Skill

parallel-web-search

Performs web searches via parallel-cli for research, lookups, and current info. Delivers cited summaries with full JSON results saved to /tmp for follow-ups.

Bash

developer-tools

npx claudepluginhub parallel-web/parallel-agent-skills --plugin parallel

Tool Access

This skill is limited to using the following tools:

Bash(parallel-cli:*)

Preview

Search the web for: $ARGUMENTS

SKILL.md

Similar Skills

parallel-web

1.6k

Enables web searches prioritizing academic/scientific sources, URL extraction for pages/PDFs, bulk data enrichment from web, and deep research reports via parallel-cli.

10 files

k-dense-ai-claude-scientific-writer

parallel

586

Executes high-accuracy web searches via Parallel.ai API using Python SDK. Provides rich excerpts, citations for deep research, fact-checking, company lookups, and complex AI agent queries.

2 files

sundial-org-awesome-openclaw-skills-4

parallel-deep-research

Conducts deep exhaustive research on topics via parallel-cli Bash tools for 'deep research' or 'comprehensive report' requests. Supports multi-turn context chaining; polls results asynchronously.

1 tool

parallel

Stats

Stars35

Forks0

Last CommitMar 27, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Web Search

Search the web for: $ARGUMENTS

Command

Choose a short, descriptive filename based on the query (e.g., ai-chip-news, react-vs-vue). Use lowercase with hyphens, no spaces.

parallel-cli search "$ARGUMENTS" -q "<keyword1>" -q "<keyword2>" --json --max-results 10 --excerpt-max-chars-total 27000 -o "/tmp/$FILENAME.json"

The first argument is the objective — a natural language description of what you're looking for. It replaces multiple keyword searches with a single call for broad or complex queries. Add -q flags for specific keyword queries to supplement the objective. The -o flag saves the full results to a JSON file for follow-up questions.

Options if needed:

--after-date YYYY-MM-DD for time-sensitive queries
--include-domains domain1.com,domain2.com to limit to specific sources

Parsing results

Do not set max_output_tokens on the command execution — the output is already bounded by --max-results and --excerpt-max-chars-total. Capping output tokens will truncate the JSON and break parsing.

Parse the JSON from stdout. For each result, extract:

title, url, publish_date
Useful content from excerpts (skip navigation noise like menus, footers, "Skip to content")

Response format

CRITICAL: Every claim must have an inline citation. Use markdown links like Title pulling only from the JSON output. Never invent or guess URLs.

Synthesize a response that:

Leads with the key answer/finding
Includes specific facts, names, numbers, dates
Cites every fact inline as Source Title — do not leave any claim uncited
Organizes by theme if multiple topics

End with a Sources section listing every URL referenced:

Sources:
- [Source Title](https://example.com/article) (Feb 2026)
- [Another Source](https://example.com/other) (Jan 2026)

This Sources section is mandatory. Do not omit it.

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

Setup

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

curl -fsSL https://parallel.ai/install.sh | bash

If unable to install that way, install via pipx instead:

pipx install "parallel-web-tools[cli]"
pipx ensurepath

Then authenticate:

parallel-cli login

Or set an API key: export PARALLEL_API_KEY="your-key"