SQL Server performance tuning skills for LLMs — 829 checks across 26 skills covering T-SQL, execution plans, wait stats, deadlocks, Query Store, indexes, encryption, Always On AG, WSFC, ERRORLOG, SPN, memory, disk I/O, config drift, setup logs, SSRS & migration readiness. Remote MCP server on Cloudflare Workers.
> /plugin marketplace add vanterx/mssql-performance-skills> /plugin install mssql-performance-skills@mssql-performance-skills
Repo: vanterx/mssql-performance-skills
What's inside
Go to claude.ai → Settings → Connectors → Add custom connector, enter the URL and click Add:
https://mssql-mcp.tsx113.workers.dev
A collection of Claude Code skills covering the full SQL Server performance tuning workflow — from static T-SQL source review to execution plan analysis, I/O statistics, workload traces, wait statistics, Query Store analysis, procedure runtime stats, index recommendations, live blocking chain analysis, deadlock diagnosis, batch workload assessment, WSFC cluster log analysis, Always On AG health, AG configuration correctness, ERRORLOG operational review, SPN/Kerberos delegation diagnosis, full encryption infrastructure review (TDE, Always Encrypted, CLE, backup encryption, TLS, certificates, key hierarchy including sp_control_dbmasterkey_password/SSISDB, dynamic data masking, PCI-DSS/HIPAA/GDPR/FedRAMP compliance), instance/database configuration drift, SQL Server Setup Bootstrap log analysis, SQL Server Reporting Services (SSRS) report server trace log analysis, and SQL Server migration readiness (version/edition/platform compatibility, security-object portability, operational-object portability) — plus an agentic orchestrator that routes mixed artifacts to the right specialised skill. 904 checks across 27 skills.
AI-Generated Skills — These skills were planned and generated by Claude with open source community resource guidance. The check catalog, thresholds, and output formats are intended to be improved and validated by human DBAs against real workloads. PRs welcome for new checks, threshold adjustments, or output format refinements.
| Skill | Purpose |
|---|---|
| mssql-performance-review | Agentic offline orchestrator — routes mixed artifacts (or a symptom description) to the right specialised skills, runs an adversarial root-cause check, and emits a single consolidated report with evidence chain, risk-rated fixes, and rollback. Use when you have several artifact types together or are not sure which skill to run. Also invocable as /sql-triage (equal-primary alias). |
| tsql-review | Analyze raw T-SQL source code — 85 checks (T1–T85) — structural, security, correctness, performance, SQL 2017–2022 modern syntax |
| sqlstats-review | Parse and analyze SET STATISTICS IO, TIME ON output — 27 checks (I1–I18 IO, W1–W9 time) |
| sqltrace-review | Analyze Profiler trace / Extended Events output — 25 checks (X1–X12 event-level, X13–X25 workload aggregate) |
| sqlwait-review | Analyze sys.dm_os_wait_stats — 44 checks (V1–V44) across I/O, lock, parallelism, memory, CPU, latch contention, log space, poison/throttle waits, backup I/O, insert hotspots, trend analysis, modern feature waits (In-Memory OLTP, Columnstore, Query Store, Transaction/DTC, Service Broker, Full Text, Parallel Redo), forced memory grants, grant timeouts, stolen memory, file I/O latency, IQP/PSP/ADR feature waits, and TempDB metadata contention |
| sqlplan-review | Analyze a single .sqlplan file — 111 checks, prioritized report |
| sqlplan-compare | Diff two plans to find what caused a regression |
| sqlindex-advisor | Derive indexes from operator patterns + consolidate optimizer suggestions into a ranked CREATE INDEX script |
| sqldeadlock-review | Analyze a deadlock XML graph — identify pattern and fix |
| sqlblocking-review | Analyze a live or already-finished blocking incident — 54 checks (BL1–BL54): head blocker identification and state, chain topology, lock escalation and Sch-M evidence, transaction/isolation faults, per-index and Query Store lock wait history, statistics/lock-partitioning/foreign-key causes, ORM and platform patterns, capture and alerting readiness |
| sqlplan-batch | Batch-analyze a folder of plans — dashboard + index script |
| sqlquerystore-review | Analyze Query Store DMV output — 32 checks for regressed queries, plan instability, resource hotspots, configuration health, SQL 2019/2022 IQP/PSP/DOP/CE feedback, QS hints, and auto-tuning |
| sqlprocstats-review | Analyze collected sys.dm_exec_procedure_stats snapshots — 25 checks (R1–R25) for top consumers, per-execution efficiency, N+1 patterns, trends, and advanced runtime patterns |
| sqlclusterlog-review | Analyze WSFC CLUSTER.LOG for Always On AG root-cause diagnosis — 30 checks (L1–L30): lease timeouts, health check failures, quorum loss, node eviction, network partition, RHS crashes, Cloud Witness, Azure Arc, Contained AG |
| sqlhadr-review | Analyze Always On AG health from sys.dm_hadr_* DMVs — 27 checks (H1–H28, H21 retired): replica connectivity, data loss risk, recovery time, throughput, configuration, modern AG features, seeding/initialization integrity |
| sqlag-review | Audit Always On AG configuration correctness across all layers — 37 checks (F1–F37): prerequisites, replica design, listener architecture, backup strategy, endpoint security, distributed AG topology, Basic/Contained AG constraints, AG scale ceiling, automatic seeding/manual-restore mismatch |
| sqlerrorlog-review | Analyze SQL Server ERRORLOG for operational issues — 33 checks (E1–E33): AG failover events, lease expiry, memory pressure, I/O slow, corruption warnings, login failure bursts, startup/shutdown, SQL 2019/2022 feature events |
| sqlspn-review | Analyze SQL Server SPN configuration and Kerberos delegation settings — 54 checks (K1–K54): SPN presence, service account binding, AG listener and alias, permissions, delegation, AD account sensitivity, Entra ID hybrid, gMSA rollover, CNAME alias, double-hop platform constraints (linked server, SSISDB), clock skew and token size, SQL Server on Linux keytabs, client driver limits |
| sqlmemory-review | Analyze SQL Server memory pressure from memory clerks, PLE, plan cache, and memory grants — 20 checks (O1–O20): PLE, plan cache bloat, grant queue depth, grant timeout, ColumnStore/XTP footprint, OS pressure, LPIM, Max Server Memory |
| sqldiskio-review | Analyze SQL Server file-level I/O latency and auto-growth events from sys.dm_io_virtual_file_stats — 15 checks (Z1–Z15): data/log latency, hot file, stall ratio, storage placement, TempDB co-location, auto-growth sizing and timing |
| sqlencryption-review | Analyze the full SQL Server encryption posture from DMV output — 112 checks (A1–A112) across 20 categories: TDE, Always Encrypted, CLE, Backup, Transport/TLS, Certificates, Keys, Key Hierarchy, EKM/AKV, Compliance, TLS Hardening, AE Advanced, Key Lifecycle, Ledger, Azure, DMK Password Auto-Open (sp_control_dbmasterkey_password/SSISDB), DDM Patterns, Compliance Explicit (PCI-DSS v4/HIPAA/GDPR/FedRAMP), Operational Validation, Advanced Crypto Patterns |
| sqlbootstraplog-review | Analyze SQL Server Setup Bootstrap logs (Summary.txt, Detail.txt, MSI logs, ConfigurationFile.ini) to diagnose failed installs, failed CU/SP patches, and risky setup-time configuration — 24 checks (U1–U24): exit-code extraction, failed setup rules, pending reboot, MSI Return value 3 forensics, service accounts, IFI, TempDB layout, security surface, directory placement |
| sqldbconfig-review | Analyze SQL Server instance and database configuration drift from sp_configure and sys.databases output — 29 checks (B1–B29): MAXDOP alignment to NUMA, Cost Threshold for Parallelism, Max Server Memory, auto-shrink, auto-close, compatibility level, RCSI, page verification, auto-statistics, VLF count, percent auto-growth, Instant File Initialization, TempDB file count, surface area exposure, service-SID sysadmin membership |
| ssrstracelog-review | Analyze SQL Server Reporting Services (SSRS) report server trace logs, RSReportServer.config/ReportingServicesService.exe.config excerpts, ExecutionLog3 output, and Event Log entries — 24 checks (G1–G24): trace configuration health, report server database connectivity, memory pressure and AppDomain recycling, report processing/rendering performance, subscription delivery failures, scale-out and encryption key management |
| sqlmigration-review | Audit SQL Server migration version/edition/platform compatibility — 15 checks (Y1–Y15): edition-gated features, version/compatibility-level ceiling, collation, discontinued features, In-Memory OLTP, Azure SQL limits, backup/log-chain readiness, AG seeding edition limits, source lifecycle urgency. Dispatcher with own checks |
| sqlmigration-security-review | Audit security-object portability for a SQL Server migration — 15 checks (J1–J15): login portability, permission fidelity, credentials/proxies, certificates/keys, CMS registrations |
| sqlmigration-objects-review | Audit operational-object portability for a SQL Server migration — 16 checks (M1–M16): SQL Agent jobs/operators/alerts/proxies, linked servers, Database Mail, backup devices, custom errors, server triggers, XE sessions, endpoints |
5 minutes to your first analysis:
/sqlplan-review skills/sqlplan-review/examples/horrible.sqlplan
Don't have a plan yet? Use the symptom-based routing in PERFORMANCE_TUNING_GUIDE.md to pick the right skill for what you have.
The skills are plain Markdown files. Copy them into your agent's skills directory — no build, no runtime, no dependencies.
Option 1: Plugin Marketplace (recommended)
# Add the marketplace (once per machine or project)
/plugin marketplace add vanterx/mssql-performance-skills
# Install all 27 skills
/plugin install mssql-performance-skills@mssql-performance-skills
For project-scoped install, append --scope project to the marketplace add command.
Option 2: npx one-liner
npx skills add vanterx/mssql-performance-skills # requires Node.js >= 18
Uses the third-party skills npm package — not maintained by Anthropic or this repo.
Option 3: Manual
git clone https://github.com/vanterx/mssql-performance-skills.git
cp -r mssql-performance-skills/skills/* ~/.claude/skills/ # global
# or
cp -r mssql-performance-skills/skills/* .claude/skills/ # project-scoped
After cloning, install the git hooks to keep skills-data.ts in sync automatically:
bash scripts/install-hooks.sh
This installs a pre-commit hook that regenerates mcp-server/src/skills-data.ts whenever a skills/*/SKILL.md file is staged, so you never have to run npm run bundle manually before committing.
The skills are hosted as a remote MCP server on Cloudflare Workers — no Node.js, no clone, no build required.
claude.ai web — Settings → Connectors → Add custom connector:
https://mssql-mcp.tsx113.workers.dev
FAQ
mssql-performance-skills is a Claude Code plugin with 27 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes mssql-performance-review, sqlag-review, sqlblocking-review. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it