aggregate-logs
CommandGenerate LEARNINGS.md from skill execution logs over a configurable time window.
Check the memory-palace research queue for items needing evaluation.
> /plugin marketplace add athola/claude-night-market
Check the memory-palace research queue for items needing evaluation.
ls -lt plugins/memory-palace/docs/knowledge-corpus/queue/*.md 2>/dev/null | head -20
Check for:
hooks write it quoted: `status: "pending_review"`)
Display pending items using this format:
## Knowledge Queue Status ### Pending Review (X items) | File | Age | Topic | Priority | |------|-----|-------|----------| | webfetch-article-name-2026-01-15.md | 2 days | "Article Title" | medium | | websearch-query-2026-01-10.md | 7 days | "Search Query" | medium | ### Action Required - [ ] 3 items older than 7 days - review or archive - [ ] 1 high-priority item awaiting decision
For each pending item older than 3 days:
1. Display summary (topic, source, content preview) 2. Request decision:
update index
rationale
3. Execute decision (move file, update frontmatter)
Example evaluation prompt:
Queue Item: webfetch-claude-plugins-guide-2026-01-10.md (7 days old) Topic: "Claude Code Plugin Development Guide" Source: https://docs.anthropic.com/plugins/guide Content: 2,340 chars Decision options: [P]romote to knowledge-corpus/ [A]rchive (not valuable) [D]efer (review later) [S]kip (next item)
For items marked for promotion:
# 1. Move from queue to corpus mv plugins/memory-palace/docs/knowledge-corpus/queue/webfetch-*.md \ plugins/memory-palace/docs/knowledge-corpus/ # 2. Update frontmatter status # Change: status: "pending_review" -> status: "processed" # 3. Rename to permanent filename (remove webfetch- prefix, timestamp) # webfetch-article-name-2026-01-15.md -> article-name.md
Create TodoWrite items for each promotion decision:
queue-review:promoted:<filename> queue-review:archived:<filename> queue-review:deferred:<filename>
To skip queue check: use `--skip-queue` flag.
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.