Skip to content

Batch PR comment review decisions - #55

Merged
kin0992 merged 6 commits into
mainfrom
feats/batch-review-pr-comments
Aug 11, 2026
Merged

kin0992 merged 6 commits into
mainfrom
feats/batch-review-pr-comments

Conversation

@kin0992

@kin0992 kin0992 commented Aug 11, 2026

Copy link
Copy Markdown
Owner

Summary

  • collect Accept, Defer, or Reject decisions before GitHub mutations
  • provide and retain suggested replies during triage
  • publish the grouped reactions and approved replies only after confirmation
  • add coverage for the grouped workflow trigger

Validation

  • pnpm --filter @kin0992/skills format:check
  • pnpm marketplace:check

kin0992 and others added 3 commits August 11, 2026 12:30
Collect comment decisions and reply drafts before publishing reactions and approved replies together.

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

changeset-bot Bot commented Aug 11, 2026

Copy link
Copy Markdown

🦋 Changeset detected

Latest commit: bf1423d

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 1 package
Name Type
@kin0992/skills Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

@github-actions

Copy link
Copy Markdown
Contributor

=== review-pr-comments ===

Running benchmark: review-pr-comments-eval
Skill: engineering/review-pr-comments
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Review Agent Feedback
✓ [2/3] Review Unresolved Comments
✓ [3/3] Should Not Trigger

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 237ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Review Agent Feedback 1.00 has_output
Review Unresolved Comments 1.00 has_output
Should Not Trigger 1.00 has_output

Benchmark: review-pr-comments-eval | Skill: engineering/review-pr-comments | Model: claude-sonnet-4-20250514

=== branch-name ===

Running benchmark: branch-name-eval
Skill: git/branch-name
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Feature Branch Naming
✓ [2/3] Fix Branch Naming
✓ [3/3] Should Not Trigger

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 234ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Feature Branch Naming 1.00 has_output, no_ids
Fix Branch Naming 1.00 has_output, no_ids
Should Not Trigger 1.00 has_output, no_ids

Benchmark: branch-name-eval | Skill: git/branch-name | Model: claude-sonnet-4-20250514

=== commit-message ===

Running benchmark: commit-message-eval
Skill: git/commit-message
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Basic Bug Fix Commit
✓ [2/3] Multi-Area Diff
✓ [3/3] Should Not Trigger - PR Description Request

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 238ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Basic Bug Fix Commit 1.00 has_output, no_conventional_commits, no_period_ending
Multi-Area Diff 1.00 has_output, no_conventional_commits, no_period_ending
Should Not Trigger - PR Description Request 1.00 has_output, no_conventional_commits, no_period_ending

Benchmark: commit-message-eval | Skill: git/commit-message | Model: claude-sonnet-4-20250514

=== pr-title-description ===

Running benchmark: pr-title-description-eval
Skill: git/pr-title-description
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Basic Feature PR
✓ [2/3] PR With Template
✓ [3/3] Should Not Trigger - Commit Message Request

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 235ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Basic Feature PR 1.00 has_output
PR With Template 1.00 has_output
Should Not Trigger - Commit Message Request 1.00 has_output

Benchmark: pr-title-description-eval | Skill: git/pr-title-description | Model: claude-sonnet-4-20250514

═══════════════════════════════════════════════
MULTI-SKILL RUN SUMMARY
═══════════════════════════════════════════════

Skill Status Pass Rate Avg Score
──────────────────────────────────────────────────────────────────────
review-pr-comments ✅ Passed 100.0% 1.00
branch-name ✅ Passed 100.0% 1.00
commit-message ✅ Passed 100.0% 1.00
pr-title-description ✅ Passed 100.0% 1.00

Combined summary saved to: results_summary.json
Results saved to: results_review-pr-comments.json
Results saved to: results_branch-name.json
Results saved to: results_commit-message.json
Results saved to: results_pr-title-description.json

Ask before editing code for accepted review comments, then refresh the grouped publication plan.

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

Copy link
Copy Markdown
Contributor

=== review-pr-comments ===

Running benchmark: review-pr-comments-eval
Skill: engineering/review-pr-comments
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Review Agent Feedback
✓ [2/3] Review Unresolved Comments
✓ [3/3] Should Not Trigger

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 245ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Review Agent Feedback 1.00 has_output
Review Unresolved Comments 1.00 has_output
Should Not Trigger 1.00 has_output

Benchmark: review-pr-comments-eval | Skill: engineering/review-pr-comments | Model: claude-sonnet-4-20250514

=== branch-name ===

Running benchmark: branch-name-eval
Skill: git/branch-name
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Feature Branch Naming
✓ [2/3] Fix Branch Naming
✓ [3/3] Should Not Trigger

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 250ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Feature Branch Naming 1.00 has_output, no_ids
Fix Branch Naming 1.00 has_output, no_ids
Should Not Trigger 1.00 has_output, no_ids

Benchmark: branch-name-eval | Skill: git/branch-name | Model: claude-sonnet-4-20250514

=== commit-message ===

Running benchmark: commit-message-eval
Skill: git/commit-message
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Basic Bug Fix Commit
✓ [2/3] Multi-Area Diff
✓ [3/3] Should Not Trigger - PR Description Request

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 247ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Basic Bug Fix Commit 1.00 has_output, no_conventional_commits, no_period_ending
Multi-Area Diff 1.00 has_output, no_conventional_commits, no_period_ending
Should Not Trigger - PR Description Request 1.00 has_output, no_conventional_commits, no_period_ending

Benchmark: commit-message-eval | Skill: git/commit-message | Model: claude-sonnet-4-20250514

=== pr-title-description ===

Running benchmark: pr-title-description-eval
Skill: git/pr-title-description
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Basic Feature PR
✓ [2/3] PR With Template
✓ [3/3] Should Not Trigger - Commit Message Request

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 247ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Basic Feature PR 1.00 has_output
PR With Template 1.00 has_output
Should Not Trigger - Commit Message Request 1.00 has_output

Benchmark: pr-title-description-eval | Skill: git/pr-title-description | Model: claude-sonnet-4-20250514

═══════════════════════════════════════════════
MULTI-SKILL RUN SUMMARY
═══════════════════════════════════════════════

Skill Status Pass Rate Avg Score
──────────────────────────────────────────────────────────────────────
review-pr-comments ✅ Passed 100.0% 1.00
branch-name ✅ Passed 100.0% 1.00
commit-message ✅ Passed 100.0% 1.00
pr-title-description ✅ Passed 100.0% 1.00

Combined summary saved to: results_summary.json
Results saved to: results_review-pr-comments.json
Results saved to: results_branch-name.json
Results saved to: results_commit-message.json
Results saved to: results_pr-title-description.json

Record the review-pr-comments workflow update for the next patch release.

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

Copy link
Copy Markdown
Contributor

=== review-pr-comments ===

Running benchmark: review-pr-comments-eval
Skill: engineering/review-pr-comments
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Review Agent Feedback
✓ [2/3] Review Unresolved Comments
✓ [3/3] Should Not Trigger

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 218ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Review Agent Feedback 1.00 has_output
Review Unresolved Comments 1.00 has_output
Should Not Trigger 1.00 has_output

Benchmark: review-pr-comments-eval | Skill: engineering/review-pr-comments | Model: claude-sonnet-4-20250514

=== branch-name ===

Running benchmark: branch-name-eval
Skill: git/branch-name
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Feature Branch Naming
✓ [2/3] Fix Branch Naming
✓ [3/3] Should Not Trigger

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 217ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Feature Branch Naming 1.00 has_output, no_ids
Fix Branch Naming 1.00 has_output, no_ids
Should Not Trigger 1.00 has_output, no_ids

Benchmark: branch-name-eval | Skill: git/branch-name | Model: claude-sonnet-4-20250514

=== commit-message ===

Running benchmark: commit-message-eval
Skill: git/commit-message
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Basic Bug Fix Commit
✓ [2/3] Multi-Area Diff
✓ [3/3] Should Not Trigger - PR Description Request

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 221ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Basic Bug Fix Commit 1.00 has_output, no_conventional_commits, no_period_ending
Multi-Area Diff 1.00 has_output, no_conventional_commits, no_period_ending
Should Not Trigger - PR Description Request 1.00 has_output, no_conventional_commits, no_period_ending

Benchmark: commit-message-eval | Skill: git/commit-message | Model: claude-sonnet-4-20250514

=== pr-title-description ===

Running benchmark: pr-title-description-eval
Skill: git/pr-title-description
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Basic Feature PR
✓ [2/3] PR With Template
✓ [3/3] Should Not Trigger - Commit Message Request

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 219ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Basic Feature PR 1.00 has_output
PR With Template 1.00 has_output
Should Not Trigger - Commit Message Request 1.00 has_output

Benchmark: pr-title-description-eval | Skill: git/pr-title-description | Model: claude-sonnet-4-20250514

═══════════════════════════════════════════════
MULTI-SKILL RUN SUMMARY
═══════════════════════════════════════════════

Skill Status Pass Rate Avg Score
──────────────────────────────────────────────────────────────────────
review-pr-comments ✅ Passed 100.0% 1.00
branch-name ✅ Passed 100.0% 1.00
commit-message ✅ Passed 100.0% 1.00
pr-title-description ✅ Passed 100.0% 1.00

Combined summary saved to: results_summary.json
Results saved to: results_review-pr-comments.json
Results saved to: results_branch-name.json
Results saved to: results_commit-message.json
Results saved to: results_pr-title-description.json

Publish the updated review-pr-comments workflow as plugin patch version 0.1.1.

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

Copy link
Copy Markdown
Contributor

=== review-pr-comments ===

Running benchmark: review-pr-comments-eval
Skill: engineering/review-pr-comments
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Review Agent Feedback
✓ [2/3] Review Unresolved Comments
✓ [3/3] Should Not Trigger

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 227ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Review Agent Feedback 1.00 has_output
Review Unresolved Comments 1.00 has_output
Should Not Trigger 1.00 has_output

Benchmark: review-pr-comments-eval | Skill: engineering/review-pr-comments | Model: claude-sonnet-4-20250514

=== branch-name ===

Running benchmark: branch-name-eval
Skill: git/branch-name
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Feature Branch Naming
✓ [2/3] Fix Branch Naming
✓ [3/3] Should Not Trigger

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 226ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Feature Branch Naming 1.00 has_output, no_ids
Fix Branch Naming 1.00 has_output, no_ids
Should Not Trigger 1.00 has_output, no_ids

Benchmark: branch-name-eval | Skill: git/branch-name | Model: claude-sonnet-4-20250514

=== commit-message ===

Running benchmark: commit-message-eval
Skill: git/commit-message
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Basic Bug Fix Commit
✓ [2/3] Multi-Area Diff
✓ [3/3] Should Not Trigger - PR Description Request

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 231ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Basic Bug Fix Commit 1.00 has_output, no_conventional_commits, no_period_ending
Multi-Area Diff 1.00 has_output, no_conventional_commits, no_period_ending
Should Not Trigger - PR Description Request 1.00 has_output, no_conventional_commits, no_period_ending

Benchmark: commit-message-eval | Skill: git/commit-message | Model: claude-sonnet-4-20250514

=== pr-title-description ===

Running benchmark: pr-title-description-eval
Skill: git/pr-title-description
Engine: mock
Model: claude-sonnet-4-20250514

✓ [1/3] Basic Feature PR
✓ [2/3] PR With Template
✓ [3/3] Should Not Trigger - Commit Message Request

🧪 Waza Eval Results

Status: ✅ Passed | Score: 1.00 | Duration: 235ms

  • Tests: 3 total, 3 passed, 0 failed, 0 errors
  • Success Rate: 100.0%
  • Score Range: 1.00 - 1.00 (σ=0.0000)

Task Results

Task Score Status Graders
Basic Feature PR 1.00 has_output
PR With Template 1.00 has_output
Should Not Trigger - Commit Message Request 1.00 has_output

Benchmark: pr-title-description-eval | Skill: git/pr-title-description | Model: claude-sonnet-4-20250514

═══════════════════════════════════════════════
MULTI-SKILL RUN SUMMARY
═══════════════════════════════════════════════

Skill Status Pass Rate Avg Score
──────────────────────────────────────────────────────────────────────
review-pr-comments ✅ Passed 100.0% 1.00
branch-name ✅ Passed 100.0% 1.00
commit-message ✅ Passed 100.0% 1.00
pr-title-description ✅ Passed 100.0% 1.00

Combined summary saved to: results_summary.json
Results saved to: results_review-pr-comments.json
Results saved to: results_branch-name.json
Results saved to: results_commit-message.json
Results saved to: results_pr-title-description.json

@kin0992
kin0992 merged commit 81b5517 into main Aug 11, 2026
7 checks passed
@kin0992
kin0992 deleted the feats/batch-review-pr-comments branch August 11, 2026 10:56
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant