File Download Agent Skill

| Download files from websites, save PDFs, and read downloaded content. fetch a file from a URL, grab a report, download and read a PDF, or save page content as a file.

2k tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

237

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/billy-enrizky/openbrowser-ai --skill file-download

The instruction itself

13 sections, as written by the author

File Download

Download files from websites using the browser's authenticated session. Handles PDFs, CSVs, images, and any downloadable content. Preserves cookies and login sessions for authenticated downloads.

All code runs via openbrowser-ai -c. The daemon starts automatically and persists variables across calls. All browser functions are async -- use await.

The CLI daemon also persists cookies and login state in ~/.config/openbrowser/profiles/daemon/storage_state.json, so authenticated sessions can be reused across later runs.

Setup

Before running, verify openbrowser-ai is installed:

openbrowser-ai --help

If not found, install:

# macOS/Linux
curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh

# Windows (PowerShell)
irm https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.ps1 | iex

Workflow

Step 1 -- Navigate and find download links

openbrowser-ai -c - <<'EOF'
await navigate("https://example.com/reports")

# Get browser state to find clickable download links
state = await browser.get_browser_state_summary()
for idx, el in state.dom_state.selector_map.items():
    text = el.get_all_children_text(max_depth=1)
    if "download" in text.lower() or "pdf" in text.lower() or "export" in text.lower():
        print(f"[{idx}] {el.tag_name}: {text}")
EOF

Step 2 -- Download a file by URL

Use download_file() to download directly. This uses the browser's JavaScript fetch internally, preserving cookies and authentication:

openbrowser-ai -c - <<'EOF'
path = await download_file("https://example.com/reports/annual-report.pdf")
print(f"Saved to: {path}")
EOF

With a custom filename:

openbrowser-ai -c - <<'EOF'
path = await download_file(
    "https://example.com/api/export?format=csv",
    filename="sales-data.csv"
)
print(f"Saved to: {path}")
EOF

Step 3 -- Extract a download URL from the page

When the download URL is not directly visible, extract it from a link or button:

openbrowser-ai -c - <<'EOF'
# Extract href from a download link
download_url = await evaluate("""
(function(){
  const link = document.querySelector("a[href$=\".pdf\"]");
  return link ? link.href : null;
})()
""")

if download_url:
    path = await download_file(download_url)
    print(f"Downloaded: {path}")
else:
    print("No PDF link found")
EOF

Step 4 -- Read a downloaded PDF

After downloading, use pypdf to extract text (requires pip install openbrowser-ai[pdf]):

openbrowser-ai -c - <<'EOF'
from pypdf import PdfReader

reader = PdfReader(path)
print(f"Pages: {len(reader.pages)}")

# Extract text from all pages
for i, page in enumerate(reader.pages):
    text = page.extract_text()
    print(f"--- Page {i+1} ---")
    print(text[:500])
EOF

Step 5 -- Read other file types

openbrowser-ai -c - <<'EOF'
from pathlib import Path

file_path = Path(path)

# CSV
if file_path.suffix == ".csv":
    import pandas as pd
    df = pd.read_csv(file_path)
    print(df.to_string())

# JSON
if file_path.suffix == ".json":
    import json
    data = json.loads(file_path.read_text())
    print(json.dumps(data, indent=2))

# Plain text
if file_path.suffix in (".txt", ".md", ".log"):
    print(file_path.read_text())
EOF

Step 6 -- Download multiple files

openbrowser-ai -c - <<'EOF'
urls = [
    "https://example.com/report-q1.pdf",
    "https://example.com/report-q2.pdf",
    "https://example.com/report-q3.pdf",
]

paths = []
for url in urls:
    path = await download_file(url)
    paths.append(path)
    print(f"Downloaded: {path}")

print(f"Total files: {len(paths)}")
EOF

Step 7 -- List all downloads

openbrowser-ai -c - <<'EOF'
files = list_downloads()
for f in files:
    print(f)
print(f"Total: {len(files)} files")
EOF

Step 8 -- Download from authenticated pages

download_file() preserves the browser's login session. Log in first, then download:

openbrowser-ai -c - <<'EOF'
# Navigate and log in
await navigate("https://portal.example.com/login")
await input_text(username_index, "[email protected]")
await input_text(password_index, "password")
await click(login_button_index)
await wait(2)

# Now download an authenticated resource
path = await download_file("https://portal.example.com/api/reports/confidential.pdf")
print(f"Downloaded: {path}")
EOF

Tips

Code is piped via stdin using heredoc (-c - <<'EOF'), so all Python syntax works without shell escaping issues.
Use download_file(url) instead of navigate(url) for files. navigate() opens PDFs in the browser viewer but does not save them.
download_file() preserves cookies and authentication -- no need to re-authenticate.
Filename conflicts are handled automatically with (N) suffix (e.g., report (1).pdf).
If no filename is provided, it is derived from the URL path.
Use list_downloads() to see all files saved in the downloads directory.
For large files, download_file() has a 120-second timeout.
The fallback strategy uses Python requests if the browser fetch fails (e.g., CORS restrictions), but without browser cookies.

Cleanup

This step is mandatory. Run it after every download run, whether the file landed successfully or the request failed. Without it, the daemon keeps Chrome running until its 10-minute idle timeout, leaving a stale browser process, a locked profile, and (on macOS/Linux desktop) a visible window.

Stop the daemon, then verify it is gone:

openbrowser-ai daemon stop
openbrowser-ai daemon status

daemon stop closes every tab, exits Chrome, flushes saved cookies/login state to the profile, and shuts down the daemon process. daemon status should report the daemon is not running. If it still reports running, the daemon is wedged, force-kill it:

pkill -f 'openbrowser.*daemon' || true

If a download can fail mid-workflow (timeout, 4xx/5xx, CORS), guarantee cleanup with a shell trap so the browser is never left orphaned:

trap 'openbrowser-ai daemon stop >/dev/null 2>&1 || true' EXIT
# ... openbrowser-ai -c calls here ...

Downloaded files in ~/.config/openbrowser/downloads/ survive daemon stop, only the browser process is terminated. Do not rely on the idle timeout. Do not call done() as a substitute, done() only marks the task complete inside the agent loop, it does not close the browser.

Other skills for the same job

different authors, same section of the catalogue

DOCX

by anthropics

vendor ×16

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.

3k tokens

How to use it

Copy the folder

Take billy-enrizky/file-download from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference pip. Without those the skill loads but fails at the first command.