Check Meilisearch index status, tasks, health, and settings. Use for debugging search issues, monitoring indexing tasks, and inspecting index configuration. Read-only admin operations.
| name | meilisearch-admin |
| description | Check Meilisearch index status, tasks, health, and settings. Use for debugging search issues, monitoring indexing tasks, and inspecting index configuration. Read-only admin operations. |
Use this skill for admin operations on Meilisearch - checking status, monitoring tasks, and inspecting index settings.
node .claude/skills/meilisearch-admin/query.mjs <command> [options]
| Command | Description |
|---|---|
health | Check if Meilisearch is healthy |
stats | Get overall stats and list indexes |
task-summary | Task count breakdown by status |
tasks | List recent tasks |
task <id> | Get details of a specific task |
indexes | List all indexes |
index <name> | Get index stats |
index <name> settings | Get all index settings |
index <name> filterable | Get filterable attributes |
index <name> sortable | Get sortable attributes |
index <name> searchable | Get searchable attributes |
| Flag | Description |
|---|---|
--feed | Use feed/metrics search (METRICS_SEARCH_HOST) instead of main search |
--status <s> | Filter tasks by status: enqueued, processing, succeeded, failed |
--limit <n> | Limit results (default: 20) |
--json | Output raw JSON |
# Check health
node .claude/skills/meilisearch-admin/query.mjs health
# Get overall stats
node .claude/skills/meilisearch-admin/query.mjs stats
# Task count summary by status
node .claude/skills/meilisearch-admin/query.mjs task-summary
# Check failed tasks
node .claude/skills/meilisearch-admin/query.mjs tasks --status failed
# Check processing tasks
node .claude/skills/meilisearch-admin/query.mjs tasks --status processing --limit 50
# Get specific task details
node .claude/skills/meilisearch-admin/query.mjs task 2030419
# List all indexes
node .claude/skills/meilisearch-admin/query.mjs indexes
# Get index stats
node .claude/skills/meilisearch-admin/query.mjs index models_v9
# Get filterable attributes for an index
node .claude/skills/meilisearch-admin/query.mjs index metrics_images_v1 filterable
# Use feed search instead of main
node .claude/skills/meilisearch-admin/query.mjs --feed stats
node .claude/skills/meilisearch-admin/query.mjs --feed tasks --status failed
The project has two Meilisearch instances:
| Instance | Env Variables | Purpose |
|---|---|---|
| Main Search | SEARCH_HOST, SEARCH_API_KEY | Primary search (models, users, etc.) |
| Feed/Metrics | METRICS_SEARCH_HOST, METRICS_SEARCH_API_KEY | Image feed and metrics search |
Use --feed flag to target the feed/metrics instance.
models_v9 - Model searchusers_v3 - User searcharticles_v3 - Article searchmetrics_images_v1 - Image feed with metrics# Check if indexing is stuck
node .claude/skills/meilisearch-admin/query.mjs tasks --status processing
# Find failed indexing tasks
node .claude/skills/meilisearch-admin/query.mjs tasks --status failed
# Get error details for a failed task
node .claude/skills/meilisearch-admin/query.mjs task <taskId>
# Check if an index is still indexing
node .claude/skills/meilisearch-admin/query.mjs index <indexName>
Wire an existing ecosystem into the generation system. Adds generation support to basemodel.constants.ts, creates graph and handler files, and wires them into the ecosystem discriminator, workflow config, and router. Use after add-ecosystem when you need the ecosystem to show up in the generation form. Always checks @civitai/client for ecosystem-specific types before writing the handler.
Draft a model description for the CivitaiOfficial account when mirroring a third-party model on civitai.com or civitai.red. Use when the user is publishing or rewriting a mirrored model page (e.g. Sulphur, HappyHorse, Wan, ACE-Step) and wants a structured, properly-credited description rather than a one-line stub. Produces HTML ready to paste into the Civitai rich-text editor.
Read, replace, reset, export, and import XGuard policy options on the orchestrator. Use when you need to inspect current per-label policies for text or prompt scans, ship a refined policy, restore defaults, or back up the policy registry. Read-only by default; destructive operations require an explicit `--writable` flag.
Run PostgreSQL queries for testing, debugging, and performance analysis. Use when you need to query the database directly, run EXPLAIN ANALYZE, compare query results, or test SQL optimizations. Always uses read-only connections unless explicitly directed otherwise.
Author a prompt-enhancement system prompt for a new ecosystem and register/update it on the orchestrator's prompt-analysis service. Use when onboarding a new ecosystem (e.g. happyhorse, a new Flux variant, a new Wan video version) and the user provides the ecosystem key plus a reference link, model card, or description. Produces a guide that mirrors the structure and tone of existing ecosystem guides so the prompt-analysis tool behaves consistently.
Query and explore Civitai Orchestration workflows, jobs, and results. Use for analyzing image/video generation jobs, viewing job results, searching by workflow ID, job ID, user, or date range.
