Register a temporary MCP connector in claude.ai and/or chatgpt.com, verify it works, then offer cleanup. Trigger when the user wants to test an MCP server URL through a real AI frontend — phrases like "test mcp", "add test connector", "smoke-test mcp server", "register connector for testing", "check mcp in claude"…
Use when the user asks for a multi-perspective review of a Go diff, PR, branch, commit range, or commit hash. Triggers on requests like "review this PR", "umbrella review", "do a full review", "deep review of branch X", or any Go-codebase code review where multiple independent angles (security, perf, concurrency…
Establishes the ClickHouse connection mode, cluster macro, and default log timeframe for diagnostics. Use first, before any other altinity-expert-clickhouse skill, to verify connectivity and set shared analysis rules.
Analyze ClickHouse external dictionaries including configuration, memory usage, reload status, and performance. Use for dictionary issues and load failures.
Diagnose and resolve ClickHouse grant and authentication errors, especially after upgrades. Use when queries fail with ACCESSDENIED/NOTENOUGHPRIVILEGES, AUTHENTICATIONFAILED/WRONGPASSWORD/REQUIREDPASSWORD, or ON CLUSTER privilege errors; when system. or INFORMATIONSCHEMA access is denied; or when grant behavior…
Analyze whether ClickHouse indexes (PRIMARY KEY, ORDER BY, skipping indexes, projections) are being used effectively for actual query patterns. Use when investigating index effectiveness, ORDER BY key design, query-to-index alignment, or when queries scan more data than expected.
Diagnose ClickHouse INSERT performance, batch sizing, part creation patterns, and ingestion bottlenecks. Use for slow inserts and data pipeline issues.
Diagnose ClickHouse Kafka engine health, consumer status, thread pool capacity, and consumption issues. Use for Kafka lag, consumer errors, and thread starvation.
Analyze ClickHouse system log table health including TTL configuration, disk usage, freshness, and cleanup. Use for system log issues and TTL configuration.
Real-time monitoring of ClickHouse metrics, events, and asynchronous metrics. Use for load average, connections, queue monitoring, and resource saturation.
Runs a fast ClickHouse server health snapshot and routes to specialist skills. Use as the entry point for general health checks or when the problem area is not yet known.
Analyze ClickHouse table structure, partitioning, ORDER BY keys, materialized views, and identify schema design anti-patterns. Use for table design issues and optimization.
Profile a ClickHouse cluster via MCP and emit a per-cluster "analyst" Skill the user can save in claude.ai. Activate when the user asks to "profile this ClickHouse", "generate an analyst skill", "build a schema guide", "map the data in this cluster", or regenerate an existing cluster-analyst Skill after schema…