forecasting-time-series-data
This skill enables Claude to forecast future values based on historical time series data. It analyzes time-dependent data to identify trends, seasonality, and other patterns. Use this skill when the user asks to predict future values of a time series, analyze trends in data over time, or requires insights into time-dependent data. Trigger terms include "forecast," "predict," "time series analysis," "future values," and requests involving temporal data.
Install with Tessl CLI
npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill forecasting-time-series-data78
Quality
51%
Does it follow best practices?
Impact
97%
1.04xAverage score across 6 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./backups/skills-batch-20251204-000554/plugins/ai-ml/time-series-forecaster/skills/time-series-forecaster/SKILL.mdDiscovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description that clearly communicates its purpose and includes explicit trigger guidance. The main strengths are the comprehensive 'Use when' clause and good trigger term coverage. The description could be improved by adding more specific concrete actions and narrowing language to reduce potential overlap with general analytics or prediction skills.
Suggestions
Add more specific concrete actions like 'generate forecasts with confidence intervals', 'detect seasonality patterns', or 'compare ARIMA vs exponential smoothing models' to increase specificity.
Differentiate from general prediction/analytics skills by emphasizing unique time series aspects like 'sequential data', 'lagged variables', or specific file formats/data structures it handles.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (time series forecasting) and some actions (forecast future values, analyze trends, identify patterns), but lacks specific concrete actions like 'generate confidence intervals', 'detect anomalies', or 'compare multiple forecasting models'. | 2 / 3 |
Completeness | Clearly answers both what (forecast future values, analyze trends, identify seasonality and patterns) AND when (explicit 'Use this skill when...' clause with specific trigger scenarios and terms). | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger terms users would say: 'forecast', 'predict', 'time series analysis', 'future values', and 'temporal data'. Good coverage of common variations users might naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | While time series forecasting is a specific domain, phrases like 'analyze trends in data over time' could overlap with general data analysis skills. The temporal focus helps but 'predict' and 'forecast' could conflict with other predictive modeling skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
20%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is descriptive rather than instructive, explaining what time series forecasting is rather than teaching Claude how to perform it. It lacks any executable code, specific library usage, or concrete implementation details. The content assumes Claude needs to be told what forecasting means rather than providing the actionable guidance needed to actually perform the task.
Suggestions
Replace abstract descriptions with executable Python code showing how to load data, fit models (e.g., statsmodels ARIMA, Prophet), and generate forecasts with confidence intervals
Remove explanatory content about what time series forecasting is and what triggers the skill - Claude already knows this
Add validation steps: how to check data quality, evaluate model fit (AIC/BIC), and verify forecast reasonableness before presenting results
Include specific input/output examples showing expected data format and forecast output structure
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Verbose and padded with unnecessary context. Explains concepts Claude already knows (what time series forecasting is, what ARIMA/Prophet are, basic data quality principles). The 'How It Works' and 'When to Use' sections describe rather than instruct. | 1 / 3 |
Actionability | No executable code, no concrete commands, no specific implementation details. Examples describe what 'the skill will do' abstractly rather than providing copy-paste ready code or specific steps Claude should follow. | 1 / 3 |
Workflow Clarity | Steps are listed (analyze, select model, generate predictions) but lack validation checkpoints, error handling, or feedback loops. No guidance on what to do if model selection fails or predictions are poor quality. | 2 / 3 |
Progressive Disclosure | Content is organized into sections but everything is inline with no references to detailed materials. The 'Integration' section mentions other tools but provides no links or specifics. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.