parallel-deep-research
Skill4 starsChanged 48 days agoMITView on GitHub
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", "competitive landscape comparing A/B/C", "industry deep-dive on...", "deep research report on...", "strategic report with predictions for 2027". WRONG tool for quick facts, a single-page fetch, one-URL scraping, or small structured-field extraction — use built-in WebSearch/WebFetch. Also NOT the Forge RESEARCH or PLAN stage: "run the research stage", "do Phase 2", or codebase/OWASP/DRY investigation into a design doc route to `research` and `plan` (they may INVOKE this skill). Requires PARALLEL_API_KEY.
- Reads credentials
- Sends data out
2 other projects use a version of this.
Adopted by
Most recently taken up by
- xiangu152/my_claude_skillstheir own version, first seen Apr 5, 2026
- parallel-web/parallel-agent-skillstheir own version, first seen Mar 27, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- parallel-web/parallel-agent-skills★ 91same name
- xiangu152/my_claude_skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository51 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/permissions-guidance.mdcCursor rule
- claim-safetySkill
- devSkill
- gatesSkill
- hermes-forgeSkill
- issue-basicsSkill
- kernelSkill
- memorySkill
- parallel-deep-researchSkill
- planSkill
- portabilitySkill
- researchSkill
- reviewSkill
- rollbackSkill
- setupSkill
- shepherdSkill
- shipSkill
- smithSkill
- sonarcloud-analysisSkill
- sonarcloudSkill
- statusSkill
- triage-readySkill
- using-forgeSkill
- validateSkill
- verifySkill
- worktreeSkill
- claim-safetySkill
- devSkill
- gatesSkill
- hermes-forgeSkill
- issue-basicsSkill
- kernelSkill
- memorySkill
- planSkill
- portabilitySkill
- researchSkill
- reviewSkill
- rollbackSkill
- setupSkill
- shepherdSkill
- shipSkill
- smithSkill
- sonarcloud-analysisSkill
- sonarcloudSkill
- statusSkill
- triage-readySkill
- using-forgeSkill
- validateSkill
- verifySkill
- worktreeSkill
The file
Files
Parallel Deep Research
Comprehensive research reports with multi-source synthesis. Use pro (3-9 min, $0.10) or ultra (5-25 min, $0.30) for deep analysis.
Safety: The
inputis transmitted to Parallel AI's external service and may be logged or retained. Never include secrets, API keys/tokens, PII, or private/proprietary repo content — send only information safe to share with a third party.CLI alternative (recommended): Install
parallel-clifor official skill:npx skills add parallel-web/parallel-agent-skills --skill parallel-deep-research
Setup
API_KEY=$(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: {"run_id": "trun_abc123...", "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"
fiProcessors
| 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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

