Dashboard analysis and editing workflow and rules for using dashboard JSON, filters, variables, and time ranges. Load when the user provides dashboard context (for example a dashboard link) or asks to create or change a dashboard.
1418d agoReviewMountCreate a free account to mount
DataPrime query language for logs/spans/custom datasets (shared syntax, patterns, and rules). Load when you need to write a DataPrime query to explore logs or spans. Also load in case the user asks for help with a DataPrime query or its generation.
1418d agoReviewMountCreate a free account to mount
Dataset discovery and source-selection guidance for DataPrime system and user-defined datasets. Load when the user asks what datasets exist, how to use `list_datasets`, how to query `system/...` or `default/...` sources, or how to inspect a specific system dataset after discovery. The `coralogix-dataprime` skill should be loaded alongside this skill.
1418d agoReviewMountCreate a free account to mount
Data usage, billing units, plan consumption, quota metrics, anomaly detection, and time-series analysis concepts and query workflow. Load when the user asks about data usage, ingestion volumes, billing, plan limits, overage, quota attribution, usage anomalies, or usage trends over time.
1418d agoReviewMountCreate a free account to mount
Search and read official Coralogix platform documentation using **`search_docs`** and **`fetch_doc`**. Use when the user asks how Coralogix features work, how to configure or use the UI, set up integrations (OpenTelemetry, agents, collectors, webhooks), manage API keys, explore spans/traces/logs in the product, configure alerts/SLOs/dashboards, or needs authoritative product docs — not live tenant telemetry.
1418d agoReviewMountCreate a free account to mount
Find and inspect infrastructure resources: monitored resource types, resource inventory, health history, raw source data, and configuration changes. Load when the user asks to "show resource types", "list infrastructure resources", "what resources of this kind are monitored", "is this resource healthy", "resource health history", "when did this resource go critical", "get raw resource data", "what changed on this host", "which resources changed configuration", "infrastructure inventory", "find resources by name", "filter resources by service or environment", or wants to explore infrastructure resources and their data.
1418d agoReviewMountCreate a free account to mount
Log-specific concepts, fields, field discovery usage, and troubleshooting patterns. The `coralogix-dataprime` skill should be loaded alongside this skill. Load when you need to explore logs in your investigation or to answer a question about logs.
1418d agoReviewMountCreate a free account to mount
PromQL fundamentals and metric discovery/query workflow. Load when you need to explore metrics in your investigation or to answer a question about metrics. For service-level RED metrics (error rate, latency percentiles, throughput) or pod/JVM resource saturation, load the `coralogix-service-catalog` skill instead — it is a pre-aggregated path for that data; this skill is for custom, infrastructure, and hand-written PromQL work.
1418d agoReviewMountCreate a free account to mount
- Use when the user wants to investigate or analyze data in Coralogix, or explicitly asks to use Olly. Examples: "ask Olly", "why is my service slow", "what alerts fired", "investigate this incident", "analyze errors", "explain this spike".
1418d agoReviewMountCreate a free account to mount
Use when the user asks to "query RUM", "cx_rum", "real user monitoring", "frontend errors", "browser errors", "mobile app crashes", "Web Vitals", "slow page load", "LCP", "CLS", "browser network failures", "user clicks", "session replay", "RUM SDK", "install RUM", "source maps for RUM", or wants to query Coralogix RUM telemetry using query_dataprime with `source rum.events`, DataPrime, and flat `$d.*` fields (field catalog is in Key Fields below), or needs official RUM SDK docs (read_rum_sdk_docs).
1418d agoReviewMountCreate a free account to mount
The fast, authoritative path for APM/RED data — error rate, latency percentiles (p50-p99), throughput, health status, resource saturation (CPU/memory/OOMKilled for k8s-pod, heap/thread/GC for jvm), and dependency latency — across services, databases, operations, k8s pods, and JVMs. Load this FIRST for any question about service errors, slowness, latency, health, or saturation, including broad ones like "is any service erroring or slow right now?", before reaching for raw spans or PromQL. Also covers inventory questions such as listing services or available entity types.
1418d agoReviewMountCreate a free account to mount
Deep single-case investigation. Load when the user asks about one specific case by ID (UUID or readable id like "CASE-123") — e.g. summarize comments, explain who was notified where, judge whether the trigger reflects a real incident, walk the lifecycle. The `coralogix-alerts` skill should be loaded alongside this skill.
1418d agoReviewMountCreate a free account to mount
Span-specific concepts, fields, duration handling, and investigation patterns. Load when you need to explore spans in your investigation or to answer a question about spans. For service-level error rate, latency percentiles, throughput, or health, load the `coralogix-service-catalog` skill instead — it is the pre-aggregated path for those; use this skill when you need individual traces, span attributes, or span-level detail the catalog does not expose. Always load the `coralogix-dataprime` skill together with this one before writing any query.
1418d agoReviewMountCreate a free account to mount
Investigate incidents that involve a Cribl observability pipeline. Decide whether Cribl caused the problem, witnessed it, or is not involved; trace missing or delayed telemetry from Source to Destination; and search the customer's ingested data with Cribl Search (KQL) and PromQL. Load this when an investigation involves Cribl, data-pipeline delivery, missing or delayed telemetry, or a Cribl-sourced alert.
1418d agoReviewMountCreate a free account to mount
Guidelines for investigating production incidents in the CRM application. Use when triaging any alert or incident involving the CRM REST API, SQS queues, Lambda functions, or Aurora DSQL database in this AWS account. Ensures thorough root cause analysis using AWS-native observability tools.
1418d agoReviewMountCreate a free account to mount
Database-level data-plane diagnostics for Aurora MySQL and Aurora PostgreSQL. Executes predefined read-only health check queries via RDS Data API to analyze buffer pool, connections, locks, replication, storage, performance, and index efficiency. Requires the rds-aidba MCP server for database-internal access beyond what CloudWatch and RDS APIs provide.
1418d agoReviewMountCreate a free account to mount
Report what the AWS DevOps Agent itself costs to run, and where that cost comes from, per Agent Space and per role on demand in chat or on a schedule through a custom agent. Use this skill when a user asks to measure, break down, attribute, explain, or forecast DevOps Agent spend, or the cost of the downstream AWS API calls. Covers direct agent time by activity, Support plan credit offset, downstream API cost, and tool usage.
1418d agoReviewMountCreate a free account to mount
Assess Layer-3 (BGP prefix) failover resilience across redundant AWS Direct Connect virtual interfaces. Use when the user asks whether their Direct Connect setup is resilient, whether failover will work, whether the same routes/prefixes are advertised across redundant VIFs, why traffic was lost after a VIF or connection failure, or to audit DX BGP route symmetry. Checks both directions (routes received from on-prem and routes advertised by AWS) using the ListVirtualInterfaceRoutes API and the deterministic dx-resilience-mcp analysis tools. Read-only: analysis and recommendations only, never configuration changes. Complements Layer-1/2 checks (redundant connections, diverse locations/devices) — this skill covers what those miss.
1418d agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.