Data Wiki turns data into portable knowledge bundles following Open Knowledge Format (OKF) and serves them to AI agents over the Model Context Protocol (MCP).
aws-samples/sample-okf-llm-wiki is a sample system that turns AWS data sources into portable knowledge bundles: organized Markdown documents explaining datasets, tables, relationships, metrics, and known issues. It serves those bundles to AI agents through the Model Context Protocol, using sources such as AWS Glue Data Catalog and Amazon Redshift. The catalogue entries support the system's setup and workflow.
This repository also configures its own agents. See what sample-okf-llm-wiki tells them →
aws-samples/sample-okf-llm-wiki
Skill Claude CodeCodex ✓ vendor
The report-authoring methodology: required structure, language, evidence discipline, and figure selection. Read BEFORE your first createreport of a conversation - the tool validates shape; this is everything it cannot check.
aws-samples/sample-okf-llm-wiki
Skill Claude CodeCodex ✓ vendor
Author Open Knowledge Format (OKF) bundles — knowledge represented as a directory of markdown files with YAML frontmatter. Use when asked to create, write, generate, enrich, or validate an OKF bundle or OKF concept docs; to turn a data source (Glue database, API, database, catalog), documentation, or a research topic…
aws-samples/sample-okf-llm-wiki
Skill Claude CodeCodex ✓ vendor
How to author an analysis worth reusing: document shape, question design, the computation-first sourcing ladder, and step discipline. Read BEFORE your first createanalysis or updateanalysis of a conversation.
aws-samples/sample-okf-llm-wiki
Skill Claude CodeCodex ✓ vendor
How to execute a saved analysis: resolve-then-ask for its questions, follow the steps as written, honor the sourcing ladder, and finalize per the document. Read BEFORE running your first analysis of a conversation.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: