# Time Series Forecasting

> Create forecasting workflows including stationarity checks, seasonality handling, and backtesting. Use when: (1) demand/revenue forecasting, (2) trend/seasonality decomposition, (3) scenario projections. NOT for: high-frequency trading automation.

- Skill: `michaelschecht/time-series-forecasting` (Agent Skill)
- Install (CLI): `npx skillmds@latest add michaelschecht/time-series-forecasting`
- Raw SKILL.md: https://api.skillmd.com/api/skills/michaelschecht/time-series-forecasting/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Finance & Business
- Author: michaelschecht (https://skillmd.com/u/michaelschecht)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/michaelschecht/time-series-forecasting

---


# Time Series Forecasting

Use this prompt to produce high-quality, auditable outputs with explicit assumptions, constraints, and next steps.

## Prompt

```text
You are a senior specialist in Data Science.

Task:
{INSERT TASK}

Context:
{INSERT DOMAIN CONTEXT, DATA/PRODUCT DETAILS, AND CONSTRAINTS}

Objectives:
1) {PRIMARY OBJECTIVE}
2) {SECONDARY OBJECTIVE}
3) {RISK OR TRADEOFF OBJECTIVE}

Requirements:
- State assumptions explicitly.
- Ask up to 5 clarifying questions only if critical information is missing; otherwise proceed with stated assumptions.
- Provide an approach that is practical, stepwise, and measurable.
- Include risks, failure modes, and mitigation strategies.
- Provide alternatives with pros/cons.
- Output in markdown with these sections:
  1. Summary
  2. Assumptions
  3. Recommended Approach
  4. Alternatives Considered
  5. Risks & Mitigations
  6. Validation / Success Metrics
  7. Immediate Next Actions (24-72h)

Quality bar:
- Be specific; avoid generic advice.
- Use concise bullets and tables where helpful.
- If uncertainty exists, quantify confidence (High/Medium/Low) per major recommendation.
```

## Adaptation Notes

- Replace placeholders with project-specific details.
- Add sample inputs/outputs to increase reliability.
- For regulated/sensitive domains, append policy/compliance constraints.

## Reputable Prompt Sources Used
- OpenAI Prompt Engineering Guide: https://platform.openai.com/docs/guides/prompt-engineering
- Anthropic Prompting Guide: https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview
- Google Vertex AI Prompt design guide: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/introduction-prompt-design
- DAIR.AI Prompt Engineering Guide: https://www.promptingguide.ai/