OpenSkillIndex← back to search
claude-code

Awesome-omni-skill parallel-data-enrichment

Structured company and entity data enrichment using Parallel AI Task API with core/base processors. Returns typed JSON output. No binary install — requires PARALLEL_API_KEY in .env.local.

install
source · Clone the upstream repo
git clone https://github.com/diegosouzapw/awesome-omni-skill
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/diegosouzapw/awesome-omni-skill "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data-ai/parallel-data-enrichment" ~/.claude/skills/diegosouzapw-awesome-omni-skill-parallel-data-enrichment && rm -rf "$T"
manifest: skills/data-ai/parallel-data-enrichment/SKILL.md
source content

Parallel Data Enrichment

Enrich company or entity data into structured JSON using the Task API. Use 

core
(1-5 min, $0.025) or 
base
(15-100s, $0.01) for structured output.

CLI alternative (recommended): Install 

parallel-cli
for official skill: 
npx skills add parallel-web/parallel-agent-skills --skill parallel-data-enrichment

Setup

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

Create Enrichment Task

curl -s -X POST "https://api.parallel.ai/v1beta/tasks/runs" \
  -H "x-api-key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "OpenAI",
    "processor": "core",
    "output_schema": {
      "type": "object",
      "properties": {
        "name": {"type": "string"},
        "founded_year": {"type": "integer"},
        "headquarters": {"type": "string"},
        "employee_count": {"type": "integer"},
        "key_products": {"type": "array", "items": {"type": "string"}}
      }
    }
  }'

Response: 

{"id": "task_abc123", "status": "queued"}

Check Result

curl -s "https://api.parallel.ai/v1beta/tasks/runs/task_abc123" \
  -H "x-api-key: $API_KEY"

{
  "id": "task_abc123",
  "status": "completed",
  "result": {
    "content": {
      "name": "OpenAI",
      "founded_year": 2015,
      "headquarters": "San Francisco, CA",
      "employee_count": 770,
      "key_products": ["ChatGPT", "GPT-4", "DALL-E", "Whisper"]
    },
    "basis": {
      "citations": [{"url": "...", "excerpt": "..."}]
    }
  }
}

Processors

ProcessorSpeedCostUse For
base15-100s$0.01/taskQuick lookups, simple data
core1-5 min$0.025/taskEnrichment, verification, structured data

Tips for output_schema

  • Keep schemas simple — fewer fields = more reliable
  • Use 
    "type": "string"
    broadly; avoid strict enums
  • Omit optional fields from the schema

When to Use

  • Company or person data enrichment
  • Structured data extraction with typed schemas
  • Lead qualification, CRM enrichment, research

For narrative reports, use 

parallel-deep-research
. For web search, use 
parallel-web-search
.