parallel-web-extract

Q: How do I install parallel-web-extract?

Run npx skills add https://github.com/parallel-web/parallel-agent-skills --skill parallel-web-extract in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/parallel-web-extract/ (personal) or .claude/skills/parallel-web-extract/ (project).

by parallel-web OfficialAI & Agents

CLI-backed URL extraction. Use when the user explicitly invokes this skill, needs CLI-only controls or saved JSON output, or no Parallel webfetch MCP tool is available. When the bundled Parallel Search MCP is available, prefer its webfetch tool for ordinary webpages, articles, PDFs, and JavaScript-heavy sites.

Installs: 13.6K
Last 24h: +27
Trending rank: #4628
Security: Warn

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/parallel-web/parallel-agent-skills --skill parallel-web-extract

01
Install
Run the command in your project. The CLI asks which agents to install for.
02
Describe the task
Ask your agent for something this skill covers. It loads parallel-web-extract automatically when relevant.
03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.

Security audits

Independent scans of the skill's instructions and bundled files.

Gen Agent Trust Hub PassSAFE ·The skill facilitates web content extraction via a vendor-specific CLI tool. It introduces a surface for indirect prompt injection by processing external data without boundary markers and includes a shell command execution pattern that relies on proper sanitization of user-supplied arguments.

Socket PassNo alerts

Snyk WarnMEDIUM ·Risk: MEDIUM · 2 issues

Runlayer WarnMEDIUM ·1/1 file flagged

ZeroLeaks PassLOW ·1 finding · Score: 82/100

SKILL.md

The instructions your agent reads when the skill is triggered.

URL Extraction

Extract content from: $ARGUMENTS

Command

Choose a short, descriptive filename based on the URL or content (e.g., vespa-docs, react-hooks-api). Use lowercase with hyphens, no spaces. Substitute it into the command inline — $FILENAME is a placeholder, not a shell variable.

Pass each requested URL as a separate quoted positional argument, up to 20 per call. Do not collapse multiple URLs into one quoted $ARGUMENTS string or use eval to split them. Construct arguments directly from the requested URLs. For example:

parallel-cli extract "https://docs.parallel.ai/integrations/cli" "https://docs.parallel.ai/integrations/cursor-marketplace" --json -o "/tmp/parallel-docs.json"

-o saves JSON. Use a .json extension and inspect an existing path before use because Extract overwrites it. Read the saved file as authoritative; stdout may truncate and human-readable output previews only part of the content. Do not treat a stale file as a successful response after a failed call.

Options if needed:

--objective "focus area" to focus extraction on a specific goal (also silences the "neither objective nor search_queries" warning that V1 emits when neither is set)
-q "keyword" (repeatable) to prioritize keywords in excerpts
--full-content to include the complete page body (for long articles, PDFs, or when excerpts may not capture what you need)
--full-content-max-chars N to cap full-content size per result
--no-excerpts to strip excerpts when you only want full content
--session-id "<returned-session-id>" to group related Search/Extract calls. A session ID is not a Task interaction ID or run ID; never use it with research status/poll or --previous-interaction-id

Handling failed extractions

Inspect the exit status, API error, results, per-URL errors and any warnings. errors: [] is normal success. Nonempty errors can coexist with successful results: retain and present successful content, then name each failed URL and its returned reason. Empty results or missing content are not a successful extraction. Do not fabricate content. For affected URLs, suggest:

Verifying the URL (the page may have moved)
Requesting --full-content if excerpts are empty but the returned metadata supports that the page was fetched
Using parallel-cli search to locate the current URL if the page was renamed

Response format

Return content as:

Page Title

Use returned full_content for full-page requests; excerpts alone are selected passages and must be labelled as such. Even full content may be capped by --full-content-max-chars or upstream limits; do not promise completeness when capped. Preserve retrieved content verbatim, with these rules:

Keep content verbatim - do not paraphrase or summarize
Preserve every numbered/bulleted item in the retrieved content; do not claim an excerpt contains the whole page
Strip only obvious noise: nav menus, footers, ads
Preserve all facts, names, numbers, dates, quotes

After the response, mention the output file path (/tmp/$FILENAME.json) so the user knows it's available for follow-up questions.

For large content, keep the full verbatim text in the saved file and provide a brief labelled preview plus its path. Never silently truncate content while claiming it is the complete extraction.

Setup

If parallel-cli is not found, install and authenticate:

/parallel:parallel-cli-setup

If a documented command or option is missing, check the installed version and upgrade through its installation method: standalone parallel-cli update, pipx pipx upgrade parallel-web-tools, uv uv tool upgrade parallel-web-tools, Homebrew brew upgrade parallel-web/tap/parallel-cli, or npm npm update -g parallel-web-cli. Verify help in the same terminal before retrying.

For authentication errors, inspect parallel-cli auth --json and its authenticated boolean; exit zero alone does not prove authentication. A 403 can indicate permissions, policy or billing. Report the actual error; check balance only for a billing-specific failure and never add funds without explicit confirmation.

FAQ

What does the parallel-web-extract skill do?

How do I install parallel-web-extract?

Run npx skills add https://github.com/parallel-web/parallel-agent-skills --skill parallel-web-extract in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/parallel-web-extract/ (personal) or .claude/skills/parallel-web-extract/ (project).

Which AI agents can use parallel-web-extract?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is parallel-web-extract safe to install?

Security partners have reviewed it: Gen Agent Trust Hub passed; Socket passed; Snyk flagged items to review; Runlayer flagged items to review; ZeroLeaks passed. As with any skill, read the SKILL.md and bundled scripts before installing.

Who maintains parallel-web-extract?

It is published by parallel-web in parallel-web/parallel-agent-skills, and it is an official skill from the maker of the technology it covers. It has 13,645 recorded installs.