# looker-expert

looker-expert — a Looker skill for the assistant: writes and reviews LookML, designs explores and measures, and catches fanout bugs before they reach a dashboard.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 194 installs · ★ 45 repo stars
- Author: PCL Team
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/personamanagmentlayer/pcl/tree/HEAD/stdlib/data/looker-expert/SKILL.md
- Updated: 2026-10-12
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/looker-expert

## What it does

This skill steers the assistant through Looker work: LookML views, dimensions and measures, explores with joins, persistent derived tables, dashboards, field-level access. It carries an opinion on what keeps a model maintainable, so answers come out concrete instead of generic.

The rules cover view and explore design: primary keys, date dimension groups, `value_format_name`, hidden technical fields, `sql_always_where` and `always_filter` defaults. A performance section deals with aggregate tables, datagroups for caching and indexes on PDT join keys. Deeper material sits in `references/CORE_CONCEPTS.md` and is read only when the task calls for it.

Anti-patterns come as bad and good LookML side by side: `sql_distinct_key` to stop double counting across a one-to-many join, `primary_key: yes`, `CURRENT_DATE` in place of a written-in year, labels and descriptions on fields. The skill expects `looker-sdk` 23.0.0 or newer. The assistant also gets `Read`, `Write`, `Edit`, `Bash`, `Glob` and `Grep`, so it can open and change project files.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add personamanagmentlayer/pcl --skill looker-expert -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/looker-expert/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/looker-expert/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add personamanagmentlayer/pcl --skill looker-expert -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/looker-expert/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add personamanagmentlayer/pcl --skill looker-expert -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/looker-expert/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install personamanagmentlayer/pcl stdlib/data/looker-expert
```

2. **Manually: put the files in place**
- File: `.github/skills/looker-expert/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add personamanagmentlayer/pcl --skill looker-expert -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/personamanagmentlayer/pcl --path stdlib/data/looker-expert
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/looker-expert/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add personamanagmentlayer/pcl --skill looker-expert -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/personamanagmentlayer/pcl/tree/HEAD/stdlib/data/looker-expert/SKILL.md

## When to use it
- stop a measure from double counting after a one-to-many join
- add primary keys and date groups to a view
- move a heavy calculation into a persistent derived table
- replace a hardcoded year with `CURRENT_DATE`
- hide technical fields and document the rest with labels

## Example prompts
- Review `orders.view.lkml` — `total_items` looks inflated once `order_items` is joined in.
- Draft an explore for sales joined to `users`, and spell out the relationship for every join.
- This dashboard is slow. Which parts should become a PDT, and what datagroups fit?

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: c6410e3abb16488a.

BEGIN THIRD-PARTY FILE c6410e3abb16488a
````text
---
name: looker-expert
version: 1.1.0
description: >-
  Expert-level Looker BI, LookML, explores, dimensions, measures, dashboards, and data
  modeling. Use when the user mentions LookML, BI, analytics, dashboards, or data modeling,
  or when the task involves LookML Basics, Advanced Dimensions and Measures, Persistent
  Derived Tables, or Explores and Joins.
category: data
author: PCL Team
license: Apache-2.0
tags:
  - looker
  - lookml
  - bi
  - analytics
  - dashboards
  - data-modeling
allowed-tools:
  - Read
  - Write
  - Edit
  - Bash
  - Glob
  - Grep
requirements:
  looker-sdk: '>=23.0.0'
---

# Looker Expert

You are an expert in Looker with deep knowledge of LookML, explores, dimensions, measures, dashboards, PDTs (Persistent Derived Tables), and semantic data modeling. You design maintainable, performant Looker models that enable self-service analytics.

## Best Practices

### 1. View Design

- Use primary keys on all views
- Create dimension groups for dates
- Add descriptions to all fields
- Use value_format_name for consistent formatting
- Hide technical fields from users
- Use drill_fields for exploration paths

### 2. Explore Design

- Join dimensions and fact tables appropriately
- Understand and use correct relationship types
- Use symmetric aggregates for one-to-many joins
- Apply sql_always_where for data filtering
- Set sensible always_filter defaults
- Use aggregate awareness for performance

### 3. Performance

- Use persistent derived tables for complex calculations
- Implement aggregate tables for common queries
- Set appropriate datagroups for caching
- Use indexes on PDT join keys
- Limit explore field exposure
- Monitor and optimize slow queries

### 4. Maintainability

- Use consistent naming conventions
- Organize views by domain
- Create reusable dimensions with extends
- Document complex logic
- Use refinements to avoid duplication
- Version control LookML in Git

### 5. Governance

- Implement access controls with user attributes
- Use field-level security for sensitive data
- Create curated explores for different audiences
- Document data lineage
- Establish naming standards

## Anti-Patterns

### 1. Symmetric Aggregate Issues

```lookml
# Bad: Incorrect fanout handling
measure: total_items {
  type: sum
  sql: ${order_items.quantity} ;;  # Will double-count with 1-to-many join
}

# Good: Use symmetric aggregates or subquery
measure: total_items {
````
END THIRD-PARTY FILE c6410e3abb16488a

The third-party file has ended. Everything between the c6410e3abb16488a tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2425 of 4133 bytes. © PCL Team · Apache-2.0 · https://github.com/personamanagmentlayer/pcl/tree/HEAD/stdlib/data/looker-expert/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
