aggregate-logs
Generate LEARNINGS.md from skill execution logs over a configurable time window.
**Navigation**: [<- Summary](summary.md) | [Step 6 Hub](../6-complete.md) | [Main Workflow](../../workflow-steps.md)
> /plugin marketplace add athola/claude-night-marketHow it fires
How this command gets triggered: by you, by Claude, or both.
/verificationContext preview
What this command does when you run it.
**Navigation**: [<- Summary](summary.md) | [Step 6 Hub](../6-complete.md) | [Main Workflow](../../workflow-steps.md)
> **Navigation**: [<- Summary](summary.md) | [Step 6 Hub](../6-complete.md) | [Main Workflow](../../workflow-steps.md)
**Purpose**: Run final verification and ensure all workflow gates pass before reporting complete.
---
This phase runs automatically at the end of /fix-pr.
Skill(sanctum:resolve-threads)
This validates any threads missed during Step 6.3 are resolved via batch operation.
**Step 6 Output**: All threads resolved, issues created, summary posted
---
**ALL THREE conditions must be true:**
# === GATE 1: Thread Resolution === UNRESOLVED=$(gh api graphql -f query="..." --jq '...' ) [[ "$UNRESOLVED" -eq 0 ]] && echo "Gate 1: Threads" || echo "Gate 1 FAILED" # === GATE 2: Reconciliation Complete === # Verify reconciliation table has no UNACCOUNTED items # This is a manual check - review your reconciliation table above echo "Gate 2: Verify UNACCOUNTED = 0 in reconciliation table" # === GATE 3: Issues Created === # Count issues created that reference this PR ISSUES=$(gh issue list --search "PR #$PR_NUM in:body created:>=today" --json number --jq 'length') echo "Issues created today referencing PR: $ISSUES" # Compare against Suggestion + Deferred count from triage
**Workflow completion checklist:**
**DO NOT report "/fix-pr complete" until all gates pass.**
---
> **Back to**: [Step 6 Hub](../6-complete.md) | [Main Workflow](../../workflow-steps.md)
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.
Scaffold new Claude Code skills with brainstorming, TDD methodology, and proper frontmatter and module structure.