Analytics & Monitoring Agent Skills for Windsurf (legacy)

LLM cost tracking with Langfuse for cached responses.

Interactive sample size calculator for medical research.

Calculate cryptocurrency tax obligations with cost basis tracking, capital

Score how past confidence aged. Samples old tagged claims ([HIGH]/[MED]/[LOW], gate predictions, premortem risks, estimates) and checks…

Drive any measurable system toward "good" by running a disciplined scientific loop — MEASURE → DIAGNOSE → PLAN → ACT → RE-MEASURE → DECIDE…

Bounded autonomous research and engineering loop through TORC that evaluates committed candidates against a saved objective and constraints.

Execute this skill enables AI assistant to analyze capacity requirements

Logistics carbon emission tracking and reduction planning skill supporting sustainability initiatives

This skill should be used when the user wants to "set up tracing", "monitor my ADK agent", "configure logging", "add observability"…

Discover and subscribe to external spatial datasets via CARTO Data Observatory and partner catalogs.

Preview an existing saved CARTO Builder map inline in the chat via the CARTO MCP server — resolve the map with read_maps (by name or…

Render an ad-hoc interactive map inline in the chat from a deck.gl declarative spec via the CARTO MCP server's view_map tool.

Collect CAST AI diagnostic bundle for support tickets and troubleshooting.

Use when the causal identification strategy is the bottleneck for a Quarterly Journal of Economics (QJE) manuscript — RCT, staggered DID…

Systematically investigates causal relationships to identify true root causes rather than correlations or symptoms.

Sets up, audits, and reports on marketing measurement — tracking plans, event schemas, attribution models, and the dashboards built on them.

Chan Theory analysis for A-shares. Merge K-lines by containment, identify strokes (bi), fractals (fenxing), and channels. Supports…

Create, review, and restyle data visualizations using Edward Tufte principles: high data-ink ratio, direct labels, range-frame axes, small…

Generate images using ChatGPT/DALL-E through OpenClaw browser automation.

Check release health and compare error rates across deployments

Convenes a multi-model "council" to answer a question, then synthesizes a single best answer — inspired by Karpathy's llm-council.