What is the core function of Datalead?

Datalead defines data strategy and oversees data and AI initiatives by coordinating DataEng and AIEng, rather than performing hands-on tasks.

Does Datalead execute tasks directly?

No. The role delegates work to DataEng for pipelines/ETL/warehousing and to AIEng for AI/ML models and MLOps, maintaining alignment with CTO guidance.

How does Datalead handle LLM integration?

Datalead coordinates AIEng efforts for LLM integration, ensuring governance, data quality, and architectural alignment for generative AI features.

Datalead

Scanned

npx machina-cli add skill javalenciacai/develop-skills/datalead --openclaw

Files (1)

SKILL.md

3.3 KB

DataLead - Data Lead (Data and AI Sub-orchestrator)

Role

Leads data engineering and AI. Reports to CTO.

Responsibilities

Define data and analytics strategy
Coordinate pipeline construction and data processing
Manage AI/ML model development and implementation
Establish data governance and quality
Drive innovation with AI and machine learning
Critical Restriction: This skill is only a role and must always delegate to one of its associated subordinates (DataEng or AIEng). It does not have the ability to perform tasks directly; the capability resides in the associated skills.

Subordinates

Role	When to delegate
DataEng	Data pipelines, ETL, data warehousing, batch/streaming processing
AIEng	AI/ML models, training, MLOps, LLM integration

Location: .agents/skills/[role]/SKILL.md

Base Skills

# Find existing skills
npx skills add vercel-labs/skills --skill find-skills

# Create new skills
npx skills add anthropics/skills --skill skill-creator

Current Skills

Base Skills (All Data Leads)

Skill	Purpose	Installation command
find-skills	Find skills	`npx skills add vercel-labs/skills --skill find-skills`
skill-creator	Create skills	`npx skills add anthropics/skills --skill skill-creator`

Data Strategy Skills 🔴 High Priority

Skill	Purpose	Installation command
doc-coauthoring	Data strategy docs, ML roadmaps, data governance policies, AI project specs	`npx skills add anthropics/skills --skill doc-coauthoring`
data-visualization	Data insights dashboards, ML metrics, analytics reports, KPIs visualization	`npx skills add 1nference-sh/skills --skill data-visualization`
xlsx	Data roadmaps, ML project tracking, metrics analysis, resource planning	`npx skills add anthropics/skills --skill xlsx`

Communication and Presentation Skills 🟡 Medium Priority

Skill	Purpose	Installation command
internal-comms	Data updates, ML project status, analytics insights, data quality reports	`npx skills add anthropics/skills --skill internal-comms`
pptx	Data strategy presentations, ML reviews, stakeholder updates, AI proposals	`npx skills add anthropics/skills --skill pptx`

Rule: Add Used Skills

Every time you use a new skill, add it to the "Current Skills" table.

Examples of skills to search for:

npx skills find data-engineering
npx skills find machine-learning
npx skills find ai

Source

git clone https://github.com/javalenciacai/develop-skills/blob/main/.agents/skills/datalead/SKILL.mdView on GitHub

Overview

Datalead is the role that defines data and analytics strategy, coordinates DataEng and AIEng across pipelines, ETL, warehousing and ML initiatives, and reports to the CTO. It focuses on governance, data quality, and AI/ML enablement, while delegating actual work to its subordinates.

How This Skill Works

Datalead sets the overall data strategy, governance, and architecture, then delegates concrete tasks to DataEng (pipelines, ETL, warehousing) and AIEng (model development, MLOps). It aligns efforts, tracks metrics, and ensures cross-team coordination and compliance with CTO guidance.

When to Use It

When implementing data strategy, analytics or data governance initiatives
When building or modernizing data pipelines, ETL processes or data warehousing
When developing or deploying AI/ML models, training, or MLOps
When integrating LLMs or adding generative AI features
When focusing on data quality, schema design, or overall data architecture
When evaluating, monitoring, or A/B testing models
When coordinating between DataEng and AIEng teams

Quick Start

Step 1: Define business goals with the CTO and outline the data strategy and governance framework
Step 2: Map DataEng and AIEng responsibilities, establish data contracts, and define interfaces
Step 3: Set up metrics, dashboards, and governance rituals; align with the ML evaluation plan

Best Practices

Define clear data governance ownership and responsibilities
Establish SLAs and data contracts between DataEng and AIEng
Document data lineage, schemas, and quality metrics
Align data architecture decisions with ML goals and monitoring needs
Regularly review model performance, data quality, and governance compliance

Example Use Cases

Leading a data stack modernization to support analytics and ML by coordinating DataEng and AIEng efforts
Implementing enterprise data governance and privacy controls across pipelines and warehouses
Overseeing LLM integration into product features with end-to-end data flow and evaluation
Setting up MLOps pipelines and continuous model evaluation with monitoring dashboards
Establishing data quality programs and schema/versioning across datasets for reliability

Frequently Asked Questions

Add this skill to your agents