Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →microsoftdocs/azure-horizondb
Expert knowledge for Azure Horizondb development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment.
5 of 22 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 5 comparable cases; this report requires 8.
This benchmark measured an earlier version of the skill.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
After performing a vector similarity search in Azure HorizonDB, we want to perform semantic reranking on the top 20 candidate rows before returning results to an LLM context window. What azure_ai SQL function performs semantic reranking?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies azure_ai.rank as the semantic reranking function in Azure HorizonDB. | Missed | Passed |
| Passes query text with candidate documents into azure_ai.rank within the SELECT list. | Missed | Passed |
The instructions your model reads when the skill loads.
This skill provides expert guidance for Azure Horizondb. Covers troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.
IMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g.,
L35-L120), useread_filewith the specified lines. For categories with file links (e.g.,[security.md](security.md)), useread_fileon the linked reference file
IMPORTANT for Agent: If
metadata.generated_atis more than 3 months old, suggest the user pull the latest version from the repository. Ifmcp_microsoftdocstools are not available, suggest the user install it: Installation Guide
This skill requires network access to fetch documentation content:
mcp_microsoftdocs:microsoft_docs_fetch with query string from=learn-agent-skill. Returns Markdown.fetch_webpage with query string from=learn-agent-skill&accept=text/markdown. Returns Markdown.| Category | Lines | Description |
|---|---|---|
| Troubleshooting | L37-L44 | Diagnosing and fixing HorizonDB issues: extension management errors, TLS/cert rotation failures, autovacuum tuning, and transaction ID wraparound prevention. |
| Best Practices | L45-L55 | Performance and operations guidance for HorizonDB: data prep for AI, pgvector tuning, partitioning, extensions, Apache AGE, Query Store, and cluster maintenance best practices. |
| Decision Making | L56-L61 | Guidance on choosing between vector, full-text, and hybrid search in HorizonDB, and selecting the optimal vector index type for your data, queries, and performance needs. |
| Architecture & Design Patterns | L62-L66 | Patterns for building RAG with graph data in HorizonDB and implementing hybrid BM25+vector search, including design choices and query strategies. |
| Limits & Quotas | L67-L72 | Managing HorizonDB replica counts, read-scale limits, and how to request quota or limit increases for HorizonDB resources. |
| Security | L73-L88 | Securing HorizonDB: TLS/SSL setup, cert management, SCRAM auth, access control/roles, user accounts, encryption at rest, deletion protection, password resets, and security best practices. |
| Configuration | L89-L165 | Configuring HorizonDB clusters: AI models/pipelines, search/vector indexing, extensions, networking/firewalls, HA/replication, autovacuum, connections, logging, WAL, and detailed PostgreSQL parameter tuning. |
| Integrations & Coding Patterns | L166-L178 | Using HorizonDB with AI: azure_ai SQL/embedding/rerank functions, LangChain vector store, building knowledge graphs, and integrating/moving data via the Azure Storage extension. |
| Deployment | L179-L182 | Guides for migrating data by dumping PostgreSQL databases and restoring them into HorizonDB, including required tools, commands, and compatibility considerations. |
| Topic | URL |
|---|---|
| Resolve common HorizonDB extension management errors | https://learn.microsoft.com/en-us/azure/horizondb/extensions/errors-extensions |
| Troubleshoot TLS connection failures after HorizonDB cert rotation | https://learn.microsoft.com/en-us/azure/horizondb/security/security-tls-troubleshoot |
| Monitor and tune autovacuum in Azure HorizonDB | https://learn.microsoft.com/en-us/azure/horizondb/troubleshoot/how-to-autovacuum-monitor-tune |
| Prevent and resolve transaction ID wraparound in HorizonDB | https://learn.microsoft.com/en-us/azure/horizondb/troubleshoot/how-to-prevent-resolve-wraparound |
| Topic | URL |
|---|---|
| Prepare data in HorizonDB for AI apps and agents | https://learn.microsoft.com/en-us/azure/horizondb/ai/ai-data-preparation |
test cases passed with the skill
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.