parallel-web/parallel-agent-skills
9 skills89.3k installs558 starsGitHub
Install
npx skills add https://github.com/parallel-web/parallel-agent-skillsSkills in this repo
1Parallel Deep Researchparallel-deep-research is a CLI skill that orchestrates deep, multi-turn web research via the parallel-cli platform. Developers invoke it explicitly for exhaustive topic investigation (10-100x slower/costlier than shallow search), selecting from six processor tiers (lite-fast to ultra8x-fast) based on latency and depth needs. The workflow: (1) kick off research with `parallel-cli research run` and receive a run_id and monitoring URL, (2) poll results via `parallel-cli research poll` with a 9-minute timeout, writing markdown reports and JSON metadata to disk. Key feature: pass `--previous-interaction-id` to chain context across follow-ups, enabling progressive drill-downs without restating prior findings. Designed for agents and CLI tools requiring structured, cited, long-form research output.12.4kinstalls2Parallel Web SearchDEFAULT 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 name parallel-web-search description DEFAULT for all research and web queries Use for any lookup research investigation or question needing current info Only use parallel-deep-research if user explicitly requests deep or exhaustive research user-invocable true argument-hint query context fork agent parallel parallel-subagent compatibility Requires parallel-cli and internet access allowed-tools Bash parallel-cli metadata author parallel 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.11.4kinstalls3Parallel Web Extractparallel-web-extract fetches and extracts content from any URL, returning structured JSON output. Developers use it to harvest webpage text, API documentation, articles, and PDFs without manual parsing or browser overhead. It runs in a forked context for token efficiency and supports focus via objectives, keyword filtering, and full-content modes. Handles JavaScript-rendered pages and provides clear error reporting when extraction fails, with suggestions for retry strategies.10.9kinstalls4Parallel Data EnrichmentBulk data enrichment tool that augments CSV files or inline datasets with web-sourced information (CEO names, founding years, recent funding, contact details). Developers use it to enrich lead lists, company databases, or people records without manual research. Supports multi-turn workflows by chaining to prior research tasks via interaction IDs. Runs via parallel-cli with --no-wait mode for async execution; developers poll results later with a 9-minute timeout. Output is always JSON array of {input, output} objects regardless of input format.10.8kinstalls5StatusThis skill checks the execution status of a research task within the Parallel platform by querying its run ID. Developers invoke it during async research workflows to track progress without blocking execution. It wraps the `parallel-cli research status` command with JSON output, enabling agent-driven polling and status monitoring in CI/CD pipelines or autonomous agent loops.10.7kinstalls6ResultThis skill retrieves results from completed Parallel research tasks using a run ID. Developers invoke it through a Bash command that queries the parallel-cli research subsystem with JSON output formatting. The skill wraps the underlying `parallel-cli research poll` command, handling cases where the CLI is not installed by directing users to run setup. It serves as a monitoring checkpoint in research workflows, enabling developers to access and present task outputs in structured formats.10.7kinstalls7Parallel MonitorContinuously track the web for changes on a recurring cadence. Use when the user asks to 'monitor', 'track changes to', 'watch', or 'alert me when' something on the web changes - e.g., 'Track price changes for iPhone 16', 'Alert me when Tesla files a new 8-K', 'Monitor competitor pricing pages weekly'. Also use to list, inspect, update, or delete existing monitors. --- name: parallel-monitor description: "Continuously track the web for changes on a recurring cadence. Use when the user asks to 'monitor', 'track changes to', 'watch', or 'alert me when' something on the web changes - e.g., 'Track price changes for iPhone 16', 'Alert me when Tesla files a new 8-K', 'Monitor competitor pricing pages weekly'. Also use to list, inspect, update, or delete existing monitors." user-invocable: true argument-hint: <create|list|events|get|update|simulate|event-group|delete> [args] compatibility: Requires parallel-cli >= 0.3.0 and internet access.9.6kinstalls8Parallel FindallDiscover entities (companies, people, products, etc.) matching a natural-language description. Use when the user asks to 'find all X' or 'list every Y that…' - e.g., 'Find AI startups that raised Series A in 2026', 'List roofing companies in Charlotte NC', 'Show me YC W24 dev tools companies'. Different from web-search (which returns webpages) and deep-research (which returns a narrative report). --- name: parallel-findall description: "Discover entities (companies, people, products, etc.) matching a natural-language description. Use when the user asks to 'find all X' or 'list every Y that…' - e.g., 'Find AI startups that raised Series A in 2026', 'List roofing companies in Charlotte NC', 'Show me YC W24 dev tools companies'. Different from web-search (which returns webpages) and deep-research (which returns a narrative report). Use this when the user wants a structured list of entities." user-invocable: true argument-hint: <objective describing entities to find> compatibility: Requires parallel-cli >= 0.6.0 and internet access.9.6kinstalls9Parallel Cli SetupThe parallel-cli-setup skill installs and maintains parallel-cli so agents can run Parallel web search, extract, and deep research tools. Step one checks command -v parallel-cli and installs via Homebrew tap, uv tool, npm global, or pipx when missing, requiring version 0.4.0 or newer with upgrade paths per install method. Step two runs parallel-cli auth --json and parallel-cli login --json when unauthenticated or selected_org_id is legacy, using device OAuth with optional --no-browser for headless sessions. Step three checks parallel-cli balance get and prompts parallel-cli balance add when zero, noting payment methods at platform.parallel.ai settings. Step four runs parallel-cli skills install to place skills under ~/.agents/skills, possibly requiring agent restart without hot reload. Step five suggests first commands such as parallel-web-search, parallel-web-extract, or parallel-deep-research. Allowed tools include Bash for brew, uv, npm, pipx, curl, and parallel-cli invocations.3.1kinstalls