opensearch-project

Evaluate, benchmark, and improve an AI agent with the Agent Health CLI and server APIs. Use when the user wants to run evaluations/benchmarks, interpret judge results (matcherResults / improvementStrategies), diagnose eval-vs-reality gaps, or raise an agent's…

Use when instrumenting an application with OpenTelemetry for Agent Health. Provides span structure, required attributes, and config setup for routing traces.

Use when instrumenting an application with OpenTelemetry for Agent Health. Provides span structure, required attributes, and config setup for routing traces.

Add OpenTelemetry instrumentation to an AI agent for Agent Health observability. Use when a user wants to make their agent's traces visible in Agent Health dashboards, or when debugging why traces aren't appearing. Covers span structure, Gen AI semantic…

Use when the user wants to profile or improve the agent/codebase based on the current session. Profiles this session's traces against a chosen evaluator and proposes concrete edits.

Use when adding, modifying, or debugging agent connectors. Provides connector architecture, built-in types, and custom connector template.

Use when working on config loading, authentication, AWS profiles, or data source resolution. Explains the two config systems (TS vs JSON), auth priority, and multi-profile setup.

Create a pull request for Agent Health following all compliance requirements. Use after implementing a feature or fix. Handles SPDX headers, DCO signoff, CHANGELOG, and the PR template.

Deploy OpenSearch search applications to Aiven for OpenSearch (a fully managed OpenSearch service across AWS, GCP, Azure, DigitalOcean, and UpCloud). Use this skill when the user wants to provision an Aiven OpenSearch service, deploy a search configuration to…

Deploy OpenSearch search applications to managed cloud providers. Use this skill when the user wants to provision an OpenSearch domain or serverless collection on AWS, provision a managed OpenSearch service on Aiven, deploy search configurations, set up…

Build search applications and query log analytics data with OpenSearch. Use this skill when the user mentions OpenSearch, search app, index setup, search architecture, semantic search, vector search, hybrid search, BM25, dense vector, sparse vector, agentic…

Process unstructured documents (PDF, DOCX, PPTX, XLSX) into search-ready JSONL chunks using Docling. Runs locally — no AWS or cloud services needed. Use this skill when the user wants to prepare documents for indexing, chunk documents, evaluate chunk quality,…

Process unstructured documents into search-ready chunks. Use this skill when the user wants to process PDFs or unstructured documents into JSONL chunks using Docling. Activate even if the user says document processing, chunking, Docling, PDF processing, or…

Build search applications with OpenSearch from scratch. Use this skill when the user mentions search app, index setup, search architecture, semantic search, vector search, hybrid search, BM25, dense vector, sparse vector, agentic search, RAG, embeddings, KNN,…

Build search applications with OpenSearch. Use this skill when the user mentions search app, index setup, search architecture, semantic search, vector search, hybrid search, BM25, dense vector, sparse vector, agentic search, RAG, embeddings, KNN, PDF…

Deploy OpenSearch search applications to Amazon OpenSearch Service or Amazon OpenSearch Serverless. Use this skill when the user wants to provision an OpenSearch domain or serverless collection on AWS, deploy search configurations to AWS, set up Bedrock…

APM RED metrics (Rate, Errors, Duration) for service-level monitoring using PromQL and PPL queries.

Cross-signal correlation between traces, logs, and metrics using OTel semantic convention fields for end-to-end observability investigations.

Query and search log data from OpenSearch using PPL for severity filtering, trace correlation, error patterns, and log volume analysis.

Query metrics from Prometheus using PromQL for HTTP request rates, latency percentiles, error rates, active connections, and GenAI token usage.

Query OpenSearch Dashboards APIs for workspace configuration, index pattern discovery, APM correlation configs, and saved objects.

Comprehensive PPL (Piped Processing Language) reference for OpenSearch with command syntax, functions, and examples for observability queries.

SLO/SLI definitions, Prometheus recording rules, error budget calculations, and burn rate alerting for service reliability management.

Check observability stack component health, verify data ingestion, and troubleshoot common issues.

Generate a concise PR description from code changes, following the repo's PR template

Automatically resolve CVEs by checking GitHub issues, verifying presence in codebase, and attempting various remediation strategies while documenting the process.

Run Jest unit tests for files changed in the current branch

Automatically retry failed required CI checks on GitHub PRs, with smart waiting and filtering logic

Use when the user asks to write, generate, fix, explain, or validate a PPL query, or mentions PPL, Piped Processing Language, observability queries, or OpenSearch log/trace/span queries.

Benchmark the Seismic index in this repo — the fixed protocol (MS MARCO base_full.csr, lambda=6000/beta=400/alpha=0.4, cut=3/heap_factor=1.0, single-thread query) plus how to obtain the dataset, which harness to run (query_latency_bench, nsparse_benchmark,…

Guides users through migrating OpenSearch Dashboards saved objects (dashboards, visualizations, index patterns) between instances using the osd-migrate CLI tool.