health-checking

name: health-checking description: > Checks waggle configuration health: Scheduled Task remnants, custom intake settings, config.json migration status, and Notion Desktop Extension version. Triggers on: "health check", "check config", "check setup", "ヘルスチェック", "設定チェック", "設定確認" user-invocable: true

Waggle — Health Check

You are performing a configuration health check for waggle. This skill verifies that user-dependent settings are correct and up-to-date.

Output Discipline

This skill runs as a multi-step pipeline, but the user only needs its outcomes. Do not narrate step transitions ("Now I'll...", "X done, next Y") and do not relay protocol internals — provider detection, config/schema checks, cache state, validation plumbing, view-server pushes. Surfacing them buries what actually matters.

Emit user-facing text only when it changes something for the user:

• a prompt or confirmation that needs their input
• an error or a warning
• an intermediate result that changes the outcome (e.g., a non-PASS quality verdict and the gaps behind it — it explains why a task lands at a different status than expected)
• the final result summary

Step 0: Session Bootstrap

Invoke the bootstrap-session skill to establish the active provider and current user. Skip if active_provider and current_user are already set in this conversation.

Step 1: Run Checks

Run each check below and collect results. Skip checks marked with environment/provider conditions when they don't apply.

Check 1: Scheduled Task Remnant (Claude Desktop / Cowork only)

Skip if execution_environment = "cli".

Call mcp__scheduled-tasks__list_scheduled_tasks to retrieve all Scheduled Tasks.

Look for entries where:

• description contains "waggle" (case-insensitive), AND
• cronExpression is set (i.e., it is a recurring scheduled task, not a one-time fireAt task)

Check 2: Custom Intake Instructions

CLI / Claude Desktop (execution_environment is "cli" or "claude-desktop")

Read ~/.waggle/intake-prompt.md via Bash: cat ~/.waggle/intake-prompt.md 2>/dev/null

Cowork (execution_environment = "cowork")

Check the system prompt for <waggle-custom-intake> and </waggle-custom-intake> tags.

Check 3: ~/.waggle/config.json Migration (CLI / Claude Desktop only)

Skip if execution_environment = "cowork".

Read ~/.waggle/config.json via Bash: cat ~/.waggle/config.json 2>/dev/null

Migration Flow

1. Parse the config.json content and identify the provider and values:

   Provider	Config Key	Target Env Var
   Notion	tasksDatabaseId	WAGGLE_NOTION_TASKS_DB_ID
   Notion	teamsDatabaseId	WAGGLE_NOTION_TEAMS_DB_ID
   Notion	intakeLogDatabaseId	WAGGLE_NOTION_INTAKE_LOG_DB_ID
   Notion	sprintsDatabaseId	WAGGLE_NOTION_SPRINTS_DB_ID
   Notion	activeThreadsDatabaseId	WAGGLE_NOTION_ACTIVE_THREADS_DB_ID
   SQLite	dbPath	WAGGLE_SQLITE_DB_PATH
   Turso	tursoUrl	TURSO_URL
   Turso	tursoAuthToken	TURSO_AUTH_TOKEN

2. Display the migration plan to the user:

   "Legacy ~/.waggle/config.json found. I can migrate these values to ~/.claude/settings.json env and delete the old file."

   Show the key → env var mapping with values.

3. Ask for confirmation via AskUserQuestion:

   "Proceed with config.json migration?"

4. If approved:

   • Read ~/.claude/settings.json (create if it doesn't exist)
   • Add each env var to the env field (preserve existing env vars)
   • Write the updated ~/.claude/settings.json
   • Delete ~/.waggle/config.json via Bash: rm ~/.waggle/config.json
   • Report: PASS: Migration complete

5. If declined:

   • Report: WARN: Migration skipped. Manual migration recommended.

Check 4: Notion Desktop Extension Version (Claude Desktop / Cowork, Notion provider only)

Skip if execution_environment = "cli" or active_provider is not "notion".

Check available MCP tools, then probe pagination support:

Pagination probe: when mcp__notion-extension__notion-query is available, call it with database_id: <intakeLogDatabaseId from the Waggle Config page> and page_size: 1. The Intake Log is guaranteed to exist after the first ingesting-messages run and is always small (bounded by Step 4's TTL cleanup), so it is the safest probe target. If intakeLogDatabaseId is not yet set in config (first-ever waggle session, before ingesting-messages has created the DB), fall back to any other small config-referenced DB you already have an ID for. Do not probe tasksDatabaseId — on a v0.3.x host the probe itself will fetch the entire Tasks DB and trigger the very overflow this check is meant to detect.

Inspect the response:

• Response object contains a has_more key → server honors page_size → v0.4.0+. PASS.
• Response object does not contain has_more (only results) → server ignored page_size and aggregated everything → v0.3.x or earlier. WARN.

Step 2: Report

Output a markdown report summarizing all check results:

## Waggle Health Check Report

| Check | Result | Details |
|---|---|---|
| Scheduled Task Remnant | PASS/FAIL | ... |
| Custom Intake Instructions | INFO | ... |
| config.json Migration | PASS/WARN | ... |
| Notion Extension Version | PASS/WARN | ... |

If any checks resulted in FAIL or WARN, summarize the required actions at the end of the report.