
Parallel Deep Research
The parallel-deep-research skill conducts exhaustive, multi-source research investigations for users who explicitly request deep or comprehensive analysis, using Parallel's research infrastructure to gather and synthesize information across extended timeframes. It serves researchers, analysts, and users tackling complex topics who need thorough investigation beyond quick fact-checking, solving the problem of shallow or incomplete research by providing configurable depth levels (pro-fast, ultra-fast, ultra) with appropriate latency and cost trade-offs. The skill supports context chaining across multiple turns, allowing users to drill deeper into topics by referencing previous research interactions without restating prior findings.
- skills.sh installs
- 16.1K
- GitHub stars
- 91
- last updated
- Aug 21, 2026
Install
$ npx -y skills add parallel-web/parallel-agent-skills --skill parallel-deep-research --agent claude-codeInstalls into .claude/skills of the current project.
Files
Deep Research
Research topic: $ARGUMENTS
Requires
parallel-cli≥ 0.3.0 for text output and context chaining. If a documented command or option is missing, checkparallel-cli --versionand that command's--help, then follow the installation-specific upgrade guidance in Setup. API, authentication and input errors are not evidence of an older CLI.
When to use (vs parallel-web-search)
ONLY use this skill when the user explicitly requests deep/exhaustive research. It can take several minutes and costs more than a quick search, depending on the processor and task. For normal "research X" requests, quick lookups, or fact-checking, use parallel-web-search instead.
Step 1: Start the research
Choose a descriptive output base in a persistent directory (e.g., reports/ai-chip-market-2026). Include the returned run ID to make it unique, then use this base in step 2 as -o "$FILENAME". Check for existing .json and .md files before saving.
parallel-cli research run "$ARGUMENTS" --processor pro-fast --text --no-wait --json
Sponsors