skills.rest
Postergully
PostergullyCOMMUNITY
Explore all skills by this author →
GitHub

data-research

Automate structured data research from emails, web sources, and APIs.

Updated May 4, 2026
Search Tags:#research#email#deduplication#web#data-extraction#structured-data#tracker
One-click install
npx skills add https://github.com/Postergully/11mirror-plugin --skill data-research-postergully
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-research
Source: https://github.com/Postergully/11mirror-plugin/tree/main/skills/data-research
Command: npx skills add https://github.com/Postergully/11mirror-plugin --skill data-research-postergully

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Structured data research from emails, web sources, and APIs can be time-consuming and error-prone; this skill automates the end-to-end process to collect, normalize, and track data.

Core Features & Use Cases

  • Phase-driven extraction: search sources, classify, extract structured data, archive raw sources, deduplicate results, and update canonical trackers.
  • Reusable recipes: investor-updates, expense-tracker, company-updates with customizable schemas.
  • Traceable outputs: links back to raw sources and running tracker pages.

Quick Start

Set up a new data-tracking recipe and start the seven-phase pipeline to search, extract, archive, deduplicate, and update canonical trackers from your sources.

Frequently Asked Questions about data-research

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate structured data extraction from emails and web sources?▼

Automate structured data extraction by running a configurable, seven-phase pipeline that searches sources, classifies content, extracts structured data, archives raw inputs, deduplicates results, and updates canonical trackers.

What is the best way to track investor updates and company metrics without manual data entry?▼

Tracking investor updates and company metrics is handled through reusable recipes that normalize collected data, maintain running trackers, and generate backlinks to archived raw sources.

How does data deduplication work when collecting research from multiple sources?▼

Data deduplication operates as a dedicated phase in the research pipeline, processing extracted structured data to identify and remove duplicate entries before updating the canonical tracker.

Can I customize the data schema for different tracking workflows like expense tracking?▼

Customizable schemas are supported across reusable recipes, allowing you to configure specific data extraction and classification rules for workflows like expense tracking, investor updates, and company metrics.

How do I trace extracted data back to its original email or web source?▼

Trace extracted data back to its original source using the pipeline's archiving and backlinking features, which maintain direct links from canonical tracker entries to raw emails and web sources.

Do I need to install any dependencies to run the data research pipeline?▼

No external dependencies are required to run the data research pipeline, as the skill operates independently to execute its search, extraction, deduplication, and tracker maintenance phases.

Related Skills

Explore More Data & Analytics Skills→
angryracoonangryracoon

data360-prepare

Prepare Salesforce Data Cloud ingestion assets for raw source data.

Community
Advanced
SJTU-IPADSSJTU-IPADS
7

data-analyst-cn

Clean datasets and generate statistics, correlations, and visualization templates.

Official
Intermediate
ltdrewltdrew
1

data-research

Gather sources and extract fields into canonical tracker pages.

Community
Advanced
GYF0311GYF0311
5

data-research

Generate structured, deduplicated tracker data from research inputs with provenance.

Community
Advanced