Deep web research, competitive intelligence, entity discovery, and data enrichment using Parallel AI's specialized APIs.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionparallel-researchExecute the skills CLI command in your project's root directory to begin installation:
Fetches parallel-research from casper-studios/casper-marketplace and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate parallel-research. Access via /parallel-research in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
10
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
10
stars
Deep web research, competitive intelligence, entity discovery, and data enrichment using Parallel AI's specialized APIs.
What do you need?
│
├── Quick factual answer (3-5 seconds)
│ └── Chat API ($0.005/request)
│ └── Script: scripts/parallel_research.py chat "question"
│
├── Comprehensive research report (5min-2hr)
│ └── Deep Research API ($0.30/report for ultra)
│ └── Script: scripts/parallel_research.py research "topic"
│
├── Find entities matching criteria (companies, people)
│ └── FindAll API ($0.03 + $0.10/match)
│ └── Script: scripts/parallel_research.py findall "query"
│
└── Enrich existing data (add fields to records)
└── Task API with schema ($0.025/record for core)
└── Script: scripts/parallel_research.py enrich data.csv
# Required in .env
PARALLEL_API_KEY=your_api_key_here
Get your API key: https://platform.parallel.ai/settings/api-keys
python scripts/parallel_research.py chat "What is Anthropic's latest funding round?"
python scripts/parallel_research.py research "Competitive landscape of AI code editors in 2025" --processor ultra
python scripts/parallel_research.py findall "AI code editor companies that raised funding in 2024-2025" --limit 50
python scripts/basic_research.py "Company Name"
python scripts/vendor_selection.py "CRM software" --requirements "enterprise,API,automation"
| Processor | Cost/1K | Latency | Best For |
|---|---|---|---|
lite |
$5 | 10-60s | Basic metadata |
base |
$10 | 15-100s | Simple research |
core |
$25 | 1-5min | Cross-referenced research |
pro |
$100 | 2-10min | Exploratory research |
ultra |
$300 | 5-25min | Deep research (recommended) |
ultra-fast |
$300 | 2-10min | Speed + quality |
| Task | API | Cost |
|---|---|---|
| 100 quick questions | Chat | $0.50 |
| Market research report | Deep Research (ultra) | $0.30 |
| Find 50 competitors | FindAll (core) | ~$5.00 |
| Enrich 100 leads | Task (core) | $2.50 |
20,000 requests free (combined across all APIs).
PARALLEL_API_KEY in .env file (never commit to git).tmp/ directorySymptoms: Request times out or returns partial results Cause: Complex query requiring more processing time than allowed Solution:
lite or base instead of ultra)Symptoms: "Insufficient credits" or quota error Cause: Account credits depleted Solution:
Symptoms: JSON parsing error or unexpected response structure Cause: API returned error or malformed response Solution:
Symptoms: Research returns no results or off-topic content Cause: Query too narrow, ambiguous, or poorly structured Solution:
Symptoms: "Invalid API key" or 401 error Cause: API key expired, invalid, or not set Solution:
PARALLEL_API_KEY is set correctly in .envSymptoms: 429 error or "rate limit exceeded" Cause: Too many concurrent requests Solution:
Skills: parallel-research → content-generation Use case: Create polished reports from research findings Flow:
Skills: parallel-research → attio-crm Use case: Populate CRM with discovered companies Flow:
Skills: parallel-research → google-workspace Use case: Build research database in Google Sheets Flow:
Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
jezweb/claude-skills
Solid pick for teams standardizing on skills: parallel-research is focused, and the summary matches what you get after install.
We added parallel-research from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Useful defaults in parallel-research — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
parallel-research is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
We added parallel-research from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Solid pick for teams standardizing on skills: parallel-research is focused, and the summary matches what you get after install.
Keeps context tight: parallel-research is the kind of skill you can hand to a new teammate without a long onboarding doc.
parallel-research fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
parallel-research has been reliable in day-to-day use. Documentation quality is above average for community skills.
Useful defaults in parallel-research — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
showing 1-10 of 39