aggregate-logs
CommandGenerate LEARNINGS.md from skill execution logs over a configurable time window.
Enforcement checks to verify all required outputs were produced, and the full list of command options.
> /plugin marketplace add athola/claude-night-market
Enforcement checks to verify all required outputs were produced, and the full list of command options.
> **See Also**: > [Main Command](../../pr-review.md) | > [Workflow Index](review-workflow.md) | > [Phases 1-4](review-workflow-phases-1-4.md) | > [Phases 5-6](review-workflow-phases-5-6.md) | > [Framework](review-framework.md) | > [Configuration](review-configuration.md)
---
**CRITICAL: The /pr-review command is NOT complete unless ALL of these outputs exist:**
| Output | Phase | Verification | |--------|-------|--------------| | Review | Phase 4 | `gh pr view --json comments,reviews`: a review or comment body contains "PR Review" | | Test plan comment | Phase 5 | `gh pr view --json comments` contains "Test Plan" | | PR description | Phase 6 | `gh pr view --json body` is non-empty and contains "Review Summary" |
**Enforcement Check (run at end of review):**
# Validate all mandatory outputs
PR_NUMBER=${1:-$(gh pr view --json number -q '.number')}
REVIEW_EXISTS=$(gh pr view $PR_NUMBER --json comments,reviews --jq '[(.comments[].body, .reviews[].body) | contains("PR Review")] | any')
TEST_PLAN_EXISTS=$(gh pr view $PR_NUMBER --json comments --jq '[.comments[].body | ascii_downcase | contains("test plan")] | any')
DESCRIPTION_EXISTS=$(gh pr view $PR_NUMBER --json body --jq '.body | length > 0')
echo "=== Mandatory Output Verification ==="
echo "Review comment: $( [[ $REVIEW_EXISTS == "true" ]] && echo "✅" || echo "❌ MISSING" )"
echo "Test plan: $( [[ $TEST_PLAN_EXISTS == "true" ]] && echo "✅" || echo "❌ MISSING" )"
echo "PR description: $( [[ $DESCRIPTION_EXISTS == "true" ]] && echo "✅" || echo "❌ MISSING" )"
if [[ $REVIEW_EXISTS != "true" ]] || [[ $TEST_PLAN_EXISTS != "true" ]] || [[ $DESCRIPTION_EXISTS != "true" ]]; then
echo ""
echo "⚠️ PR review INCOMPLETE - mandatory outputs missing"
echo "Run /pr-review-enforcer $PR_NUMBER to fix"
exit 1
fi
echo ""
echo "✅ All mandatory outputs verified for PR #$PR_NUMBER"**If verification fails, the review is INCOMPLETE. Go back and complete missing phases.**
of posting to the PR. Default path: `.pr-review/pr-<number>-review.md`. Skips API calls, issue creation, and PR description updates. Unlike `--dry-run`, produces a permanent file.
most one clarifying sentence, plus one short summary review. This is the one flag that narrows the MANDATORY outputs: the test plan comment and the description update are not posted, and the verification checklist in `pr-review.md` checks only for the summary review. Findings with no diff line to anchor to go in the summary, one line each.
findings in chat with a `[y/n/select]` prompt before any of them is posted. Extends Phase 4.6, which already does this for INVARIANT findings. Does not touch `--no-insights`, which governs Discussions.
A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Analyze skill file complexity metrics and generate modularization recommendations for splitting or progressive loading.
Generate context optimization report for skill directories
Create slash commands with brainstorming and best practices
Scaffold new Claude Code skills with brainstorming, TDD methodology, and proper frontmatter and module structure.
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.