feat: adopt org-wide feature-ideation reusable workflow#68
Conversation
Adds the BMAD Analyst (Mary) feature-research-and-ideation workflow as a thin caller stub for the org-wide reusable workflow at petry-projects/.github/.github/workflows/feature-ideation-reusable.yml. Runs every Friday at 07:00 UTC (manually dispatchable). Mary executes a 5-phase multi-skill pipeline (Market Research → Brainstorming → Party Mode → Adversarial → Publish) on Claude Opus 4.6 and posts evidence-grounded feature proposals to the Ideas discussion category. Standard: https://github.com/petry-projects/.github/blob/main/standards/ci-standards.md#8-feature-ideation-feature-ideationyml--bmad-method-repos Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
Caution Review failedPull request was closed or merged during review No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughThis PR adds a new GitHub Actions workflow for feature research and ideation. The workflow is scheduled to run weekly on Fridays at 07:00 UTC and supports manual triggering with optional parameters for focus area and research depth. It delegates execution to an organization-level reusable workflow while passing project context and secrets. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
|
There was a problem hiding this comment.
Pull request overview
This PR adds a repo-local GitHub Actions workflow that delegates to the org-wide “feature research & ideation” reusable workflow, customizing only the project-specific context used to generate weekly ideation Discussions.
Changes:
- Adds a scheduled + manually-dispatchable
.github/workflows/feature-ideation.ymlcaller workflow. - Configures job-level permissions, concurrency, and passes
focus_area/research_depthinputs plus the required secret to the reusable workflow.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| and vendors use today. Stack: React + GraphQL + Supabase, mobile- | ||
| first PWA-friendly UX. |
There was a problem hiding this comment.
The project_context describes the stack as "React + GraphQL + Supabase" and a "PWA-friendly UX", but this repo’s documented stack is React Native/Expo frontend with a Go gqlgen backend on Cloud Run + Cloud SQL Postgres (plus Firebase Auth/Realtime). Since this paragraph is the main customization for the ideation workflow, it should be updated to reflect the current architecture so the generated research/ideas aren’t based on incorrect assumptions.
| and vendors use today. Stack: React + GraphQL + Supabase, mobile- | |
| first PWA-friendly UX. | |
| and vendors use today. Stack: React Native/Expo mobile frontend, | |
| Go gqlgen GraphQL backend on Cloud Run, Cloud SQL Postgres, and | |
| Firebase Auth/Realtime for authentication and live updates. |
| uses: petry-projects/.github/.github/workflows/feature-ideation-reusable.yml@main | ||
| with: | ||
| project_context: | | ||
| markets is a real-time market operations platform for local farmer |
There was a problem hiding this comment.
Minor grammar: "local farmer and art markets" reads like a singular noun; consider changing to "local farmers and art markets" (or similar) for clarity in the prompt text.
| markets is a real-time market operations platform for local farmer | |
| markets is a real-time market operations platform for local farmers |


Summary
Adopts the org-wide BMAD Analyst (Mary) feature-research-and-ideation workflow as a thin caller stub. The reusable workflow lives at petry-projects/.github — this repo only customizes the
project_contextparagraph that tells Mary what the project is and what competitive landscape to research.Standard: ci-standards.md §8
Schedule
Runs every Friday at 07:00 UTC (3 AM EDT / 2 AM EST). Manually dispatchable via the Actions tab with optional
focus_areaandresearch_depth(quick / standard / deep) inputs.What it produces
Each run executes a 5-phase multi-skill pipeline on Claude Opus 4.6:
Typical cost: ~$2-3 per run on Opus 4.6 standard depth.
Test plan
🤖 Generated with Claude Code
Summary by CodeRabbit