From memory-toolkit
Session reflection — analyzes what happened, proposes backlog items, captures insights.
How this skill is triggered — by the user, by Claude, or both
Slash command
/memory-toolkit:reflectThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Analyze current session and propose additions to the project backlog.
Analyze current session and propose additions to the project backlog.
Check memory for saved preference:
node "$MEM" --dir="$MEM_DIR" search "backlog_target"
If no saved preference — detect automatically:
backlog.md, TODO.md, TODO, docs/backlog.mdgh issue list --limit 1 2>/dev/nullWhere do you track backlog?
1. backlog.md (will create)
2. TODO.md
3. GitHub Issues (gh issue create)
4. Other — specify path or tool
Save preference:
node "$MEM" --dir="$MEM_DIR" note "CONFIG: backlog_target=<chosen path or github-issues>"
Read current backlog to avoid duplicates.
Review what happened and find:
For each insight, ask: "Should any contributor to this project know this?" If yes — it's a DOC, not just a backlog item or feedback. Save it immediately:
node "$MEM" --dir="$MEM_DIR" note "DOC: <domain> — <insight>"
Examples of what IS a DOC:
Examples of what is NOT a DOC:
Show list in format:
## Reflect: <date>
### New items
- **<section>**: <description> — <why, with specific case from session>
### Close
- <item that is done>
### Skip
- (nothing found / everything already in backlog)
Do NOT write yet. Show user, wait for confirmation.
Update the backlog target:
[x]gh issue create --title "<item>" --body "<why>" for each new item; gh issue close <number> for closedAlso save insights to memory (included in the same confirmation — no separate prompt needed):
node "$MEM" note "REFLECT: <key insight from session>"
node "$MEM" --dir="$MEM_DIR" docs
If DOC: notes exist — notify user: "Found N documentation findings. Run /docs-reflect to process them, or /session-end will handle it."
If called from /session-end — pass control to /docs-reflect automatically.
npx claudepluginhub aivandelindt/claude_memory-toolkit --plugin memory-toolkitGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Enforces test-driven development: write failing test first, then minimal code to pass. Use when implementing features or bugfixes.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.