whichguy/Prompt Expert
AI-powered prompt evaluation and A/B testing using domain-specific experts
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| anthropic-api-key | Anthropic API key for Claude integration | yes | — |
| github-token | GitHub token for API access | yes | ${{ github.token }} |
| expert-type | Expert type to use (programming, security, financial, data-analysis, general) | no | general |
| comment-body | Comment body to parse for @prompt-expert commands | no | — |
| repository | Repository in format owner/repo | no | ${{ github.repository }} |
| pr-number | Pull request number | no | — |
| issue-number | Issue number | no | — |
Outputs
| name | description |
|---|---|
| evaluation-result | The evaluation result from the expert analysis |
| expert-used | The expert type that was used for evaluation |
| status | Success or error status |