Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Adds web-sourced information to CSV files or inline data in bulk. Can carry context forward from previous research tasks through a prior interaction ID.
Investigate complex bugs with multiple potential causes through parallel hypothesis testing. Collect evidence and arbitrate competing explanations to identify the root cause.
Supports explicitly requested deep or exhaustive research and comprehensive reports. Trades greater time and cost for depth and can continue with context from earlier research or enrichment tasks.
Split large features into independent work streams for simultaneous implementation. Covers file ownership, conflict avoidance, interface contracts, integration patterns, and choosing vertical slices or horizontal layers.
Produces structured lists of entities that meet specified criteria. Supports requests such as finding startups by funding stage or companies by location, rather than returning webpages or narrative reports.
Retrieves past Parallel runs when their context may help current work. Supports evicting individual runs or clearing memory on request.
Tracks changes such as product prices, company filings, or competitor webpages on a recurring cadence. Supports listing, inspecting, updating, stopping, and deleting monitors.
Identifies an explicit /parallel-task command as its only activation method. The description does not specify the tasks performed or execution behavior.
Supports URL extraction, entity discovery, structured enrichment, and recurring web monitoring. Suits current-evidence research, academic-source discovery, repeated lookups, and exhaustive reports.
CLI-backed URL extraction. Use when the user explicitly invokes this skill, needs CLI-only controls or saved JSON output, or no Parallel web_fetch MCP tool is available. When the bundled Parallel Search MCP is available, prefer its web_fetch tool for ordinary webpages, articles, PDFs, and JavaScript-heavy sites.
CLI-backed web search. Use when the user explicitly invokes this skill, needs CLI-only controls or saved JSON output, or no Parallel web_search MCP tool is available. When the bundled Parallel Search MCP is available, prefer its web_search tool for ordinary lookups and current-information queries. Only use parallel-deep-research if the user explicitly requests deep or exhaustive research.
Systematic fuzzing across two dimensions: (1) content discovery — hidden directories, files, backup/source leaks, HTTP verb enumeration, 401/403 bypass via path manipulation; (2) input validation — auth/token stripping, type confusion, boundary value analysis, HTTP parameter pollution, header fuzzing, cookie fuzzing, mass assignment discovery, and entropy/predictability analysis of any generated v…
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name