Mística AI Discussions #158
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Mística AI Discussions | |
| permissions: | |
| contents: read | |
| pull-requests: write | |
| on: | |
| discussion: | |
| types: [created, edited] | |
| concurrency: | |
| group: ${{ github.repository }}-${{ github.event.number || github.head_ref || github.sha }}-${{ github.workflow }} | |
| cancel-in-progress: true | |
| jobs: | |
| chatgpt: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: platisd/openai-pr-description@master | |
| with: | |
| github_token: ${{ secrets.NOVUM_PRIVATE_REPOS }} | |
| openai_api_key: ${{ secrets.OPENAI_API_KEY }} | |
| sample_prompt: | | |
| It acts as the person who will decide whether a design requirement should enter into an overall design system and complies with the following rules: | |
| 1. The requirement must be global, i.e. it must work outside the product and/or business logic. It should be as agnostic as possible. | |
| 2. It must be scalable to another type of product. | |
| 3. It should work for mobile and desktop environments | |
| 4. That it is multi-brand | |
| sample_response: | | |
| Base on rules that Mística defines, evaluate the proposal with the following requirements: | |
| 1. The requirement must be global, i.e. it must work outside the product and/or business logic. It should be as agnostic as possible. | |
| 2. It must be scalable to another type of product. | |
| 3. It should work for mobile and desktop environments | |
| 4. That it is multi-brand | |
| - name: Add comment to discussion | |
| run: | | |
| curl -X POST \ | |
| -H "Authorization: Bearer ${{ secrets.NOVUM_PRIVATE_REPOS }}" \ | |
| -H "Accept: application/vnd.github.v3+json" \ | |
| https://api.github.com/repos/{owner}/{repo}/discussions/{discussion_number}/comments \ | |
| --data-raw '{"body": "Generated response: ${description}"}' | |
| env: | |
| description: ${{ steps.openai-pr-description.outputs.response }} |