bracket-predictor — Claude Code skill: what it does, how to install
Generates tournament bracket predictions, upset analyses, and contrarian pick strategies with confidence scores.
npx skills add OneWave-AI/claude-skills --skill bracket-predictor -a claude-codeWhat bracket-predictor does
The skill instructs the agent to act as a tournament analyst for March Madness and playoff brackets. It evaluates team matchups, compares standard chalk picks with contrarian strategies, and uses historical trend analysis.
Selections include explicit reasoning alongside confidence ratings. Output arrives in structured Markdown. It features a generated timestamp, detailed results, and clear recommendations. Because the skill includes no live data feed, you must supply current matchups and seeds in your prompt.
What it helps with
- Identify upset opportunities across tournament brackets
- Compare chalk predictions against contrarian strategies
- Generate structured playoff picks with confidence levels
- Document matchup reasoning in a formatted Markdown report
Example prompts for the agent
- Build a March Madness bracket prediction focusing on upset potential
- Compare a chalk strategy with contrarian picks for the upcoming playoff round
- Evaluate this matchup and give me confidence levels with reasoning
How to install bracket-predictor
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill bracket-predictor -a claude-code2Manually: put the files in place
~/.claude/skills/bracket-predictor/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/bracket-predictor/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill bracket-predictor -a codex2Manually: put the files in place
.agents/skills/bracket-predictor/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill bracket-predictor -a cursor2Manually: put the files in place
.cursor/skills/bracket-predictor/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OneWave-AI/claude-skills bracket-predictor2Manually: put the files in place
.github/skills/bracket-predictor/SKILL.md1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill bracket-predictor -a gemini-cli2Platform CLI
gemini skills install https://github.com/OneWave-AI/claude-skills --path bracket-predictorManually: put the files in place
.devin/skills/bracket-predictor/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill bracket-predictor -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about bracket-predictor
How to install bracket-predictor in Claude Code?
Run npx skills add OneWave-AI/claude-skills --skill bracket-predictor -a claude-code. Alternatively, add the file manually at ~/.claude/skills/bracket-predictor/SKILL.md.
What does bracket-predictor do?
It provides an analytical framework for tournament brackets and playoff picks. It analyzes matchups, evaluates upsets, and outputs a formatted breakdown with recommendations.
Does bracket-predictor require external API keys?
No external APIs or sports feeds are required. You provide tournament matchups and team context directly in your prompt.
Source text
SKILL.md · MIT
---
name: bracket-predictor
description: March Madness, playoff brackets, tournament picks. Upset potential, chalk vs contrarian strategies, historical trends, confidence levels.
---
# Bracket Predictor
March Madness, playoff brackets, tournament picks. Upset potential, chalk vs contrarian strategies, historical trends, confidence levels.
## Instructions
You are an expert bracket analyst and tournament predictor. Create data-driven tournament predictions with: upset identification, chalk vs contrarian strategies, historical trend analysis, matchup breakdowns, confidence levels per pick, and reasoning for each selection.
### Output Format
```markdown
# Bracket Predictor 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!
© OneWave-AI · MIT · OneWave-AI/claude-skills
