Markit

What it does

When your agent uses it

• You need to extract content from any document format
• Tasks that involve Word documents
• Tasks that involve PowerPoint presentations

Example prompts

• “/markit”

Requirements

• Python 3
• Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit 4197c76. It shows what the files ask for, not the result of running them.

• Tool permissions

  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.

• Runs code

  Ships script files (Python, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • npx

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • github.com
  • en.wikipedia.org
  • gist.github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Markit loads about 299 tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 15 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~51

When it runs · the whole SKILL.md, loaded when a task matches

~299

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.

Safety

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.

SKILL.md

The full file from shift-labs-ai/markit at commit 4197c76, republished under its MIT licence (© shift-labs-ai). 15 words, ~299 tokens.

name

markit

description

Convert files and URLs to Markdown. Supports PDF, DOCX, PPTX, XLSX, HTML, EPUB, CSV, JSON, GitHub URLs, images, audio, ZIP, and more. Use when you need to extract content from any document format.

# Convert a file
npx @shiftlabs/markit report.pdf -q

# Convert a URL
npx @shiftlabs/markit https://en.wikipedia.org/wiki/Markdown -q

# GitHub URLs (repos, files, gists, issues, PRs)
npx @shiftlabs/markit https://github.com/owner/repo -q
npx @shiftlabs/markit https://github.com/owner/repo/issues/42 -q
npx @shiftlabs/markit https://gist.github.com/user/id -q

# Write to file
npx @shiftlabs/markit document.docx -q -o output.md

# See all options
npx @shiftlabs/markit --help

# See supported formats
npx @shiftlabs/markit formats

import { Markit } from "@shiftlabs/markit";

const markit = new Markit();
const { markdown } = await markit.convertFile("report.pdf");
const { markdown } = await markit.convertUrl("https://example.com");
const { markdown } = await markit.convert(buffer, { extension: ".docx" });

© shift-labs-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 233 other files in the repository root of shift-labs-ai/markit.

• SKILL.md
• .github/workflows/ci.yml
• .github/workflows/release.yml
• .gitignore
• AGENTS.md
• LICENSE
• README.md
• benchmark/README.md
• benchmark/bench.py
• benchmark/generate_shitty_pdf_bench_anchors.py
• benchmark/judge_office.py
• benchmark/media/non-ocr-field-plate.png
• benchmark/media/non-ocr-field-plate@2x.png
• benchmark/media/shitty-pdf-bench-plate.png
• benchmark/media/shitty-pdf-bench-plate@2x.png
• benchmark/media/speed-plate.png
• benchmark/media/speed-plate@2x.png
• … and 217 more

Open the folder on GitHubat commit 4197c76