First-use onboarding for gutt memory integration. Verifies MCP connection, demonstrates memory search and capture, explains HUD and active hooks. Triggers on: onboard, getting started, first time, setup guide, how does this work.
How this skill is triggered — by the user, by Claude, or both
Slash command
/gutt-claude-code-plugin:onboardThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Announce:** "Starting gutt memory onboarding..."
Announce: "Starting gutt memory onboarding..."
Walk the user through first-use setup and verification of the gutt memory integration.
Check if the gutt MCP server is configured in the project's settings.
# Check for gutt MCP configuration in settings
cat .claude/settings.json 2>/dev/null | grep -q "gutt"
/gutt-claude-code-plugin:setup to configure it..claude/settings.json.Run a test query to confirm the MCP connection is live:
search_memory_nodes(query="test connectivity", max_nodes=1)
| Result | Action |
|---|---|
| Success (any response) | "MCP connection verified." Proceed to Step 3. |
| Not configured error | "MCP server not configured. Run /gutt-claude-code-plugin:setup first." Stop. |
| Unreachable / timeout | "MCP server unreachable. Check your network and server URL." Stop. |
| Auth failure | "Authentication failed. Check your API key or token." Stop. |
Demonstrate memory retrieval by searching the knowledge graph:
search_memory_nodes(query="recent decisions or lessons", max_nodes=5)
Show results formatted as:
## Your Memory Graph
Found [N] entries:
| Entity | Type | Summary |
| ------ | ------ | --------------- |
| [name] | [type] | [brief summary] |
Explain: "The gutt memory graph stores organizational knowledge -- lessons learned, decisions made, patterns discovered, and relationships between them. Every search, capture, and agent delegation flows through this graph."
If no results are returned: "Your memory graph is empty -- that is expected for a new setup. It will grow as you work."
Demonstrate memory capture by storing an onboarding record:
add_memory(
name="Onboarding: plugin activated",
episode_body="gutt-claude-code-plugin onboarding completed for this project. Plugin active with memory integration.",
source="text",
source_description="onboard skill - first capture"
)
Confirm: "First memory captured. This entry marks the activation of the plugin for this project."
Explain the statusline that appears at the bottom of the terminal:
The HUD statusline shows live counters:
- memoryQueries: Number of memory searches performed this session
- lessonsCaptured: Number of lessons/decisions written to memory this session
These reset each session. You can manually reset them with:
/gutt-claude-code-plugin:reset-counters
List all hooks that are active and what they do:
## Active Hooks
| Hook | Event | What It Does |
| ----------------------- | ----------------------------------- | ------------------------------------------------------- |
| session-start | SessionStart | Loads seed registry and primes memory cache on startup |
| sessionstart-setup | SessionStart | Validates MCP configuration and plugin state |
| user-prompt-submit | UserPromptSubmit | Injects relevant memory context before each prompt |
| stop-lessons | Stop | Captures lessons learned when a conversation ends |
| post-tool-lint | PostToolUse (Edit/Write) | Runs lint checks after file edits |
| cowork-periodic-capture | PostToolUse (Edit/Write/Task/Agent) | Periodically captures progress to memory during work |
| post-task-lessons | PostToolUse (Task/Agent) | Extracts lessons from completed agent tasks |
| post-memory-ops | PostToolUse (MCP memory tools) | Tracks memory operation metrics for the HUD |
| pre-task-memory | PreToolUse (Task/Agent) | Injects relevant memory context before agent delegation |
| subagent-start-memory | SubagentStart | Injects organizational memory into subagent context |
| subagent-plan-review | SubagentStop | Reviews subagent output for lessons to capture |
| statusline | StatusLine | Renders the HUD with memory operation counters |
## Next Steps
You are ready to use gutt memory integration. Here is what to try:
1. **Search before tasks** -- Use `/memory-retrieval` or just start working;
the hooks automatically search memory for relevant context.
2. **Capture corrections and decisions** -- Use `/memory-capture` when you
learn something worth remembering, or say "remember that..." naturally.
3. **Available agents** -- Check `agents/` for specialized agents like
`plugin-dev`, `plugin-qa`, `hook-expert`, and more.
4. **Skills** -- Run `/skills-discovery` to analyze what additional skills
could help your workflow.
When invoked with --check, skip the tutorial and just verify:
Output a compact status table:
## gutt Plugin Health Check
| Component | Status |
| ----------------- | ------------------------------- |
| MCP connectivity | OK / FAIL: [reason] |
| Hook registration | OK ([N] hooks) / FAIL: [reason] |
| Seed registry | OK / NOT FOUND |
| Memory cache | WARM / COLD |
npx claudepluginhub ibrain-bvba/gutt-claude-code-plugin --plugin gutt-claude-code-pluginGives Claude persistent cross-session memory: recall past failures before starting tasks, capture success/failure feedback, and auto-generate prevention rules from repeated mistakes. Runs locally via ThumbGate MCP server.
Guides agents to deliberately search or skip memory using dejavu MCP tools, with query strategies and metadata filters for decisions, user preferences, conventions, and anti-patterns.
Diagnoses and resolves Memsy MCP tool failures (auth errors, network issues, missing tools) and guides through setup steps.