Skip to content

Broaden review criteria for multimodal workflows - #5961

Open
aaronpowell wants to merge 1 commit into
mainfrom
review-prompts-and-board-fix
Open

aaronpowell wants to merge 1 commit into
mainfrom
review-prompts-and-board-fix

Conversation

@aaronpowell

Copy link
Copy Markdown
Contributor

Pull Request Checklist

  • I have read and followed the CONTRIBUTING.md guidelines.
  • I have read and followed the Guidance for submissions involving paid services.
  • My contribution adds a new instruction, prompt, agent, skill, workflow, or canvas extension file in the correct directory.
  • The file follows the required naming convention.
  • The content is clearly structured and follows the example format.
  • I have tested my instructions, prompt, agent, skill, workflow, or canvas extension with GitHub Copilot.
  • I have run npm start and verified that README.md is up to date.
  • I am targeting the main branch for this pull request.

Description

Broaden the Open PR Board and External Plugin Review Board guidance so reviewers assess Copilot workflows across coding and non-coding modalities, including image, video, audio, and creative work. Clarify that modality alone is not grounds for rejection, while retaining independent checks for user value, knowledge uplift, vendor funnels, provenance, native-feature duplication, responsible use, and workflow-appropriate validation.

Also show an actionable notice for GitHub CLI HTTP 422 decision failures rather than offering an opaque error for agent handoff.


Type of Contribution

  • New instruction file.
  • New prompt file.
  • New agent file.
  • New plugin.
  • New skill file.
  • New agentic workflow.
  • New canvas extension.
  • Update to existing instruction, prompt, agent, plugin, skill, workflow, or canvas extension.
  • Other (please specify):

Additional Notes

Focused validation passed: node --test --test-reporter=spec eng/open-pr-board.test.mjs eng/external-plugin-review-board.test.mjs (60 passed, 0 failed). git diff --check passed. npm start was not run; this change does not add resource entries or generated README content. No GitHub Copilot session test was performed.


By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

Copilot-Session: a6823cbb-5734-459d-bd6b-f80d2c864943
@aaronpowell
aaronpowell requested a review from a team as a code owner October 29, 2026 00:07
Copilot AI auto review requested due to automatic review settings October 29, 2026 00:07
@github-actions

github-actions Bot commented Oct 29, 2026 •

Copy link
Copy Markdown
Contributor

🚦 Submission status: 👀 Ready for review

Risk tier: merge-risk:high — Privileged execution, automation, or review-policy change
Required to merge: passing submission-gate checks plus 1 approval from reviewers with write access, including a maintainer with admin or maintain permission.

Why this tier
  • .github/extensions/external-plugin-review-board/lib/review-prompt.mjs is a high-risk path (automation, scripts, MCP config, hooks, or review policy)
  • .github/extensions/external-plugin-review-board/review-guidance.md is a high-risk path (automation, scripts, MCP config, hooks, or review policy)
  • .github/extensions/open-pr-board/lib/decisions.mjs is a high-risk path (automation, scripts, MCP config, hooks, or review policy)
  • .github/extensions/open-pr-board/lib/review-prompt.mjs is a high-risk path (automation, scripts, MCP config, hooks, or review policy)
  • .github/extensions/open-pr-board/review-guidance.md is a high-risk path (automation, scripts, MCP config, hooks, or review policy)
  • .github/skills/code-review/SKILL.md is a high-risk path (automation, scripts, MCP config, hooks, or review policy)
  • eng/external-plugin-review-board.test.mjs is a high-risk path (automation, scripts, MCP config, hooks, or review policy)
  • eng/open-pr-board.test.mjs is a high-risk path (automation, scripts, MCP config, hooks, or review policy)

Automated checks

Check Status Details
Line endings ✅ Passed Passed · logs
Spelling ✅ Passed Passed · logs
Contributor reputation ✅ Passed Passed · logs
Duplicate resource scan ✅ Passed Passed · logs
PR quality signal ✅ Passed Passed · logs

Review

  • Approvals: 0/1
  • Assigned reviewer: not assigned yet — comment /request-review to ask for one
  • Review target date: not set
  • Still needed: 1 more approval(s); an approval from a maintainer with admin or maintain permission
  • The core-maintainers pool is not staffed yet; an approver with admin or maintain permission is required instead.

Commands

Command Who What it does
/rerun-checks PR author, maintainers Re-runs failed or incomplete checks and re-evaluates this gate
/request-review PR author, maintainers Asks the review rotation to assign a reviewer (adds needs-reviewer)

Updated for d47bdce · gate run · This comment is maintained automatically — see submission gate docs.

@github-actions

Copy link
Copy Markdown
Contributor

🟡 Contributor Reputation Check: MEDIUM risk

Check Risk
Profile MEDIUM
Credential audit NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

@github-actions github-actions Bot added needs-review:MEDIUM Contributor reputation check flagged MEDIUM risk ready-for-review Submission passed intake validation and is ready for maintainer review and removed awaiting-automation labels Oct 29, 2026

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🔵 Needs a closer look

A maintainer should confirm the broadened submission scope before changes to the canonical code-review policy and both boards’ repository-fit criteria are merged.

No open issues 🎉

What changed in this PR

Broadens both review boards’ guidance to assess Copilot-supported multimodal workflows while preserving independent quality checks. Also improves handling of GitHub HTTP 422 decision failures.

Changes:

  • Clarifies that non-coding use or modality alone does not justify rejection.
  • Retains checks for user value, provenance, duplication, vendor funnels, responsible use, and appropriate validation.
  • Adds actionable HTTP 422 notices and regression tests for the updated behavior and guidance.
File Description
eng/​open-pr-board.test.mjs Tests multimodal guidance and HTTP 422 notice behavior.
eng/​external-plugin-review-board.test.mjs Tests multimodal criteria in prompts and guidance.
.github/​skills/​code-review/​SKILL.md Broadens repository-fit criteria while retaining quality checks.
.github/​extensions/​open-pr-board/​review-guidance.md Removes non-coding use as a standalone rejection reason.
.github/​extensions/​open-pr-board/​lib/​review-prompt.mjs Updates review prompts and repository-fit field guidance.
.github/​extensions/​open-pr-board/​lib/​decisions.mjs Converts HTTP 422 failures into actionable notices without agent handoff.
.github/​extensions/​external-plugin-review-board/​review-guidance.md Adds workflow-inclusive value and validation criteria.
.github/​extensions/​external-plugin-review-board/​lib/​review-prompt.mjs Applies multimodal criteria to initial and repeat reviews.

Review effort: Balanced (auto)

" - `gh pr checks <number> -R " + repo + "` when checks are failing, to see which ones and why.",
" - `gh pr list -R " + repo + " --author <login> --state all` to find the author's sibling PRs. If siblings were closed for a reason, apply it consistently and cite them; flag any open sibling recorded more leniently in `checkNext`.",
"Judge the submitted result, not assumptions about the tool that produced it. A title ending in 🤖🤖🤖 is a disclosure, not a defect.",
"Do not limit repository fit to coding or text-based developer tasks. Evaluate Copilot-supported workflows across modalities, including image, video, audio, other media generation, and creative work where applicable. Modality or non-coding use alone is not a rejection reason; assess concrete Copilot relevance, specific standalone user value, knowledge uplift, provenance, product/vendor-funnel evidence, responsible use, and validation appropriate to the workflow.",
Recent maintainer decisions (calibrate against these as well as the guidance):
${formatHistory(history)}

Evaluate concrete Copilot relevance and specific standalone user value across supported workflows, not only coding or text-based developer tasks. Image, video, audio, other media-generation, and creative work may be in scope where applicable; modality or non-coding use alone is not a rejection reason. Assess knowledge uplift, provenance, product/vendor-funnel evidence, responsible use, and validation appropriate to the workflow. Preserve rejection of marketing-only funnels, paid or credit-based acquisition paths without standalone user value, duplicates of native Copilot features, and generic content with no meaningful uplift.

This branch was successfully deployed

1 active deployment
github-pages — d47bdce1 Deployed Oct 29, 2026 by aaronpowell via deploy #1197
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

merge-risk:high needs-review:MEDIUM Contributor reputation check flagged MEDIUM risk ready-for-review Submission passed intake validation and is ready for maintainer review

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants