Registry skillby onewave-ai
Play By Play Generator
onewave-ai/play-by-play-generator
Create realistic play-by-play commentary. Multiple announcer styles: traditional, hyped, analytical, homer. Color commentary included.
What it changes
Passed 20 of 22 test cases with the skill, and 3 of 22 without it.
Without skill14%
With skill91%
Checks it passed that the model alone missed
- includes section heading ## Results
- includes section heading ## Recommendations
- contains the generated timestamp metadata key
and 7 more in the full report
19 fixed1 passed either way0 still failing2 broke
- Pass-rate lift
- +77 pp
- Tokens
- +11%
- Agent turns
- 0%
- Response time
- +4%
Model gemini-3.6-flashMeasured 8/24/2026v120 of 22 cases passed with skill
See it in action
One of 19 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptGenerate fast-paced hockey commentary for a 3-on-3 Stanley Cup Finals overtime breakaway goal.
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| includes section heading ## Recommendations | Missed | Passed |
|---|
| formats the response with distinct output sections | Passed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md54 linessingle file
Play By Play Generator
Create realistic play-by-play commentary. Multiple announcer styles: traditional, hyped, analytical, homer. Color commentary included.
Instructions
You are an expert sports broadcaster. Generate engaging play-by-play commentary with appropriate style, energy, and insights.
Output Format
# Play By Play Generator Output
**Generated**: {timestamp}
---
## Results
[Your formatted output here]
---
## Recommendations
[Actionable next steps]
Best Practices
- Be Specific: Focus on concrete, actionable outputs
- Use Templates: Provide copy-paste ready formats
- Include Examples: Show real-world usage
- Add Context: Explain why recommendations matter
- Stay Current: Use latest best practices for sports
Common Use Cases
Trigger Phrases:
- "Help me with [use case]"
Track record
Benchmark
20 / 22
test cases passed, vs 3 / 22 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
ImportedLicense MITImported 8/3/2026Version v1