Refine FieldWorks AI review workflows#905
Open
johnml1135 wants to merge 6 commits into
Open
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Adds FieldWorks-specific Copilot customization artifacts to standardize PR analysis, pre-PR author “challenge” workflows, and structured response handling for review comments.
Changes:
- Added a repo-root
CONTEXT.mdglossary/invariants document to align terminology across humans and agents. - Introduced new skills/prompts for pre-PR author challenge (
challenge-pr-author) and for addressing review feedback (respond-to-review-comments), plus a terminology-grilling skill (grill-with-docs). - Added a FieldWorks-specific review analyzer instruction set and updated repo context entry points.
Reviewed changes
Copilot reviewed 8 out of 8 changed files in this pull request and generated 4 comments.
Show a summary per file
| File | Description |
|---|---|
| CONTEXT.md | New repo-wide shared language/glossary and invariants for FieldWorks. |
| .github/skills/respond-to-review-comments/SKILL.md | New workflow skill for triaging/fixing/replying to PR review comments. |
| .github/skills/grill-with-docs/SKILL.md | New skill for tightening terminology against repo context documents. |
| .github/skills/challenge-pr-author/SKILL.md | New pre-PR interactive author “challenge” workflow that writes .review/summary.md. |
| .github/prompts/respond-to-review-comments.prompt.md | Prompt wiring to invoke the respond-to-review-comments skill. |
| .github/prompts/challenge-pr-author.prompt.md | Prompt wiring to invoke the challenge-pr-author skill. |
| .github/instructions/review-analyzer.instructions.md | New FieldWorks PR/branch analysis policy with required passes and rubric. |
| .github/context/codebase.context.md | Adds pointers to CONTEXT.md and the new review-response skill. |
NUnit Tests 1 files ±0 1 suites ±0 9m 5s ⏱️ - 2m 3s Results for commit bd22510. ± Comparison against base commit b0bf8a8. This pull request removes 2 and adds 1 tests. Note that renamed tests count towards both.♻️ This comment has been updated with latest results. |
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
johnml1135
changed the title
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Refines the FieldWorks AI review customization flow into a clearer layered architecture:
challenge-pr-authortopr-preflightfor the pre-PR branch readiness workflow.review-analyzer.instructions.mdas the shared FieldWorks review policy, not a user-facing workflow.pr-preflightto the existing specialist reviewer agents for C#, WinForms, C++/interop, Avalonia, and architecture-risk passes where appropriate.grill-with-docsinto planning/OpenSpec flows so ambiguous repo language is clarified before proposal/spec/design/task artifacts are written.respond-to-review-commentsas the post-PR review feedback workflow.Docs/workflows/ai-pr-workflow.mdguide for the Jira -> worktree -> preflight -> review-response path with GitHub Copilot and Claude Code entrypoints.ReadMe.md,Docs/core-developer-setup.md,Docs/CONTRIBUTING.md,Docs/workflows/pull-request-workflow.md, and.github/pull_request_template.mdso developers can discover it from onboarding and PR authoring surfaces.Relationship to #865
The AI review workflow work now belongs in this PR. PR #865 should stay focused on non-render build/test/helper/installer cleanup and drop duplicated generic review-skill material.
CI-ready checklist
.github/commit-guidelines.md; ranCI: Full local check.CI: Full local checkreran after whitespace normalization and reported no problems.Src/**folders touched, correspondingAGENTS.mdfiles are updated or explicitly confirmed still accurate. OnlySrc/AGENTS.mdguidance was updated to align with the repo C# 8.0 policy.Notes for reviewers
This PR changes Copilot customization, skills, prompts, context/instruction files, and contributor-facing workflow docs only; no product source, build scripts, installer files, or runtime behavior changed.
This change is