nixtla-baseline-review
Analyze Nixtla baseline forecasting results (sMAPE/MASE on M4 or other benchmark datasets). Use when the user asks about baseline performance, model comparisons, or metric interpretation for Nixtla time-series experiments. Trigger with "baseline review", "interpret sMAPE/MASE", or "compare AutoETS vs AutoTheta".
npx skills add majiayu000/claude-skill-registry --skill nixtla-baseline-review-intent-solutions-io-plugins-nixtla --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Nixtla Baseline Review Skill ## Overview Analyze baseline forecasting results from the `nixtla-baseline-m4` workflow. Interpret metrics, compare models, surface patterns, and recommend next steps. ## When to Use This Skill Activate this skill when the user: - Asks "Which baseline model performed best?" - Requests interpretation of sMAPE or MASE metrics - Wants to compare AutoETS vs AutoTheta vs SeasonalNaive - Says "Explain these baseline results" - Needs guidance on model selection based on baseline performance ## Prerequisites - Baseline results must exist in `nixtla_baseline_m4/` directory - At minimum, `results_*.csv` file must be present - CSV format: columns `series_id`, `model`, `sMAPE`, `MASE` ## Instructions ### Step 1: Locate Results Files Use the **Read** tool to find baseline results: ```bash # Check for results directory (use Bash tool) ls -la nixtla_baseline_m4/ # Identify most recent results file ls -t nixtla_baseline_m4/results_*.csv | head -1 ``` Expected files: - `results_M4_Daily_h{horizon}.csv` - Full metrics table - `summary_M4_Daily_h{horizon}.txt` - Text summary (optional) If files are missing, inform the user they need to run `/nixtla-baseline-m4` first. #
- Overview
- When to Use This Skill
- Prerequisites
- Instructions
- Step 1: Locate Results Files
- Step 2: Load and Parse Metrics
- Step 3: Calculate Summary Statistics
- Step 4: Interpret Metrics
- Step 5: Identify Patterns
- Step 6: Generate Structured Explanation
- Output
- Examples
- Example 1: Simple Query
- Example 2: Detailed Comparison
Check for results directory (use Bash tool) ls -la nixtla_baseline_m4/ Identify most recent results file ls -t nixtla_baseline_m4/results_*.csv | head -1 View first few rows to confirm format head -10 nixtla_baseline_m4/results_M4_Daily_h*.csv Or use Read tool to load the full file
What does the nixtla-baseline-review skill do?
Analyze Nixtla baseline forecasting results (sMAPE/MASE on M4 or other benchmark datasets). Use when the user asks about baseline performance, model comparisons, or metric interpretation for Nixtla time-series experiments. Trigger with "baseline review", "interpret sMAPE/MASE", or "compare AutoETS vs AutoTheta".
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill nixtla-baseline-review-intent-solutions-io-plugins-nixtla --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.