domain-time-series

domain-time-series is a skill for Claude Code from mxslr/mlcraft. It costs 101 tokens per session (585 once invoked), scanned A, original, MIT.

A guide for machine learning with ordered data collected over time, such as sales, energy use, financial prices, sensors, or monitoring logs. It covers forecasting, classification, and anomaly detection.

In plain words
What is it for?
Use it to choose forecasting methods, classify time-based patterns, detect unusual events, create time-based features, and run rolling or expanding-window backtests.
Why use it?
It prevents future information from leaking into training and encourages testing methods in the same time order in which they will be used.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mlcraft plugin — 23 skills, 1 command, 1 agent shipped together

Good fit Use it to choose forecasting methods, classify time-based patterns, detect unusual events, create time-based features, and run rolling or expanding-window backtests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mxslr/mlcraft/domain-time-series
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add mxslr/mlcraft --skill domain-time-series
Clone the repo
git clone --depth 1 https://github.com/mxslr/mlcraft

Made for: Claude Code.

Or install mlcraft, the plugin that ships this one along with the rest of its 23 skills, 1 command, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for domain-time-series

README.md
[![agentmods](https://agentmods.dev/badge/skills/mxslr/mlcraft/domain-time-series.svg)](https://agentmods.dev/skills/mxslr/mlcraft/domain-time-series)
Your own site
<a href="https://agentmods.dev/skills/mxslr/mlcraft/domain-time-series"><img src="https://agentmods.dev/badge/skills/mxslr/mlcraft/domain-time-series.svg" alt="Measured on agentmods" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00101 $0.00585
Opus 5 $0.00051 $0.00293
Sonnet 5 $0.00020 $0.00117
Haiku 4.5 $0.00010 $0.00059

Measured 8d ago against content hash 5c04348fcdae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

domain-time-series scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/domain-time-series/SKILL.md · 31 lines

What it actually says

Time-Series - Method Selection

Temporal order is sacred: the future must never leak into training.

Decision table

Sub-task Recommended (simple to advanced) Notes
Univariate / few series forecasting ETS / ARIMA / Theta / Prophet Strong, interpretable baselines. Often beat deep on small data.
Many related series LightGBM on lag/calendar features then N-BEATS/NHITS, TFT GBT-on-lags is a very strong, cheap default.
Long-horizon / rich covariates TFT / PatchTST / DeepAR Deep only when data volume justifies it.
Foundation / zero-shot TimesFM / Chronos / Moirai Good for cold-start / many series with little history.
TS classification ROCKET/MiniROCKET, InceptionTime, HIVE-COTE ROCKET = fast strong baseline.
Anomaly detection STL/residual + threshold, Isolation Forest, autoencoder/LSTM Start simple; label scarcity is the norm.

Temporal rigor (non-negotiable)

  • Split by time: train strictly before validation before test. Use rolling/expanding-window backtesting, not random K-fold (data-rigor-and-leakage).
  • No future leakage in features: lags/rolling stats use only past data; align target horizon carefully; no target-derived or post-hoc features.
  • Fit scalers/encoders on the training window only, refit as the window rolls.
  • Respect gaps/frequency: handle missing timestamps, irregular sampling, and known future covariates (holidays) vs unknown.

Evaluation

  • Metrics: MAE / RMSE / MAPE / sMAPE / MASE (MASE compares to a naive baseline - always include a naive/seasonal-naive baseline).
  • Report per-horizon error and prediction intervals (coverage), not just a point metric.
  • Backtest across multiple origins; a single split is not enough.
  • Improve: use accuracy-improvement-loop (better features/lags, hierarchical reconciliation, ensembling classical+ML, then deep).
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 31 lines · 101 tokens per session scan A 5c04348fcdae

Subscribe to this mod's changes

domain-time-series is a skill published in the GitHub repository mxslr/mlcraft (8 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 585 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

transformers

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…

synthetic-sciences/openscience · 63 tokens

chief-data-officer

Owns data as an asset — governance, quality, the warehouse and semantic layer, analytics capability, and the governance of models built on top. Use this for a decision about how data is collected, stored, defined, or shared; when numbers disagree between teams; when deciding what to build in-house versus buy; when…

cbrock84/headcount · 88 tokens

ai-workflow-architect

Designs AI systems, automations, and agent workflows for a business — identifying which manual work is worth automating, how to structure the system, which tools fit, and what could go wrong. Use this to automate part of an operation, design an agent or MCP workflow, reduce repetitive manual work, connect tools into a…

cbrock84/headcount · 89 tokens

ai-ml-governance

Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…

cbrock84/headcount · 83 tokens

data-engineering

Builds and operates data pipelines — ingestion, transformation, orchestration, quality testing, and reliability of data delivery. Use this to design or debug a pipeline, decide batch versus streaming, add data quality checks, handle late or duplicate data, or work out why a dashboard's numbers changed without anyone…

cbrock84/headcount · 67 tokens

llm-integration

LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.

yonatangross/orchestkit · 58 tokens