playbooks

home / skills / onewave-ai / claude-skills / player-comparison-tool

player-comparison-tool skill

/player-comparison-tool

This skill compares players across eras with contextual adjustments and explains advanced metrics in plain English to inform decisions.

npx playbooks add skill onewave-ai/claude-skills --skill player-comparison-tool

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
1.4 KB
---
name: player-comparison-tool
description: Side-by-side stat comparisons with context. Adjust for era, pace of play, league differences. Advanced metrics explained in plain English.
---

# Player Comparison Tool
Side-by-side stat comparisons with context. Adjust for era, pace of play, league differences. Advanced metrics explained in plain English.

## Instructions

You are an expert sports statistician. Compare players across eras and contexts, explain advanced metrics clearly, and provide nuanced conclusions.

### Output Format

```markdown
# Player Comparison Tool Output

**Generated**: {timestamp}

---

## Results

[Your formatted output here]

---

## Recommendations

[Actionable next steps]

```

### Best Practices

1. **Be Specific**: Focus on concrete, actionable outputs
2. **Use Templates**: Provide copy-paste ready formats
3. **Include Examples**: Show real-world usage
4. **Add Context**: Explain why recommendations matter
5. **Stay Current**: Use latest best practices for sports

### Common Use Cases

**Trigger Phrases**:
- "Help me with [use case]"
- "Generate [output type]"
- "Create [deliverable]"

**Example Request**:
> "[Sample user request here]"

**Response Approach**:
1. Understand user's context and goals
2. Generate comprehensive output
3. Provide actionable recommendations
4. Include examples and templates
5. Suggest next steps

Remember: Focus on delivering value quickly and clearly!

Overview

This skill produces side-by-side player stat comparisons with contextual adjustments for era, pace, and league differences. It translates advanced metrics into plain English and delivers actionable recommendations for scouting, roster decisions, or fan analysis. The output is concise, reproducible, and ready to paste into reports or presentations.

How this skill works

The tool ingests player box stats, season-level league data, and era-specific pace factors, then normalizes numbers to a common baseline (per-100-possession or per-36-minute as requested). It applies regression-based era and league adjustments, computes advanced metrics (e.g., true shooting percentage, pace-adjusted plus/minus, wins above replacement), and surfaces interpretation in simple language. Results include side-by-side tables, relative percentiles, and short conclusions with recommended next steps.

When to use it

  • Comparing players from different eras (e.g., 1980s vs modern)
  • Evaluating transfer or international league performance vs target league
  • Creating scouting reports for signings, trades, or drafts
  • Explaining advanced metrics to coaches, front office, or fans
  • Preparing content for articles, broadcasts, or social posts

Best practices

  • Provide complete season-level input (minutes, possessions, team pace) for accurate adjustments
  • Specify target baseline (current NBA pace, per-100 possessions, etc.) up front
  • Use multiple seasons to reduce noise from small sample sizes
  • Combine model outputs with video scouting for context on role and fit
  • Request both raw and normalized outputs to verify adjustment impact

Example use cases

  • Head-to-head comparison of two wing scorers across 1990 and 2022 with pace normalization
  • Translate European league stats into equivalent NBA contributions for free-agent evaluation
  • Produce a one-page scouting brief showing percentile ranks and three clear takeaways
  • Generate an explainer segment that defines true shooting and win shares in plain English for broadcast
  • Run batch comparisons for shortlist of free agents to prioritize interviews

FAQ

How accurate are era and league adjustments?

Adjustments use historical pace and scoring baselines plus regression calibration; they reduce systematic bias but are subject to data quality and role differences, so treat results as strong directional evidence rather than absolute truth.

Can you compare players with limited minutes or small samples?

Yes, but small-sample outputs include confidence notes and suggest aggregating additional games or seasons to improve reliability.