5 Commits

Author	SHA1	Message	Date
Clayton Young	df58339850	feat(timesfm): complete all three examples with quality docs ... - anomaly-detection: full two-phase rewrite (context Z-score + forecast PI), 2-panel viz, Sep 2023 correctly flagged CRITICAL (z=+3.03) - covariates-forecasting: v3 rewrite with variable-shadowing bug fixed, 2x2 shared-axis viz showing actionable covariate decomposition, 108-row CSV with distinct per-store price arrays - global-temperature: output/ subfolder reorganization (all 6 output files moved, 5 scripts + shell script paths updated) - SKILL.md: added Examples table, Quality Checklist, Common Mistakes (8 items), Validation & Verification with regression assertions - .gitattributes already at repo root covering all binary types	2026-02-23 07:43:04 -05:00
Clayton Young	0d98fa353c	feat(examples): add anomaly detection and covariates examples ... Anomaly Detection Example: - Uses quantile forecasts as prediction intervals - Flags values outside 80%/90% CI as warnings/critical anomalies - Includes visualization with deviation plot Covariates (XReg) Example: - Demonstrates forecast_with_covariates() API - Shows dynamic numerical/categorical covariates - Shows static categorical covariates - Includes synthetic retail sales data with price, promotion, holiday SKILL.md Updates: - Added anomaly detection section with code example - Expanded covariates section with covariate types table - Added XReg modes explanation - Updated 'When not to use' section to note anomaly detection workaround	2026-02-23 07:43:04 -05:00
Clayton Young	dcde063723	chore: remove markdown-mermaid-writing skill from this branch ... This branch was originally created from feat/markdown-mermaid-writing-skill for development purposes, but the timesfm-forecasting skill should be independent of PR #50. - Remove scientific-skills/markdown-mermaid-writing/ directory - Remove reference to markdown-mermaid-writing from SKILL.md integration section - This PR now stands alone and does not require PR #50 to be merged first	2026-02-23 07:43:04 -05:00
Clayton Young	88300014e2	docs(skill): add note that model weights are not stored in repo ... Model weights (~800 MB) download on-demand from HuggingFace when skill is first used. Preflight checker ensures sufficient resources before any download begins.	2026-02-23 07:43:04 -05:00
Clayton Young	98670bcf47	feat(skill): add timesfm-forecasting skill for time series forecasting ... Add comprehensive TimesFM forecasting skill with mandatory system preflight checks (RAM/GPU/disk), end-to-end CSV forecasting script, full API reference, data preparation guide, and hardware requirements documentation. Supports TimesFM 2.5 (200M), 2.0 (500M), and legacy v1.0 with automatic batch size recommendations based on hardware.	2026-02-23 07:43:04 -05:00