aggregate-logs
Generate LEARNINGS.md from skill execution logs over a configurable time window.
**Navigation**: [← Step 1: Analyze](1-analyze.md) | [Main Workflow](../workflow-steps.md) | [Step 3: Plan →](3-plan.md)
> /plugin marketplace add athola/claude-night-marketHow it fires
How this command gets triggered: by you, by Claude, or both.
/2-triageContext preview
What this command does when you run it.
**Navigation**: [← Step 1: Analyze](1-analyze.md) | [Main Workflow](../workflow-steps.md) | [Step 3: Plan →](3-plan.md)
> **Navigation**: [← Step 1: Analyze](1-analyze.md) | [Main Workflow](../workflow-steps.md) | [Step 3: Plan →](3-plan.md)
**Purpose**: Classify comments by type and priority to determine what to fix now vs. later.
**Skip when**: Single simple fix with obvious resolution.
Present triage results in this actionable format:
### Triage Results #### 🔴 Fix Now (2 items) | ID | Issue | File | Why Critical | |----|-------|------|--------------| | C1 | Path traversal vulnerability | intelligence.rs:490 | Security | | C2 | SQL injection risk | github_search.rs:143 | Security | #### 🟡 This PR (4 items) | ID | Issue | File | |----|-------|------| | S1 | Missing error logging | intelligence.rs:82 | | S2 | Incomplete validation | parser.py:45 | | S3 | Missing docstring | utils.py:120 | | S4 | Inconsistent naming | models.py:67 | #### 📋 Backlog → Issues (7 items) | ID | Issue | Suggested Title | |----|-------|-----------------| | B1 | Low test coverage | test(intelligence): add integration tests | | B2 | Performance optimization | perf(parser): optimize regex compilation | | B3 | API documentation | docs(api): add endpoint documentation | #### ⏭️ Skip (2 items) - Informational comment about architecture - Praise for clean code structure
**Category definitions:**
Before classifying comments, check if relevant backlog documentation exists:
# Check for existing backlog files that may provide context ls docs/backlog/*.md 2>/dev/null # Key files to check: # - docs/backlog/queue.md - Active backlog items with worthiness scores # - docs/backlog/technical-debt.md - Known technical debt items
If these files exist:
| Type | Description | Action | |------|-------------|--------| | **Critical** | Bugs, security issues | Fix immediately | | **In-Scope** | Requirements-related | Address in this PR | | **Suggestion** | Improvements | **Create GitHub issue (Step 6)** | | **Deferred** | Medium priority, future work, out-of-scope | **Create GitHub issue (Step 6)** | | **Informational** | Questions, praise | Reply only |
> **Note**: If you classify ANY item as "deferred", "out-of-scope", "suggestion", or "future work", Step 6 will create GitHub issues for them.
**Step 2 Output**: Classified comment list with types and priorities
---
> **Next**: [Step 3: Plan (Fix Strategy) →](3-plan.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.