parallel-web-search

par parallel-web

Recherche web rapide pour des informations actuelles, des recherches et des vérifications de faits sur internet. Exécute des requêtes basées sur un seul objectif ou plusieurs recherches par mots-clés en parallèle, renvoyant jusqu'à 10 résultats avec des extraits et des métadonnées. Prend en charge le filtrage temporel via --after-date et les recherches spécifiques à un domaine avec --include-domains. Produit un JSON structuré avec titres, URL, dates de publication et extraits pour une analyse facile et des requêtes de suivi. Nécessite des citations en ligne pour chaque affirmation en utilisant le markdown...

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

Télécharger ZIP GitHub

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. Substitute it into the command inline — $FILENAME and <keyword> below are placeholders, not shell variables; do not copy them verbatim.

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

Concrete example for a query about React 19:

parallel-cli search "latest React 19 features and adoption" -q "React 19" -q "concurrent rendering" --json --max-results 10 --excerpt-max-chars-total 27000 -o "/tmp/react-19-features.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
--exclude-domains domain.com to filter out noisy sources
--mode turbo for simple fact lookups where speed and cost matter most (p50 ~200ms, lowest cost). English and Japanese queries only
--mode advanced for harder questions (multi-step, agentic search). Default basic is right for almost everything; escalate to advanced only when basic results are insufficient, and drop to turbo for high-volume simple lookups
--location us (ISO 3166-1 alpha-2) for geo-targeted results

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.

Prefer reading from the saved -o file, not stdout. Even bounded output regularly exceeds harness stdout limits and gets truncated. Read /tmp/$FILENAME.json for the authoritative payload. 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:

/parallel:parallel-cli-setup

If parallel-cli search returns 403, tell the user balance is likely required. Offer to run parallel-cli balance get, and if needed ask for explicit confirmation before running parallel-cli balance add <amount_cents>. Then retry the original search command.