Parallel Web Search
Run fast, cost-effective web lookups and broad research through parallel-cli without defaulting to deep-research unless you explicitly need exhaustive coverage.
Overview
parallel-web-search is a journey-wide agent skill that runs parallel-cli web search with JSON excerpts—usable whenever a solo builder needs current information before committing to research-heavy work.
Install
npx skills add https://github.com/parallel-web/parallel-agent-skills --skill parallel-web-searchWhat is this skill?
- Default path for any lookup, investigation, or question needing current info via parallel-cli search
- Single objective string plus optional -q keyword flags in one Bash invocation
- JSON output with up to 10 results and ~27k excerpt chars written to a descriptive /tmp filename
- Fork context with parallel:parallel-subagent for isolated research runs
- Escalate to parallel-deep-research only when the user explicitly asks for deep or exhaustive research
- --max-results 10
- --excerpt-max-chars-total 27000
Adoption & trust: 8.4k installs on skills.sh; 56 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need trustworthy, up-to-date web facts but do not want to burn time and tokens on deep research for every simple lookup.
Who is it for?
Routine market checks, API docs lookups, competitor snapshots, and any agent task where parallel-cli is installed and speed matters more than exhaustive coverage.
Skip if: Exhaustive literature reviews or multi-source synthesis—use parallel-deep-research when the user explicitly requests deep or exhaustive research.
When should I use this skill?
Any lookup, research, investigation, or question needing current info; default unless the user explicitly requests deep or exhaustive research.
What do I get? / Deliverables
Your agent writes a scoped search command, saves structured JSON under /tmp, and returns excerpted sources you can cite in specs, landing copy, or implementation decisions.
- /tmp JSON search artifact with excerpts
- structured web results for downstream summarization
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Pull recent competitor pricing pages and feature announcements into a JSON file before choosing a niche.
Verify current statistics and citations for a validation landing page hero section.
Confirm the latest API rate limits and auth docs before wiring a third-party SDK.
Sample top-ranking pages for a target query to inform metadata and content angles.
Look up breaking changes or incident postmortems when debugging a production integration.
How it compares
Use instead of pasting raw browser tabs into chat when you want reproducible CLI output and capped excerpts for the agent.
Common Questions / FAQ
Who is parallel-web-search for?
Solo and indie builders using Claude Code, Cursor, Codex, or similar agents with Parallel’s parallel-cli installed who want a default, cost-aware web search step.
When should I use parallel-web-search?
During idea research and competitor discovery, while validating scope with current pricing or regulations, before build decisions that depend on fresh docs, when preparing launch or SEO briefs with recent SERP context, and for grow or operate questions that need up-to-date troubl
Is parallel-web-search safe to install?
It invokes shell access to parallel-cli and the public internet; review the Security Audits panel on this Prism page and restrict allowed-tools in your agent policy if you need tighter boundaries.
SKILL.md
READMESKILL.md - Parallel Web Search
# 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. ```bash 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: ```bash 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 advanced` for harder questions (multi-step, agentic search). Default `basic` is right for almost everything; only escalate when basic results are insufficient - `--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/$FILENAME.json` for the authoritative payload. For each result, extract: - title, url, publish_date - Useful content from excerpts (skip navigation noise like menus, footers, "Skip to content") ## Response format **CRITICAL: Every claim must have an inline citation.** Use markdown links like [Title](URL) pulling only from the JSON output. Never invent or guess URLs. Synthesize a response that: - Leads with the key answer/finding - Includes specific facts, names, numbers, dates - Cites every fact inline as [Source Title](url) — do not leave any claim uncited - Organizes by theme if multiple topics **End with a Sources section** listing every URL referenced: ```text Sources: - [Source Title](https://example.com/article) (Feb 2026) - [Another Source](https://example.com/other) (Jan 2026) ``` This Sources section is mandatory. Do not omit it. After the Sources section, mention the output file path (`/tmp/$FILENAME.json`) so the user knows it's available for follow-up questions. ## Setup If `parallel-cli` is not found, install and authenticate: ```bash /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.