Markdrop

What it does

When your agent uses it

• Tasks that involve PDF
• Tasks that involve Document parsing
• Tasks that involve Markdown

Example prompts

• “/markdrop”

Requirements

• Python 3
• A credential in GEMINI_API_KEY
• A credential in OPENAI_API_KEY

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Capabilities
2. 2API Keys Setup
3. 3Python API Integration
4. 4CLI Execution Best Practices
5. 5Typical Model Fallbacks & Suggestions

What it can do on your machine

Read from SKILL.md and the folder at commit 2a1c475. 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

  No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and python).

  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:

  • url.to

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

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • GEMINI_API_KEY
  • OPENAI_API_KEY
  • ANTHROPIC_API_KEY
  • GROQ_API_KEY
  • OPENROUTER_API_KEY
  • LITELLM_API_KEY

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

Context cost

Markdrop loads about 1.4k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 367 words of instructions outside code blocks.

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

~43

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

~1.4k

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

• NoteMentions a .env fileSKILL.md:21

  API keys must be available in the root `.env` file or environment variables.

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 shoryasethia/markdrop at commit 2a1c475, republished under its GPL-3.0 licence (© shoryasethia). 367 words, ~1,375 tokens.

name

markdrop

description

Professional AI skill and usage instructions for the Markdrop package, a Python tool for converting PDFs to Markdown/HTML with AI-powered image/table descriptions.

markdrop setup gemini     # -> GEMINI_API_KEY
markdrop setup openai     # -> OPENAI_API_KEY
markdrop setup anthropic  # -> ANTHROPIC_API_KEY
markdrop setup groq       # -> GROQ_API_KEY
markdrop setup openrouter # -> OPENROUTER_API_KEY
markdrop setup litellm    # -> LITELLM_API_KEY

from markdrop import markdrop, MarkDropConfig, add_downloadable_tables
from pathlib import Path
import logging

# Configuration block
config = MarkDropConfig(
    image_resolution_scale=2.0,
    download_button_color="#444444",
    log_level=logging.INFO,
    log_dir="logs",
    excel_dir="markdrop-excel-tables",
)

# 1. Convert PDF to base HTML (and markdown locally). URL supported here too: "https://url.to/pdf"
html_path = markdrop("path/to/document.pdf", "output_directory", config)

# 2. Enrich HTML to allow downloading tables as Excel sheets
enhanced_html_path = add_downloadable_tables(html_path, config)

from markdrop import process_markdown, ProcessorConfig, AIProvider

config = ProcessorConfig(
    input_path="output_directory/document.md",
    output_dir="output_directory",
    ai_provider=AIProvider.GEMINI,  # Available: GEMINI, OPENAI, ANTHROPIC, GROQ, OPENROUTER, LITELLM
    # Target configurations
    remove_images=False,
    remove_tables=False,
    table_descriptions=True,
    image_descriptions=True,
    # Provider-Specific overrides (Optional)
    # Allows granular decoupling of vision parsing vs table text-parsing
    model_name_override="gemini-2.0-flash",  # Primary vision analysis model
    text_model_name_override="gemini-2.0-flash",  # Lean text-only model for generic parsing
)

# Executes AI processing and saves the enriched document
output_path = process_markdown(config)

from markdrop import generate_descriptions

generate_descriptions(
    input_path="images_folder/",
    output_dir="descriptions_output/",
    prompt="Analyze this image and describe all textual and structural elements.",
    llm_client=["gemini", "openai"],
)

© shoryasethia, GPL-3.0. 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 51 other files in the repository root of shoryasethia/markdrop.

• SKILL.md
• .agent/skills
• .gitignore
• CHANGELOG.md
• CODE_OF_CONDUCT.md
• CONTRIBUTING.md
• LICENSE
• OLD-DOCUMENTATION.md
• README.md
• dist/markdrop-4.0.1-py3-none-any.whl
• dist/markdrop-4.0.1.tar.gz
• docs/api_reference.md
• docs/architecture.md
• docs/benchmarking.md
• docs/cli_reference.md
• docs/cpu-guide.md
• docs/getting_started.md
• docs/providers.md
• … and 34 more

Open the folder on GitHubat commit 2a1c475