Semantic Layer

Semantic Layer is a Data skill for Claude Code, published by Kaelio in ktx.

1.5K stars99 forkson Kaelio/ktxAdded 2026/08/19+1% in starsRepository updated 2026/07/19

agentagent-skillsagentsai-agentai-agentsanalyticsanalytics-engineeringbusiness-intelligenceclaudeclaude-codeclaude-skillscodexcontext-layerdata-analysisdata-engineeringllmmcpmemorysemantic-layerskills

Install in seconds

Install Semantic Layer

Copy Semantic Layer into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/Kaelio/ktx/tree/main/packages/cli/src/skills/sl ~/.claude/skills/sl

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Kaelio/ktx.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: packages/cli/src/skills/sl/SKILL.md in Kaelio/ktx
Installs to: ~/.claude/skills/sl
Collection: One of 17 skills cataloged from this repository
Category: Data — 668 skills

What Semantic Layer does

Semantic Layer provides a structured YAML catalog of sources, measures, joins, and segments for querying predefined business metrics like ARR, churn, retention, LTV, and MAU. Use it to read SL source YAML or query metrics via sl_query.

Semantic Layer is cataloged under Data on DirSkills. Semantic Layer comes from a repository tagged agent, agent-skills, agents, ai-agent and ai-agents.

Documentation

README

Excerpt

Semantic Layer

ktx's semantic layer (SL) is a structured catalog. Each source represents a table, a SQL view, or an overlay that enriches a manifest-backed table with measures, computed columns, joins, and named segments. The catalog is the single source of truth for reusable business metrics.

This skill covers two parts:

Part 1 - Schema reference (what an SL source looks like).
Part 2 - Querying via sl_query.

Capture (when and how to add new patterns to the SL) is a separate concern handled by the memory-agent - see the sl_capture skill if you are running in capture mode. The research agent reads and queries the SL via the tools described here; it does not write to it.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Semantic Layer

What else does Kaelio publish alongside Semantic Layer?
Semantic Layer is one of 17 skills that DirSkills catalogs from Kaelio/ktx, the repository it ships in. Its siblings there include Google Drive Doc Synthesis, Historic SQL Patterns and Historic SQL Table Digest. Each one is a separate skill with its own page in this directory, installs the same way Semantic Layer does, and is maintained by Kaelio in that same repository. The rest of the collection is listed on the Kaelio/ktx page.
How does Semantic Layer compare to other Data skills?
Semantic Layer ranks #383 by stars among the 668 Data skills in this catalog. The most-starred ones next to it are Benchmark Methodology, Jupyter Notebook and Solana. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Semantic Layer against them. Open each page to compare what they document and how they install.