Analytics & Monitoring Agent Skills for Windsurf (legacy)

Manage `cs` (claude-statusbar) — switch theme/style/density, override severity colors, preview combinations, run doctor, reset config…

Hosted-gateway LLM router — save 84% on inference costs.

Deep-debug complex Clay enrichment failures, provider degradation, and

Collect Clay debug evidence for support tickets and troubleshooting.

Collect comprehensive debug information for Clerk issues.

Monitor ClickHouse with Prometheus metrics, Grafana dashboards, system table queries, and alerting for query performance, merge health…

Collect ClickUp API diagnostic information for troubleshooting and support.

Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR…

Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1…

Information extraction from clinical free text.

Expert-thinking profile for Clinical Trial Scientist (clinical operations / GCP trials): Reasons from protocol SAPs, ICH-GCP…

Execute mcloud logs to fetch and stream runtime logs for Cloud environments.

Analyzes and optimizes application performance across frontend, backend, and database layers.

Cloudflare analytics via GraphQL API. Query HTTP request stats (status codes, 404s, top paths), video streaming analytics (minutes…

Skill for the Cluster_98 area of Securacy. 3 symbols across 2 files.

Analyze datasets by running clustering algorithms (K-means, DBSCAN,

End-to-end ad conversion tracking: Meta Pixel+CAPI, TikTok Events API, Google Ads Enhanced Conversions, GTM, attribution.

Use when: (1) Entering a Kaggle Code Competition that requires notebooks with no internet access, (2) Need to fork a public baseline that…

tags: [gsd-2, skills, code-optimizer, performance, devops, security, database, code-review, compliance]…

Monitor CodeRabbit review effectiveness with metrics, dashboards, and

Use when asked to inspect, reconstruct, audit, compare, or summarize prior coding-agent work across Codex, Claude, OpenCode, or local…