parallel-deep-research Skill for Claude: What It Does and How to Install It

Makes Claude run a long, multi-source research task on Parallel and save a cited report.

Installs: 15.8K; on skills.sh
Stars: 91; on GitHub
Updated: Oct 2026; last repo commit

This is Parallel's own deep research skill. Only when you ask for deep, exhaustive or comprehensive research does Claude start a parallel-cli research task, give you a monitoring link, poll until it finishes, and save a cited Markdown report plus a JSON file with sources.

It needs parallel-cli installed, signed in and funded on your Parallel account. The folder holds only SKILL.md and bundles no scripts. The status and result skills in the same repo check on a saved run.

Good for

Analysts who want a sourced report on a market, company or topic
Anyone who says "deep research" and accepts a wait of several minutes
Developers who want the report saved as Markdown and JSON files

Install parallel-deep-research

Claude Code

Copy this prompt.

Install the parallel-deep-research skill in Claude Code. Run this command:

/plugin marketplace add parallel-web/parallel-agent-skills
/plugin install parallel

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Pick one route. The plugin installs all 15 skills (counted from the repo), a hosted Parallel Search MCP server (parallel-search, anonymous) and a Bash-only agent called parallel-subagent. Restart Claude Code after installing it. This skill needs parallel-cli installed, signed in and funded; the second method in each tab lists the install commands from the repo's setup skill, and /parallel:parallel-cli-setup runs them for you. In Codex, use $ instead of / for skill names.

From the project README. Source.

What's in the skill

When it loads

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 follow-ups with a known prior Task interaction ID.

Sections in SKILL.md

When to use (vs parallel-web-search)
Step 1: Start the research
Step 2: Poll for results
If polling times out or is interrupted
Response format
Setup

Key facts

Author: Parallel Web Systems (vendor's own repo)
Repo: parallel-web/parallel-agent-skills
License: MIT (LICENSE file; README and plugin.json agree)
Installs on skills.sh: 15,818 (Nov 2, 2026)
GitHub stars: 91 for the whole repo (Nov 2, 2026)
Last repo commit: Oct 28, 2026
Audits on skills.sh: Gen Agent Trust Hub: pass, Socket: pass, Snyk: warn
What it includes: 1 file: SKILL.md. It bundles no scripts
Part of: Plugin parallel: 15 skills, a hosted MCP server and 1 agent
Needs: parallel-cli 0.3.0 or newer, internet access, a funded Parallel account

What it includes

Starts only when you ask for deep, exhaustive or thorough research
For normal research or lookups SKILL.md says to use parallel-web-search instead.
Try: “Do deep research on the competitive landscape of AI code assistants”
Trigger rule
Starts the task with --processor pro-fast and --text, then returns right away (--no-wait)
It saves the run_id, interaction_id and result_url and tells you the monitoring link.
Runs code · research run
Waits in 60-second chunks and saves the report as .md plus a .json with sources
Existing output files are refused unless --force is used.
Runs code · research poll
Checks a saved run after a timeout, instead of creating a new task
Runs code · research status
Passes --previous-interaction-id so a new question reuses the earlier research
Not available on Zero Data Retention accounts. SKILL.md suggests follow-ups such as "drill deeper into X" or "compare that to Y".
Runs code · Follow-up chaining
pro-fast by default; lite-fast or base-fast for focused follow-ups; ultra only on request
`parallel-cli research processors` lists the options and latency estimates.
Runs code · Processor choice
Steers the report length, format or focus
Example in SKILL.md: keep under 1500 words, focus on M&A activity.
Runs code · --text-description
If parallel-cli is missing, runs /parallel:parallel-cli-setup
Runs code · Setup fallback

From the official docs

Permissions

Medium risk

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Your queries are sent to Parallel
The README says task inputs go to Parallel's API under its Customer Terms and Privacy Policy, and tells you not to send secrets or sensitive local content. Review what Claude puts in a request. github.com
Deep research costs more than a search
SKILL.md says it can take several minutes and costs more than a quick search, depending on the processor. The ultra tiers are meant only when you ask and within your approved budget. Check current pricing first. github.com
It runs against your funded Parallel account
The README says CLI-backed skills are billed as ordinary API usage on your own Parallel account. Check current pricing on the vendor site before large runs. github.com
The setup path installs and signs in a CLI
The repo's setup skill installs parallel-cli (brew, uv, npm or pipx), starts a device sign-in, and points to `parallel-cli balance add` for top-ups. The search and research skills say never to add funds without explicit confirmation. github.com
Tasks keep running after a timeout
Research runs on Parallel's servers. A local timeout ends only your wait, so Claude should check status with the saved run ID and not start a duplicate task. github.com

Technical details

Turning on read-only	There is no read-only switch. The skill runs parallel-cli commands that call Parallel's API under your account.
Sign-in and keys	parallel-cli signs in with a device OAuth flow you approve in a browser. The README says CLI-backed skills use credentials you already configured.
Scopes	Runs parallel-cli through Bash (allowed-tools: Bash(parallel-cli:*)) Writes a Markdown report and a JSON file to the output path Claude chooses

Questions

What does the parallel-deep-research skill do?

It makes Claude start a long, multi-source research task on Parallel's servers with parallel-cli research run, poll for it, and save a cited Markdown report plus a JSON file with sources.

How do I install parallel-deep-research?

Use the install box above. The plugin installs it with 14 other skills. Then install and sign in to parallel-cli, which needs version 0.3.0 or newer for text output and context chaining.

When does it start?

Only when you explicitly ask for deep research, exhaustive work, a comprehensive report or a thorough investigation. SKILL.md says normal "research X" requests should go to parallel-web-search.

How long does it take and what does it cost?

SKILL.md says it can take several minutes and costs more than a quick search, depending on the processor. It points to Parallel's pricing page instead of quoting numbers. Charges go to your own Parallel account, per the README.

Can I ask follow-up questions?

Yes. Claude reports the interaction ID after the run, and a follow-up reuses that research context. SKILL.md says this does not work on Zero Data Retention accounts.

How do I check on a run that is still going?

Use the run ID with the sibling status skill, or ask Claude to run parallel-cli research status. SKILL.md says a timeout ends only your local wait, and a new task should not be created.

Is it safe?

It runs parallel-cli in Bash, sends your research topic to Parallel, writes report files, and spends credits on your account. Our advice: say what budget and processor you allow before it starts.

Is it an official Parallel skill?

It is in Parallel Web Systems' own repo, and the repo's marketplace.json describes the plugin as the "Official Parallel Web Systems plugin for Claude Code".

Information

updated Nov 2, 2026

Repository: parallel-web/parallel-agent-skills
Folder: skills/parallel-deep-research

parallel-web/parallel-agent-skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 5

parallel-agent-skills README · github.com
parallel-agent-skills marketplace.json · github.com
parallel plugin.json · github.com
parallel-cli-setup SKILL.md · github.com
parallel-deep-research SKILL.md · github.com