Markit Markdown Converter

作者 reason-machines2384a003145a無授權條款83 個星標收錄於 2026年10月8日更新於 2026年10月8日儲存庫3 個月前更新

Convert files, URLs, and media to markdown using the markit-ai CLI and SDK with pluggable converters and LLM support.

僅含說明Documents & Office

AI 產生的概覽

透過 markit-ai CLI 與 TypeScript SDK，將 PDF、DOCX、圖片、音訊等檔案、網址與媒體轉換為 markdown。

功能: 此技能說明如何使用 markit-ai 命令列工具與 TypeScript/Node.js 函式庫，把多種格式——PDF、Word、PowerPoint、Excel、HTML、EPUB、筆記本、CSV、JSON、YAML、圖片、音訊、ZIP 壓縮檔、原始碼以及網頁連結——轉換為 markdown。內容涵蓋安裝、用於輸出檔案、原始輸出或 JSON 輸出以及標準輸入的 CLI 參數、用於圖片描述與音訊轉錄的 LLM 設定、SDK 用法，以及撰寫或安裝可外掛的轉換器與提供者。產出為 markdown 文字，可寫入檔案或以結構化 JSON 輸出。
適用情境: 當你需要把文件、網頁或媒體轉換為 markdown 以便閱讀、管線傳遞或後續處理時使用。也適用於為圖片或音訊轉換設定 LLM 提供者，或以自訂轉換器外掛擴充 markit。
執行需求: 需要 Node.js 與 markit-ai 套件（npm、bun 或 pnpm）；AI 描述與轉錄需要 OPENAI_API_KEY 或 ANTHROPIC_API_KEY 等 API 金鑰，網址轉換需要網路存取。此技能不附帶指令碼，僅為說明文件。

markit-markdown-converter

Skill by ara.so — Daily 2026 Skills collection.

markit converts almost anything to markdown: PDFs, Word docs, PowerPoint, Excel, HTML, EPUB, Jupyter notebooks, RSS feeds, CSV, JSON, YAML, images (with EXIF + AI description), audio (with metadata + AI transcription), ZIP archives, URLs, Wikipedia pages, and source code files. It works as a CLI tool and as a TypeScript/Node.js library, supports pluggable converters, and integrates with OpenAI, Anthropic, and any OpenAI-compatible LLM API.

Installation

bash

# Global CLInpm install -g markit-ai
# Or as a project dependencynpm install markit-ai# bun add markit-ai# pnpm add markit-ai

# Global CLInpm install -g markit-ai
# Or as a project dependencynpm install markit-ai# bun add markit-ai# pnpm add markit-ai

CLI Quick Reference

bash

# Convert a filemarkit report.pdfmarkit document.docxmarkit slides.pptxmarkit data.xlsxmarkit notebook.ipynb
# Convert a URLmarkit https://example.com/articlemarkit https://en.wikipedia.org/wiki/Markdown
# Convert media (requires LLM API key for AI features)markit photo.jpgmarkit recording.mp3markit diagram.png -p "Describe the architecture and data flow"markit receipt.jpg -p "List all line items with prices as a table"
# Output optionsmarkit report.pdf -o report.md          # Write to filemarkit report.pdf -q                    # Raw markdown only (great for piping)markit report.pdf --json                # Structured JSON output
# Read from stdincat file.pdf | markit -
# Pipe outputmarkit report.pdf | pbcopymarkit data.xlsx -q | some-other-tool
# List supported formatsmarkit formats
# Configurationmarkit init                              # Create .markit/config.jsonmarkit config show                       # Show resolved configmarkit config get llm.modelmarkit config set llm.provider anthropicmarkit config set llm.model claude-haiku-4-5
# Pluginsmarkit plugin install npm:markit-plugin-dwgmarkit plugin install git:github.com/user/markit-plugin-ocrmarkit plugin install ./my-plugin.tsmarkit plugin listmarkit plugin remove dwg
# Agent integrationmarkit onboard                           # Adds usage instructions to CLAUDE.md

# Convert a filemarkit report.pdfmarkit document.docxmarkit slides.pptxmarkit data.xlsxmarkit notebook.ipynb
# Convert a URLmarkit https://example.com/articlemarkit https://en.wikipedia.org/wiki/Markdown
# Convert media (requires LLM API key for AI features)markit photo.jpgmarkit recording.mp3markit diagram.png -p "Describe the architecture and data flow"markit receipt.jpg -p "List all line items with prices as a table"
# Output optionsmarkit report.pdf -o report.md          # Write to filemarkit report.pdf -q                    # Raw markdown only (great for piping)markit report.pdf --json                # Structured JSON output
# Read from stdincat file.pdf | markit -
# Pipe outputmarkit report.pdf | pbcopymarkit data.xlsx -q | some-other-tool
# List supported formatsmarkit formats
# Configurationmarkit init                              # Create .markit/config.jsonmarkit config show                       # Show resolved configmarkit config get llm.modelmarkit config set llm.provider anthropicmarkit config set llm.model claude-haiku-4-5
# Pluginsmarkit plugin install npm:markit-plugin-dwgmarkit plugin install git:github.com/user/markit-plugin-ocrmarkit plugin install ./my-plugin.tsmarkit plugin listmarkit plugin remove dwg
# Agent integrationmarkit onboard                           # Adds usage instructions to CLAUDE.md

AI / LLM Configuration

Images and audio always get free metadata extraction. AI-powered description and transcription requires an API key.

bash

# OpenAI (default)export OPENAI_API_KEY=sk-...markit photo.jpg
# Anthropicexport ANTHROPIC_API_KEY=sk-ant-...markit config set llm.provider anthropicmarkit photo.jpg
# OpenAI-compatible APIs (Ollama, Groq, Together, etc.)markit config set llm.apiBase http://localhost:11434/v1markit config set llm.model llama3.2-visionmarkit photo.jpg

# OpenAI (default)export OPENAI_API_KEY=sk-...markit photo.jpg
# Anthropicexport ANTHROPIC_API_KEY=sk-ant-...markit config set llm.provider anthropicmarkit photo.jpg
# OpenAI-compatible APIs (Ollama, Groq, Together, etc.)markit config set llm.apiBase http://localhost:11434/v1markit config set llm.model llama3.2-visionmarkit photo.jpg

.markit/config.json (created by markit init):

json

{  "llm": {    "provider": "openai",    "apiBase": "https://api.openai.com/v1",    "model": "gpt-4.1-nano",    "transcriptionModel": "gpt-4o-mini-transcribe"  }}

{  "llm": {    "provider": "openai",    "apiBase": "https://api.openai.com/v1",    "model": "gpt-4.1-nano",    "transcriptionModel": "gpt-4o-mini-transcribe"  }}

Environment variables always override config file values. Never store API keys in the config file — use env vars.

SDK Usage

Basic File and URL Conversion

typescript

import { Markit } from "markit-ai";
const markit = new Markit();
// Convert a file by pathconst { markdown } = await markit.convertFile("report.pdf");console.log(markdown);
// Convert a URLconst { markdown: webMd } = await markit.convertUrl("https://example.com/article");
// Convert a Buffer with explicit type hintimport { readFileSync } from "fs";const buffer = readFileSync("document.docx");const { markdown: docMd } = await markit.convert(buffer, { extension: ".docx" });

import { Markit } from "markit-ai";
const markit = new Markit();
// Convert a file by pathconst { markdown } = await markit.convertFile("report.pdf");console.log(markdown);
// Convert a URLconst { markdown: webMd } = await markit.convertUrl("https://example.com/article");
// Convert a Buffer with explicit type hintimport { readFileSync } from "fs";const buffer = readFileSync("document.docx");const { markdown: docMd } = await markit.convert(buffer, { extension: ".docx" });

With OpenAI for Vision + Transcription

typescript

import OpenAI from "openai";import { Markit } from "markit-ai";
const openai = new OpenAI(); // reads OPENAI_API_KEY from env
const markit = new Markit({  describe: async (image: Buffer, mime: string) => {    const res = await openai.chat.completions.create({      model: "gpt-4.1-nano",      messages: [        {          role: "user",          content: [            { type: "text", text: "Describe this image in detail." },            {              type: "image_url",              image_url: {                url: `data:${mime};base64,${image.toString("base64")}`,              },            },          ],        },      ],    });    return res.choices[0].message.content ?? "";  },
  transcribe: async (audio: Buffer, mime: string) => {    const res = await openai.audio.transcriptions.create({      model: "gpt-4o-mini-transcribe",      file: new File([audio], "audio.mp3", { type: mime }),    });    return res.text;  },});
const { markdown } = await markit.convertFile("photo.jpg");

import OpenAI from "openai";import { Markit } from "markit-ai";
const openai = new OpenAI(); // reads OPENAI_API_KEY from env
const markit = new Markit({  describe: async (image: Buffer, mime: string) => {    const res = await openai.chat.completions.create({      model: "gpt-4.1-nano",      messages: [        {          role: "user",          content: [            { type: "text", text: "Describe this image in detail." },            {              type: "image_url",              image_url: {                url: `data:${mime};base64,${image.toString("base64")}`,              },            },          ],        },      ],    });    return res.choices[0].message.content ?? "";  },
  transcribe: async (audio: Buffer, mime: string) => {    const res = await openai.audio.transcriptions.create({      model: "gpt-4o-mini-transcribe",      file: new File([audio], "audio.mp3", { type: mime }),    });    return res.text;  },});
const { markdown } = await markit.convertFile("photo.jpg");

With Anthropic for Vision

typescript

import Anthropic from "@anthropic-ai/sdk";import OpenAI from "openai";import { Markit } from "markit-ai";
const anthropic = new Anthropic(); // reads ANTHROPIC_API_KEY from envconst openai = new OpenAI();       // reads OPENAI_API_KEY from env
// Mix providers: Claude for images, OpenAI Whisper for audioconst markit = new Markit({  describe: async (image: Buffer, mime: string) => {    const res = await anthropic.messages.create({      model: "claude-haiku-4-5",      max_tokens: 1024,      messages: [        {          role: "user",          content: [            {              type: "image",              source: {                type: "base64",                media_type: mime as "image/jpeg" | "image/png" | "image/gif" | "image/webp",                data: image.toString("base64"),              },            },            { type: "text", text: "Describe this image." },          ],        },      ],    });    return (res.content[0] as { text: string }).text;  },
  transcribe: async (audio: Buffer, mime: string) => {    const res = await openai.audio.transcriptions.create({      model: "gpt-4o-mini-transcribe",      file: new File([audio], "audio.mp3", { type: mime }),    });    return res.text;  },});

import Anthropic from "@anthropic-ai/sdk";import OpenAI from "openai";import { Markit } from "markit-ai";
const anthropic = new Anthropic(); // reads ANTHROPIC_API_KEY from envconst openai = new OpenAI();       // reads OPENAI_API_KEY from env
// Mix providers: Claude for images, OpenAI Whisper for audioconst markit = new Markit({  describe: async (image: Buffer, mime: string) => {    const res = await anthropic.messages.create({      model: "claude-haiku-4-5",      max_tokens: 1024,      messages: [        {          role: "user",          content: [            {              type: "image",              source: {                type: "base64",                media_type: mime as "image/jpeg" | "image/png" | "image/gif" | "image/webp",                data: image.toString("base64"),              },            },            { type: "text", text: "Describe this image." },          ],        },      ],    });    return (res.content[0] as { text: string }).text;  },
  transcribe: async (audio: Buffer, mime: string) => {    const res = await openai.audio.transcriptions.create({      model: "gpt-4o-mini-transcribe",      file: new File([audio], "audio.mp3", { type: mime }),    });    return res.text;  },});

Using Built-in Providers via Config

typescript

import { Markit, createLlmFunctions, loadConfig, loadAllPlugins } from "markit-ai";
// Reads .markit/config.json and env vars automaticallyconst config = loadConfig();
// Load any installed pluginsconst plugins = await loadAllPlugins();
// Create instance with built-in providers + pluginsconst markit = new Markit(createLlmFunctions(config), plugins);
const { markdown } = await markit.convertFile("report.pdf");

import { Markit, createLlmFunctions, loadConfig, loadAllPlugins } from "markit-ai";
// Reads .markit/config.json and env vars automaticallyconst config = loadConfig();
// Load any installed pluginsconst plugins = await loadAllPlugins();
// Create instance with built-in providers + pluginsconst markit = new Markit(createLlmFunctions(config), plugins);
const { markdown } = await markit.convertFile("report.pdf");

Writing a Plugin

Plugins let you add new formats or override built-in converters. Plugin converters run before built-ins.

Basic Converter Plugin

typescript

// my-plugin.tsimport type { MarkitPluginAPI } from "markit-ai";
export default function (api: MarkitPluginAPI) {  api.setName("my-format");  api.setVersion("1.0.0");
  api.registerConverter(    {      name: "myformat",      accepts: (info) => [".myf", ".myfmt"].includes(info.extension ?? ""),      convert: async (input: Buffer, info) => {        // info.extension, info.mimeType, info.fileName available        const text = input.toString("utf-8");        const markdown = `# Converted\n\n\`\`\`\n${text}\n\`\`\``;        return { markdown };      },    },    // Optional: declare so it appears in `markit formats`    { name: "My Format", extensions: [".myf", ".myfmt"] },  );}

// my-plugin.tsimport type { MarkitPluginAPI } from "markit-ai";
export default function (api: MarkitPluginAPI) {  api.setName("my-format");  api.setVersion("1.0.0");
  api.registerConverter(    {      name: "myformat",      accepts: (info) => [".myf", ".myfmt"].includes(info.extension ?? ""),      convert: async (input: Buffer, info) => {        // info.extension, info.mimeType, info.fileName available        const text = input.toString("utf-8");        const markdown = `# Converted\n\n\`\`\`\n${text}\n\`\`\``;        return { markdown };      },    },    // Optional: declare so it appears in `markit formats`    { name: "My Format", extensions: [".myf", ".myfmt"] },  );}

Override a Built-in Converter

typescript

// better-pdf-plugin.tsimport type { MarkitPluginAPI } from "markit-ai";
export default function (api: MarkitPluginAPI) {  api.setName("better-pdf");  api.setVersion("1.0.0");
  // Runs before built-in PDF converter, effectively replacing it  api.registerConverter({    name: "pdf",    accepts: (info) => info.extension === ".pdf",    convert: async (input: Buffer, info) => {      // Custom PDF extraction logic      const markdown = `# PDF Content\n\n(extracted with custom logic)`;      return { markdown };    },  });}

// better-pdf-plugin.tsimport type { MarkitPluginAPI } from "markit-ai";
export default function (api: MarkitPluginAPI) {  api.setName("better-pdf");  api.setVersion("1.0.0");
  // Runs before built-in PDF converter, effectively replacing it  api.registerConverter({    name: "pdf",    accepts: (info) => info.extension === ".pdf",    convert: async (input: Buffer, info) => {      // Custom PDF extraction logic      const markdown = `# PDF Content\n\n(extracted with custom logic)`;      return { markdown };    },  });}

Register a Custom LLM Provider

typescript

import type { MarkitPluginAPI } from "markit-ai";
export default function (api: MarkitPluginAPI) {  api.setName("gemini-provider");
  api.registerProvider({    name: "gemini",    envKeys: ["GOOGLE_API_KEY"],    defaultBase: "https://generativelanguage.googleapis.com/v1beta",    defaultModel: "gemini-2.0-flash",    create: (config, prompt) => ({      describe: async (image: Buffer, mime: string) => {        // Call Gemini API here        return "Image description from Gemini";      },    }),  });}

import type { MarkitPluginAPI } from "markit-ai";
export default function (api: MarkitPluginAPI) {  api.setName("gemini-provider");
  api.registerProvider({    name: "gemini",    envKeys: ["GOOGLE_API_KEY"],    defaultBase: "https://generativelanguage.googleapis.com/v1beta",    defaultModel: "gemini-2.0-flash",    create: (config, prompt) => ({      describe: async (image: Buffer, mime: string) => {        // Call Gemini API here        return "Image description from Gemini";      },    }),  });}

Install and Use a Plugin

bash

# Install from filemarkit plugin install ./my-plugin.ts
# Install from npmmarkit plugin install npm:markit-plugin-dwg
# Install from gitmarkit plugin install git:github.com/user/markit-plugin-ocr
# Verifymarkit plugin list
# Removemarkit plugin remove my-format

# Install from filemarkit plugin install ./my-plugin.ts
# Install from npmmarkit plugin install npm:markit-plugin-dwg
# Install from gitmarkit plugin install git:github.com/user/markit-plugin-ocr
# Verifymarkit plugin list
# Removemarkit plugin remove my-format

Common Patterns

Batch Convert a Directory

typescript

import { Markit } from "markit-ai";import { readdirSync, readFileSync, writeFileSync } from "fs";import { extname, basename, join } from "path";
const markit = new Markit();const inputDir = "./docs";const outputDir = "./docs-md";
const files = readdirSync(inputDir);for (const file of files) {  const ext = extname(file);  if (![".pdf", ".docx", ".html"].includes(ext)) continue;
  const buffer = readFileSync(join(inputDir, file));  const { markdown } = await markit.convert(buffer, { extension: ext });  const outName = basename(file, ext) + ".md";  writeFileSync(join(outputDir, outName), markdown);  console.log(`Converted: ${file} → ${outName}`);}

import { Markit } from "markit-ai";import { readdirSync, readFileSync, writeFileSync } from "fs";import { extname, basename, join } from "path";
const markit = new Markit();const inputDir = "./docs";const outputDir = "./docs-md";
const files = readdirSync(inputDir);for (const file of files) {  const ext = extname(file);  if (![".pdf", ".docx", ".html"].includes(ext)) continue;
  const buffer = readFileSync(join(inputDir, file));  const { markdown } = await markit.convert(buffer, { extension: ext });  const outName = basename(file, ext) + ".md";  writeFileSync(join(outputDir, outName), markdown);  console.log(`Converted: ${file} → ${outName}`);}

Convert URL List

typescript

import { Markit } from "markit-ai";
const markit = new Markit();const urls = [  "https://example.com/article-1",  "https://example.com/article-2",  "https://en.wikipedia.org/wiki/TypeScript",];
const results = await Promise.all(  urls.map(async (url) => {    const { markdown } = await markit.convertUrl(url);    return { url, markdown };  }));
for (const { url, markdown } of results) {  console.log(`\n## ${url}\n\n${markdown.slice(0, 200)}...`);}

import { Markit } from "markit-ai";
const markit = new Markit();const urls = [  "https://example.com/article-1",  "https://example.com/article-2",  "https://en.wikipedia.org/wiki/TypeScript",];
const results = await Promise.all(  urls.map(async (url) => {    const { markdown } = await markit.convertUrl(url);    return { url, markdown };  }));
for (const { url, markdown } of results) {  console.log(`\n## ${url}\n\n${markdown.slice(0, 200)}...`);}

CLI in Agent/Automation Scripts

bash

# Structured JSON for programmatic parsingmarkit report.pdf --json
# Raw markdown for piping (no spinner, no extra output)markit report.pdf -q > report.md
# Pipe into another CLI toolmarkit https://example.com/article -q | wc -w
# Process multiple files in a shell loopfor f in docs/*.pdf; do  markit "$f" -o "out/$(basename "$f" .pdf).md"done

# Structured JSON for programmatic parsingmarkit report.pdf --json
# Raw markdown for piping (no spinner, no extra output)markit report.pdf -q > report.md
# Pipe into another CLI toolmarkit https://example.com/article -q | wc -w
# Process multiple files in a shell loopfor f in docs/*.pdf; do  markit "$f" -o "out/$(basename "$f" .pdf).md"done

Supported Formats Reference

Format	Extensions
PDF	`.pdf`
Word	`.docx`
PowerPoint	`.pptx`
Excel	`.xlsx`
HTML	`.html`, `.htm`
EPUB	`.epub`
Jupyter	`.ipynb`
RSS/Atom	`.rss`, `.atom`, `.xml`
CSV/TSV	`.csv`, `.tsv`
JSON	`.json`
YAML	`.yaml`, `.yml`
XML/SVG	`.xml`, `.svg`
Images	`.jpg`, `.png`, `.gif`, `.webp`
Audio	`.mp3`, `.wav`, `.m4a`, `.flac`
ZIP	`.zip`
Code	`.py`, `.ts`, `.go`, `.rs`, and more
Plain text	`.txt`, `.md`, `.rst`, `.log`
URLs	`http://`, `https://`

Run markit formats to see the full live list including any installed plugins.

Troubleshooting

AI description/transcription not working

Ensure the correct env var is set: OPENAI_API_KEY or ANTHROPIC_API_KEY
Run markit config show to verify the resolved provider and model
For custom API bases (Ollama, etc.), confirm the server is running and the model supports vision

Plugin not loading

Run markit plugin list to confirm it's installed
Check the plugin exports a default function matching (api: MarkitPluginAPI) => void
Try reinstalling: markit plugin remove <name> then markit plugin install <source>

PDF returns empty or garbled markdown

The built-in converter uses text extraction (not OCR). Scanned PDFs need an OCR plugin.
Try a custom plugin or pre-process with an OCR tool first.

Stdin (markit -) not working

Pipe content directly: cat file.pdf | markit -
Ensure the file type can be detected from content; use explicit hints if needed.

Config not being read

Config is loaded from .markit/config.json relative to the current working directory
Run markit init to create it, then markit config show to verify

來源與署名

來源：reason-machines/trending-skills位於skills/markit-markdown-converter提交2384a00

授權條款：無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架

Provider	Env Vars	Default Vision Model
`openai`	`OPENAI_API_KEY`, `MARKIT_API_KEY`	`gpt-4.1-nano`
`anthropic`	`ANTHROPIC_API_KEY`, `MARKIT_API_KEY`	`claude-haiku-4-5`

Markit Markdown Converter

markit-markdown-converter

Installation

CLI Quick Reference

AI / LLM Configuration

SDK Usage

Basic File and URL Conversion

With OpenAI for Vision + Transcription

With Anthropic for Vision

Using Built-in Providers via Config

Writing a Plugin

Basic Converter Plugin

Override a Built-in Converter

Register a Custom LLM Provider

Install and Use a Plugin

Common Patterns

Batch Convert a Directory

Convert URL List

CLI in Agent/Automation Scripts

Supported Formats Reference

Troubleshooting

來源與署名

更多來自 reason-machines/trending-skills 的技能

Yourvpndead Vpn Detection

X Mentor Skill Nuwa

Wildworld Dataset

Understand Anything Knowledge Graph

Webphysics Avbd Engine

Ui Ux Pro Max Skill

更多Documents & Office技能

Pdf

View Pdf

Wiki Ado Convert

Process Letter

Teaser

Clean Data Xls