harshanandak/forge

parallel-deep-research

Heavyweight EXTERNAL research reports — market, industry, competitive, strategic — via Parallel AI's paid pro/ultra processors that crawl and synthesize dozens of sources into one long cited report. Use when the user wants a market analysis, competitive landscape, industry deep-dive, multi-vendor/technology comparison, strategic recommendations, or market sizing/growth outlook — any multi-source synthesis needing more than 3-4 web searches. Typical phrasings: "market analysis of X", "competitiv…

First seen Feb 23, 2026

Installation

$ npx skills add harshanandak/forge --skill parallel-deep-research

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from harshanandak/forge · top by installs.

npx skills add harshanandak/forge

Browse all from harshanandak/forge

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Also listed on

Alternate registries and mirrors of this skill.

Repository health

Stars 4
License LICENSE
Default branch master
Open issues 0
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

Version1.0.0
CompatibilityRequires PARALLEL_API_KEY in .env.local. Uses curl. Takes 3-25 minutes.
More metadata
author
harshanandak
version
1.0.0

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,983 B
  • docs SUMMARY.md 1,034 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 22 installs

SKILL.md

Parallel Deep Research

Comprehensive research reports with multi-source synthesis. Use pro (3-9 min, $0.10) or ultra (5-25 min, $0.30) for deep analysis.

Safety: The input is transmitted to Parallel AI's external service and may be logged or retained. Never include secrets, API keys/tokens, PII, or private/proprietary repo content — send only information safe to share with a third party.

CLI alternative (recommended): Install parallel-cli for official skill:
npx skills add parallel-web/parallel-agent-skills --skill parallel-deep-research

Setup

API_KEY=$(grep "^PARALLEL_API_KEY=" .env.local | cut -d= -f2)

Create Research Task

curl -s -X POST "https://api.parallel.ai/v1/tasks/runs" \
  -H "x-api-key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Analyze the AI chatbot market. Include: size, growth, key players, trends, competitive threats",
    "processor": "pro"
  }'

Response: {"runid": "trunabc123...", "status": "queued"}

Get Result (polling)

The result endpoint returns both status and output in one call. Poll until status is completed.

RUN_ID="trun_abc123..."
MAX_POLLS=180  # 30 min max (180 × 10s)

for i in $(seq 1 $MAX_POLLS); do
  RESULT=$(curl -s "https://api.parallel.ai/v1/tasks/runs/$RUN_ID/result" \
    -H "x-api-key: $API_KEY")

  STATUS=$(echo "$RESULT" | grep -o '"status":"[^"]*"' | head -1 | cut -d'"' -f4)

  if [ "$STATUS" = "completed" ]; then
    echo "$RESULT"
    break
  elif [ "$STATUS" = "failed" ]; then
    echo "Task failed: $RESULT"
    break
  fi

  echo "Poll $i/$MAX_POLLS — Status: $STATUS"
  sleep 10
done

if [ "$i" = "$MAX_POLLS" ] && [ "$STATUS" != "completed" ] && [ "$STATUS" != "failed" ]; then
  echo "Timeout: task did not complete within 30 minutes"
fi

Processors

Processor Speed Cost Use For
pro 3-9 min $0.10/task Market analysis, strategic reports
ultra 5-25 min $0.30/task Comprehensive deep research

Example: Market Analysis

{
  "input": "Analyze the AI chip market in 2024. Include market size, growth rate, key players (NVIDIA, AMD, Intel), emerging competitors, and 2025 outlook.",
  "processor": "pro"
}

Result: Markdown report with citations.

When to Use

  • Market research and competitive analysis
  • Strategic reports requiring multiple sources
  • Research that needs synthesis across many documents
  • Any task that would need more than 3-4 web searches to answer properly

For quick facts or single-source lookups, use built-in WebSearch instead.

Timeout

Set polling timeout to 1800s (30 min) for ultra tasks. Pro tasks typically complete in 3-9 min.