Relevant jobs
AI / Algorithm Engineer
Full-stack / Indie Developer
Backend Engineer
Data Analyst / Data Engineer
ktxKaelio/ktx
Turns the data warehouse semantic layer (table schemas, metric definitions, business definitions)…
No ratings yet
Rate this skill
Stars1.6k
Forks107
Watchers1.6k
Open Issues52
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/Kaelio/ktx.git
OverviewOverview
Key Features
Turns the data warehouse semantic layer (table schemas, metric definitions, business definitions) into context that AI agents can read directly, so the SQL and analysis they produce are grounded in real definitions. Key capabilities include: 1. Semantic layer context injection: organizes data models, metric definitions and business definitions into an agent-loadable context layer, so the agent reads definitions before generating queries and avoids misusing fields or miscalculating metrics; 2. SQL generation and validation: generates SQL under semantic-layer constraints and validates syntax and definitions before execution, reducing wrong-table and wrong-metric errors; 3. Agent memory persistence: writes confirmed definitions, query patterns and conclusions from analysis sessions into a reusable memory layer, so later sessions reuse them instead of re-explaining business context; 4. MCP tool integration: exposes semantic-layer and query capabilities to agent clients such as Claude Code and Codex via the MCP protocol, so agents can call data capabilities like local tools; 5. Analytics engineering packaging: packages data modeling, metric maintenance and analysis scripts into version-managed skill bundles, so teams share one set of definitions and workflows.
Use Cases
When data analysts ask AI agents to write SQL according to company metric definitions; when data engineering teams maintain the semantic layer and metric definitions; when agents need to remember business definitions across sessions; when connecting data warehouse capabilities into agent toolchains such as Claude Code.
Target Roles
Data Analyst / Data Engineer, AI / Algorithm Engineer, Backend Developer, Full-stack / Indie Developer.
TopicsTopics
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 831 |
|---|---|
| Data source | GitHub |
| Repository | Kaelio/ktx |
| Category | AI & Agent Skills / Data Analytics & Semantic Layer Agent |
| Primary language | TypeScript |
| License | Apache License 2.0 |
| Default branch | main |
| GitHub repository ID | 1234904564 |
| Node ID | R_kgDOSZsl9A |
| Rank | #457 (position within the source ranking) |
| Site-wide popularity rank | #600 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
Still collecting
First record taken on 2026-09-21. Two days of data are needed before a trend line can be drawn.
TimelineTimeline
Repository created2026-05-10 19:42:326 months ago
Data last updated2026-10-26 11:59:2722 days ago
Last commit2026-09-11 04:03:452 months ago
CommitLatest commit
Version [0.16.0] committed by andreybavt. Update Category: Bug Fixes & Stability Improvements. Commit details: fix(ci): repair slow sl test and sync uv.lock to 0.16.0 (#345). This update resolves known runtime errors and enhances system reliability.