Parallel Web Extract

What it does

The entry reserves the CLI path for explicit use, CLI-only controls or missing MCP fetch capability. It describes bounded multi-URL requests, focused or full-content output and per-URL failures. A saved result is the authoritative artifact because console previews can truncate, and successful and failed URLs can coexist.

Best for

Researchers and developers who need a reproducible extraction file rather than an informal page preview.

Tradeoffs and requirements

CLI installation, authentication and service eligibility are separate prerequisites. Output paths can be overwritten and full-content responses can still be capped. The instruction requests preservation of retrieved text, but publication or redistribution must also respect applicable source rights and the host environment rules.

Requires parallel-cli and internet access.

Data and service requirements

Extraction sends the requested URLs and optional objective or query terms to Parallel. Account, policy or billing failures need their actual diagnosis; no account was connected or service balance changed by the catalog.

Instruction-level disclosure at the checked snapshot; not an independent audit of the service or its current terms.

Install from the source

First time installing a skill? Follow the walkthrough →

Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code. Catalog ingestion never executes skill instructions or install scripts.

npx skills add https://github.com/parallel-web/parallel-agent-skills/tree/6c873020213d981984aa8e897cd55e5413d1322f/skills/parallel-web-extract --skill parallel-web-extract

Review pinned skill folder ↗ · CLI documentation ↗

After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.

Safety & review signals

Static review only. This is not a security audit or a guarantee of safety.

SKILL.md text only; scripts, dependencies and runtime behavior not audited.

• Network Access — review the source context.
• Shell Or Package Install — review the source context.

Allowed tools declaration: Bash(parallel-cli:*). Runtime permissions and network behavior: Unknown.

AI Craft Pad Skill Score

85/100 · Metadata coverage 100% · Model 1.0

Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.

Documentation

100/100

100

Maintenance

100/100

100

License Clarity

100/100

100

Repository Health

100/100

100

Compatibility Evidence

80/100

80

Popularity

35/100

35

Originality

80/100

80

Static Safety

60/100

60

Suggested workflow

Confirm the requested URLs and inspect the destination file before constructing separate quoted arguments. Choose the content scope, run only an authorized service request and inspect status, per-URL errors and the actual saved file before presenting any result.

How to judge the result

Check successful content against its source URL and label excerpts, caps and partial failures accurately. Ensure a failed request did not leave a stale file that is mistaken for new output. Distinguish data retrieval from permission to reproduce an entire third-party page.