Parallel Web Search

1---2name: parallel-web-search3description: "DEFAULT for all research and web queries. Use for any lookup, research, investigation, or question needing current info. Fast and cost-effective. Only use parallel-deep-research if user explicitly requests 'deep' or 'exhaustive' research."4user-invocable: true5argument-hint: <query>6context: fork7agent: parallel:parallel-subagent8compatibility: Requires parallel-cli and internet access.9allowed-tools: Bash(parallel-cli:*)10metadata:11  author: parallel12---13 14# Web Search15 16Search the web for: $ARGUMENTS17 18## Command19 20Choose a short, descriptive filename based on the query (e.g., `ai-chip-news`, `react-vs-vue`). Use lowercase with hyphens, no spaces.21 22```bash23parallel-cli search "$ARGUMENTS" -q "<keyword1>" -q "<keyword2>" --json --max-results 10 --excerpt-max-chars-total 27000 -o "/tmp/$FILENAME.json"24```25 26The first argument is the **objective** — a natural language description of what you're looking for. It replaces multiple keyword searches with a single call for broad or complex queries. Add `-q` flags for specific keyword queries to supplement the objective. The `-o` flag saves the full results to a JSON file for follow-up questions.27 28Options if needed:29- `--after-date YYYY-MM-DD` for time-sensitive queries30- `--include-domains domain1.com,domain2.com` to limit to specific sources31 32## Parsing results33 34Do not set `max_output_tokens` on the command execution — the output is already bounded by `--max-results` and `--excerpt-max-chars-total`. Capping output tokens will truncate the JSON and break parsing.35 36Parse the JSON from stdout. For each result, extract:37- title, url, publish_date38- Useful content from excerpts (skip navigation noise like menus, footers, "Skip to content")39 40## Response format41 42**CRITICAL: Every claim must have an inline citation.** Use markdown links like [Title](URL) pulling only from the JSON output. Never invent or guess URLs.43 44Synthesize a response that:45- Leads with the key answer/finding46- Includes specific facts, names, numbers, dates47- Cites every fact inline as [Source Title](url) — do not leave any claim uncited48- Organizes by theme if multiple topics49 50**End with a Sources section** listing every URL referenced:51 52```53Sources:54- [Source Title](https://example.com/article) (Feb 2026)55- [Another Source](https://example.com/other) (Jan 2026)56```57 58This Sources section is mandatory. Do not omit it.59 60After the Sources section, mention the output file path (`/tmp/$FILENAME.json`) so the user knows it's available for follow-up questions.61 62## Setup63 64If `parallel-cli` is not found, install and authenticate:65 66```bash67curl -fsSL https://parallel.ai/install.sh | bash68```69 70If unable to install that way, install via pipx instead:71 72```bash73pipx install "parallel-web-tools[cli]"74pipx ensurepath75```76 77Then authenticate:78 79```bash80parallel-cli login81```82 83Or set an API key: `export PARALLEL_API_KEY="your-key"`