Results for “count-matrix”

Computes the Recall metric using torchmetrics, including configuration for binary, multiclass, and multilabel tasks.

Numerical computing with MATLAB and GNU Octave for matrix operations, data analysis, visualization, and scientific computing, including script execution and syntax guidance.

Computes the AUROC metric using torchmetrics, handling binary, multiclass, and multilabel tasks with configurable thresholds and averaging.

Compute the F1Score metric using torchmetrics when predictions and ground-truth labels are available.

Computes the SQuAD metric using torchmetrics, given predictions and ground truth. Use when evaluating question-answering outputs with exact match and F1 scores.

Strategic search planning for agent-driven research. Generates structured search-term matrices with tiered fallback strategies, engine-specific operators, and grading criteria before executing any searches. Use this skill whenever research requires more than a single search query — comparing technologies, verifying claims across sources, surveying a landscape, investigating a multi-faceted question, or building evidence for a decision. Do NOT use for quick factual lookups, fetching a single known URL, or questions answerable from a single source. Covers tech, academic, regulatory, and general domains. Think of it as "research planning" — the matrix is the plan, execution comes after.

Turn "can we even hit this number" into a capacity model that shows the truth before the quarter does. Models ramped-rep productivity, builds the hiring plan the target requires, states the ramp assumptions plainly, and names the gap between plan and capacity so nobody discovers it in month three. Built for B2B sales and RevOps leaders, customizable to your ramp and your CRM. Trigger on "build a capacity model", "how many reps to hit the number", "what's the hiring plan", "are we capacity constrained", "model the ramp", or any capacity or headcount planning question.

Use `analysis-agent` to map acceptance to validation, `task-agent` to add or run bounded tests, and `review-agent` to assess proof coverage. Skip work with no material change or already-fresh complete validation.

Computes the Receiver Operating Characteristic (ROC) metric using torchmetrics, supporting binary, multiclass, and multilabel tasks.

This skill should be used when the user asks about "key startup metrics", "SaaS metrics", "CAC and LTV", "unit economics", "burn multiple", "rule of 40", "marketplace metrics", or requests guidance on tracking and optimizing business performance metrics.

Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations. Use when the user runs /si:status or asks how full or healthy the agent memory is.