitHub stars. The repository was last updated on June 19, 2026.
Source: nissl-lab/toxy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.