Analytics & Monitoring Agent Skills

Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring…

🐉 Skill for interacting with Google Cloud Monitoring (CM) via APIs to avoid large context bloat.

Prepare and verify Neuroglancer precomputed EM data, then create reproducible scientific videos and review figures from CloudVolume…

Diagnoses .NET Framework CLR activation issues using CLR activation logs (CLRLoad logs) produced by mscoree.dll.

Analyzes code files and reports statistics including line counts, file counts by extension, and total size.

Optimize CodeRabbit costs through seat management, repo selection, and

Run OpenAI Codex via the Codex App Server (JSON-RPC-over-stdio) for streaming multi-turn chat sessions with persistent threads, structured…

Optimize Cohere costs through model selection, token budgets, and usage

Configure Cohere across development, staging, and production environments.

Implement Cohere reference architecture with layered project layout

Use when running LLM inference on Colab GPUs.

Run scalex performance benchmarks, profiling, and timing analysis.

Expert-thinking profile for Community Ecologist (field / experimental / multivariate community assembly): Reasons from Vellend's four…

Competitive landscape analysis: Porter''s Five Forces, competitor discovery, feature/pricing matrices, positioning maps, moat assessment…

Analyse competitor moves and translate them into strategic implications for your product roadmap.

Use when the user says 'tokenstack', 'compression', 'token savings', 'proxy status', or asks about context window usage.

Computational geometry with Shapely - create geometries, boolean operations, measurements, predicates

Recommend, create, preview, and attach Coval trace-based metrics from OpenTelemetry spans.

Configures the analytics side of a PostHog experiment — exposure criteria (server-resolved default exposure event vs custom exposure…

Configures the rollout shape of a PostHog experiment — the variant split (50/50, 80/20, A/B/C ratios), the overall rollout percentage that…

Anthropic's method for training harmless AI through self-improvement.