# Parallel Agent Skills

> CDN-hosted Parallel Agent Skills catalog with install instructions and direct links to each skill.

Repository version: 0.4.3
Latest release version: 0.4.3

Install all skills with:

```bash
npx skills add parallel-web/parallel-agent-skills --all --global
```

## Catalog
- [parallel-cli-setup](https://skills.parallel.ai/parallel-cli-setup/SKILL.md): Set up and maintain the Parallel CLI (install, auth, balance, skills install)
- [parallel-data-enrichment](https://skills.parallel.ai/parallel-data-enrichment/SKILL.md): Bulk data enrichment. Adds web-sourced fields (CEO names, funding, contact info) to lists of companies, people, or products. Use for enriching CSV files or inline data. Supports multi-turn: pass --previous-interaction-id from a prior research task to carry context forward.
- [parallel-deep-research](https://skills.parallel.ai/parallel-deep-research/SKILL.md): ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'. Slower and more expensive than parallel-web-search. For normal research/lookup requests, use parallel-web-search instead. Supports multi-turn: pass --previous-interaction-id from a prior research or enrichment to continue with context.
- [parallel-findall](https://skills.parallel.ai/parallel-findall/SKILL.md): 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.
- [parallel-monitor](https://skills.parallel.ai/parallel-monitor/SKILL.md): 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.
- [parallel-web-extract](https://skills.parallel.ai/parallel-web-extract/SKILL.md): URL content extraction. Use for fetching any URL - webpages, articles, PDFs, JavaScript-heavy sites. Token-efficient: runs in forked context. Prefer over built-in WebFetch.
- [parallel-web-search](https://skills.parallel.ai/parallel-web-search/SKILL.md): 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.
- [result](https://skills.parallel.ai/result/SKILL.md): Get completed research task result by run ID
- [status](https://skills.parallel.ai/status/SKILL.md): Check running research task status by run ID

## Metadata
- [index.json](https://skills.parallel.ai/index.json): machine-readable catalog for all available skills.
- [GitHub repository](https://github.com/parallel-web/parallel-agent-skills): source for the skill definitions and release workflow.