[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DNAFN3BN19ZCX2MGM3R7BZ":3,"skill-same:01M7DNAFN3BN19ZCX2MGM3R7BZ":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M7DNAFN3BN19ZCX2MGM3R7BZ","monte-carlo-monitoring-advisor",null,"Analyze data coverage, create monitors for warehouse tables and AI agents. Covers coverage gaps, use-case analysis, data monitor creation, and agent observability.","Hazek-dc\u002FPresensiGuru_FaceNet_EMAR","Hazek-dc","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F75208960?v=4","01M7DEQV5B4YGS86A81DYH81DR","Hazek","01M7DEQV5XP4TM0C6NTHXCXCHR",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmonte-carlo-monitoring-advisor\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: monte-carlo-monitoring-advisor\ndescription: Analyze data coverage, create monitors for warehouse tables and AI agents. Covers coverage gaps, use-case analysis, data monitor creation, and agent observability.\nrisk: unknown\nsource: https:\u002F\u002Fgithub.com\u002Fmonte-carlo-data\u002Fmc-agent-toolkit\u002Ftree\u002Fmain\u002Fskills\u002Fmonitoring-advisor\nsource_repo: monte-carlo-data\u002Fmc-agent-toolkit\nsource_type: community\ndate_added: 2026-07-01\nlicense: Apache-2.0\nlicense_source: https:\u002F\u002Fgithub.com\u002Fmonte-carlo-data\u002Fmc-agent-toolkit\u002Fblob\u002Fmain\u002FLICENSE\n---\n\n# Monte Carlo Monitoring Advisor Skill\n\nThis skill handles all monitoring requests -- coverage analysis, data monitor creation, and AI agent monitoring. It routes to the right reference file based on the user's intent.\n\n> **Monte Carlo tool routing (required):** Always call Monte Carlo MCP tools through this plugin's\n> bundled server, whose fully-qualified tool names are\n> `mcp__plugin_mc-agent-toolkit_monte-carlo-mcp__\u003Ctool>` (e.g.\n> `mcp__plugin_mc-agent-toolkit_monte-carlo-mcp__get_alerts`). Bare tool names used in this skill\n> (`get_alerts`, `search`, `get_table`, …) refer to that bundled server. If the session also has a\n> separately-configured `monte-carlo-mcp` server, do **not** route to it — it may point at a\n> different endpoint or credentials.\n\nReference files live next to this skill file. **Use the Read tool** (not MCP resources) to access them:\n\n- Data monitor creation procedure: `references\u002Fdata-monitor-creation.md` (relative to this file)\n- Agent monitor creation procedure: `references\u002Fagent-monitor-creation.md` (relative to this file)\n- Per-type references: `references\u002Fdata-*.md` and `references\u002Fagent-*.md` (relative to this file)\n\n## When to activate this skill\n\nActivate when the user:\n\n- Asks about monitoring coverage, data coverage, or coverage gaps\n- Wants to understand what's monitored vs. not in their warehouse\n- Asks about use cases, use-case criticality, or use-case analysis\n- Wants to explore their data estate and find what needs monitoring\n- Says things like \"what should I monitor?\", \"where are my coverage gaps?\", \"show me my use cases\"\n- Asks about unmonitored tables with anomalies or importance-based prioritization\n- Asks to create, add, or set up a monitor (e.g. \"add a monitor for...\", \"create a freshness check on...\", \"set up validation for...\")\n- Mentions monitoring a specific table, field, or metric\n- Wants to check data quality rules or enforce data contracts\n- Asks about monitoring options for a table or dataset\n- Requests monitors-as-code YAML generation\n- Wants to add monitoring after new transformation logic (when the prevent skill is not active)\n- Asks about monitoring AI agents, agent latency, agent token usage, or agent quality\n- Wants to set up alerts on agent behavior or execution patterns\n- Asks about investigating agent traces or conversations\n- Says things like \"monitor my agent\", \"track agent latency\", \"alert on agent errors\"\n- Asks about agent evaluation monitors, trajectory monitors, or validation monitors\n- Mentions agent observability or agent monitoring\n\n## When NOT to activate this skill\n\nDo not activate when the user is:\n\n- Just querying data or exploring table contents\n- Triaging or responding to active alerts (use the prevent skill's Workflow 3)\n- Running impact assessments before code changes (use the prevent skill's Workflow 4)\n- Asking about existing monitor configuration (use `get_monitors` directly)\n- Editing or deleting existing monitors\n\n---\n\n## Prerequisites\n\n- **Required:** Monte Carlo MCP server (`monte-carlo-mcp`) must be configured and authenticated\n- **Optional:** A database MCP server (Snowflake, BigQuery, Redshift, Databricks) for SQL profiling of table usage patterns\n\n---\n\n## Available MCP tools\n\nAll tools are available via the `monte-carlo-mcp` MCP server.\n\n### Coverage and discovery tools\n\n| Tool | Purpose |\n| --- | --- |\n| `get_warehouses` | List accessible warehouses (needed first -- `get_use_cases` requires `warehouse_id`) |\n| `get_use_cases` | List use cases with criticality, descriptions, table counts, precomputed tag names |\n| `get_use_case_table_summary` | Criticality distribution (HIGH\u002FMEDIUM\u002FLOW table counts) for a use case |\n| `get_use_case_tables` | Paginated tables with criticality, golden-table status, MCONs |\n| `get_monitors` | Check monitoring status on specific tables via `mcons` filter |\n| `get_asset_lineage` | Upstream\u002Fdownstream dependencies for tables (takes MCONs + direction) |\n| `get_audiences` | List notification audiences |\n| `get_unmonitored_tables_with_anomalies` | Tables with muted OOTB anomalies but no monitors (takes ISO 8601 time range) |\n| `search` | Find tables by name; supports `is_monitored` filter |\n| `get_table` | Table details, fields, stats, domain membership |\n| `get_queries_for_table` | Query logs for a table (source\u002Fdestination) |\n| `get_field_metric_definitions` | Available metrics per field type for a warehouse |\n| `get_domains` | List Monte Carlo domains |\n| `get_validation_predicates` | Available validation rule types |\n\n### Data monitor creation tools\n\nAll five tools follow a **two-call preview-then-confirm pattern**: the first call (with the default `dry_run=True`) returns rendered MaC YAML for review; the second call (`dry_run=False`) deploys the monitor live and returns a deep link to it. Pass `monitor_uuid` on either call to update an existing monitor in place instead of creating a new one. See `references\u002Fdata-monitor-creation.md` for the full flow.\n\n| Tool | Purpose |\n| --- | --- |\n| `create_or_update_table_monitor` | Create or update a table monitor (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_metric_monitor` | Create or update a metric monitor (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_validation_monitor` | Create or update a validation monitor (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_sql_monitor` | Create or update a custom SQL monitor (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_comparison_monitor` | Create or update a comparison monitor (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n\n### Agent monitoring tools\n\n| Tool | Purpose |\n| --- | --- |\n| `get_agent_metadata` | List AI agents -- returns agent names, `agentReference` values (the `agent` arg for monitor creation), trace table MCONs, source types |\n| `get_agent_conversation` | Retrieve recent LLM interactions\u002Fconversations for an agent |\n| `get_agent_trace` | Inspect execution traces and span trees |\n| `create_or_update_agent_metric_monitor` | Create or update monitors for quantitative span-level metrics (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_agent_evaluation_monitor` | Create or update monitors for LLM-evaluated quality metrics (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_agent_trajectory_monitor` | Create or update trajectory monitors for execution pattern alerts (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_agent_validation_monitor` | Create or update validation monitors for logical assertions (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n\n---\n\n## Routing\n\nWhen the user's request comes in, determine which workflow to follow:\n\n| User intent | Workflow |\n| --- | --- |\n| Coverage analysis, use-case exploration, \"what should I monitor?\" | **Coverage workflow** (below) |\n| Create a specific data monitor for a known table | **Read `references\u002Fdata-monitor-creation.md`** and follow its procedure |\n| Monitor AI agents, agent latency, agent quality, agent traces | **Read `references\u002Fagent-monitor-creation.md`** and follow its procedure |\n| Coverage analysis leads to monitor creation | Complete coverage workflow, then **read `references\u002Fdata-monitor-creation.md`** for creation |\n\nWhen reading reference files, always use the **Read tool** with the path relative to this skill file.\n\n---\n\n## Coverage workflow\n\nThis is the primary flow when the user asks about monitoring coverage, coverage gaps, or what to monitor.\n\n### Step 1: Discover warehouses\n\nCall `get_warehouses` to list all accessible warehouses.\n\n- If **one** warehouse: select it automatically, proceed to Step 2.\n- If **multiple** warehouses: present warehouse **names** (never UUIDs) and ask the user which one to explore.\n\n### Step 2: Discover use cases\n\nCall `get_use_cases(warehouse_id=\u003Cselected>)` to discover use cases for the chosen warehouse.\n\n- If **use cases exist** --> proceed to the **Use-case exploration** (below).\n- If **no use cases** --> proceed to the **Importance-based fallback** (below).\n\n### Step 3: Check for database MCP (optional)\n\nCheck if the user has a database MCP server available by looking for tools containing `snowflake`, `bigquery`, `redshift`, or `databricks` in the tool list. If found, note it for the SQL profiling step later. If not found, skip SQL profiling gracefully.\n\n---\n\n## Use-case exploration\n\nThis is the primary flow when use cases are defined.\n\n### Present use cases\n\n- Sort by criticality: **HIGH** before **MEDIUM** before **LOW**.\n- For each use case, show the **description** and explain the **reasoning for its criticality level** so the user understands why it matters.\n- Call `get_use_case_tables` with `golden_tables_only=true` and mention specific golden-table names as concrete examples. Golden tables are the last layer in the warehouse -- they feed ML models, dashboards, and reports. Explain this when relevant.\n- Use `get_asset_lineage` to explain how tables in a use case are connected and why certain tables are important (e.g. a golden table with many upstream dependencies).\n\n### \"Create a use case\" requests\n\nYou **cannot** create use cases -- they are generated automatically by Monte Carlo (along with their criticality), and there is no tool to author one. When the user asks to \"create\", \"set up\", or \"define\" a use case: briefly say so, and do NOT silently substitute monitor deployment. Then offer what you *can* do for the table(s) they named -- look up the existing use case \u002F criticality, recommend field monitors, generate monitor previews, or analyze coverage gaps -- and act on the do-able part without expanding to sibling tables.\n\n### Analyze coverage\n\n1. Call `get_use_case_table_summary` to show how many tables exist at each criticality level (HIGH \u002F MEDIUM \u002F LOW) for the use case.\n2. Call `get_use_case_tables` to obtain table MCONs, then call `get_monitors(mcons=[...])` to report how many are already monitored vs. not.\n3. **Default to HIGH + MEDIUM criticality scope.** This covers the most important tables without overwhelming the user. Do NOT ask the user which scope to use -- just proceed. If they want LOW-criticality tables included, they'll ask.\n4. You may suggest covering **multiple** use cases in one session.\n5. **Bias toward action, not questions.** When the scope is clear (HIGH + MEDIUM for the selected use case), proceed directly to generating monitor previews for all recommended monitors. Frame it as opt-out, not opt-in: \"I'll generate previews for all N monitors -- tell me if you want to skip any.\" Do NOT ask \"which would you like me to create?\" one at a time -- batch them.\n\n### Identify coverage gaps with anomaly data\n\nUse `get_unmonitored_tables_with_anomalies` to discover tables that are **not monitored** but already have muted out-of-the-box anomalies. This reveals real coverage gaps -- places where Monte Carlo detected data issues but no monitor was configured to alert anyone.\n\n- Call it with a recent time window (e.g. last 7-30 days) using ISO 8601 timestamps.\n- Results are ranked by **importance score** -- the most critical gaps appear first.\n- Each result includes a sample of anomaly events showing what types of issues were detected (freshness, volume, schema changes).\n- Use this to **prioritize** which unmonitored tables to cover first -- a table with recent anomalies is a stronger candidate than one with no activity.\n- Cross-reference with use-case data: if an unmonitored table with anomalies belongs to a critical use case, escalate its priority.\n\n---\n\n## Importance-based fallback\n\nWhen no use cases are defined, fall back to importance-based table discovery.\n\n1. **Find unmonitored tables:** Use `search(query=\"\", is_monitored=false)` to find unmonitored tables sorted by importance.\n2. **Find tables with anomalies:** Use `get_unmonitored_tables_with_anomalies` with a recent time window (last 14-30 days) to find tables with recent anomalies but no monitors.\n3. **Inspect top candidates:** Use `get_table` to check table details, fields, and stats for the most important unmonitored tables.\n4. **Understand criticality via lineage:** Use `get_asset_lineage` with `direction=\"DOWNSTREAM\"` to understand which tables are most connected -- a table with many downstream dependents is a stronger candidate for monitoring.\n5. **Prioritize:** Rank candidates by importance score and anomaly activity. Present the top candidates to the user with reasoning.\n\n### Important\n\n- **Do NOT present importance scores as business criticality.** Always explain that the importance score is a *computed* metric (query frequency, downstream dependencies, usage patterns), not business-defined criticality.\n- Tell the user their account doesn't have use-case data **yet** -- use cases are generated automatically by Monte Carlo from warehouse metadata and exposed as asset tags; they are not manually configured through a UI.\n- You can still create metric, validation, and custom SQL monitors for individual tables in this mode -- you just won't use tag-based table monitors, since there are no use-case tags.\n\n---\n\n## SQL profiling (optional)\n\nIf a database MCP server was detected in Step 3 of the coverage workflow:\n\n1. Call `get_queries_for_table` to see recent query patterns on candidate tables.\n2. Use the database MCP tools (e.g. `snowflake_query`, `bigquery_query`) to profile table usage -- identify which tables are queried most frequently, which columns are used in JOINs and WHERE clauses.\n3. Use this information to refine monitor suggestions -- heavily-queried tables with no monitors are high-priority gaps.\n\nIf no database MCP is available, skip this step entirely. Do not ask the user to configure one.\n\n---\n\n## Pre-creation context (coverage-driven)\n\nWhen coverage analysis leads to monitor creation, gather this context before reading the creation reference file:\n\n1. **Dedup first.** Before generating a use-case tag monitor, call `get_monitors` with the same tag pair (and `monitor_types=[\"TABLE\"]`) you'd put in the monitor's `asset_selection.filters`. If a monitor already covers that `(tag, domain)` scope, surface it (description, uuid) and ask whether to update it (pass its `monitor_uuid`), add one with a distinct scope, or skip -- do NOT silently re-create. The backend upserts a table monitor on its `(description, domain)`, so a same-description definition silently overwrites the prior monitor's settings.\n2. Call `get_audiences` to list notification audiences. Suggest one or more relevant audiences (match by team or use-case context) and ask the user which they want -- they can pick **one or several**. This is the **one** question to ask before generating; do NOT also ask about draft\u002Factive or schedule. Default to **draft** (`is_draft=True`); the user can flip to active after seeing the preview.\n3. When passing `audiences` or `failure_audiences`, use the audience **name\u002Flabel** (not UUID), as a list -- one entry per selected audience.\n4. **Never fabricate credit costs.** Do not give a generic per-monitor or per-field MC credit rate -- cost scales with the specific spec (segmentation, schedule, field count). If a preview response includes a backend estimate (e.g. `estimated_credits.credits_per_day`), report that; otherwise decline and offer to preview a specific monitor or use case to get the real estimate.\n\n### Use-case tag monitors\n\nThe most common output of coverage analysis is a **table monitor scoped by use-case tags** via `create_or_update_table_monitor`. The `asset_selection` parameter uses this structure:\n\n```json\n{\n  \"databases\": [\"\u003Cdatabase_name>\"],\n  \"schemas\": [\"\u003Cschema_name>\"],\n  \"filters\": [\n    {\n      \"type\": \"TABLE_TAG\",\n      \"tableTags\": [\"\u003Ctag_key>:\u003Ccriticality>\"],\n      \"tableTagsOperator\": \"HAS_ANY\"\n    }\n  ]\n}\n```\n\nRules:\n- Filter `type` is **always** `TABLE_TAG` for use-case monitors.\n- `tableTagsOperator` should be `HAS_ANY`.\n- Each entry in `tableTags` is `\"\u003Ctag_key>:\u003Cvalue>\"` where the tag key is the precomputed tag name from `get_use_cases` output and the value is the criticality level in lowercase (`high`, `medium`, `low`).\n- To monitor only HIGH-criticality tables: `[\"tag_name:high\"]`\n- To monitor MEDIUM + HIGH: `[\"tag_name:high\", \"tag_name:medium\"]`\n- To monitor ALL: `[\"tag_name:high\", \"tag_name:medium\", \"tag_name:low\"]`\n\n### Monitor title (`description`) and reasoning (`notes`)\n\nKeep these distinct -- both are accepted by the creation tools. The backend auto-generates the monitor `name` slug; `description` is the title users see.\n\n- **`description` -- the title.** Short and scannable (≤ ~80 chars), plain English, naming the asset\u002Fuse case and criticality scope. Do NOT cram reasoning here.\n- **`notes` -- the reasoning.** 1-3 sentences answering \"why this monitor?\", grounded in criticality, scope, and downstream impact.\n\nExample for a use-case tag monitor:\n\n- **Bad description** (this is reasoning, not a title): `\"Monitor HIGH criticality tables in the Revenue Reporting use case to catch issues before they affect dashboards and financial reports.\"`\n- **Good description:** `\"Revenue Reporting coverage -- HIGH + MEDIUM criticality tables\"`\n- **Good notes** (paired): `\"Covers HIGH\u002FMEDIUM-criticality tables in the Revenue Reporting use case. Catches freshness, volume, and schema issues before they reach dashboards and financial reports.\"`\n\n---\n\n## Transient and truncate-and-reload tables\n\nSome tables show 0 rows when queried directly but have recent write activity in Monte Carlo metadata. These are **transient tables** -- fully replaced on each pipeline run (truncate-and-reload pattern). Recognize this pattern early to avoid wasting time querying empty tables.\n\nSigns of a transient table:\n- `get_table` shows recent `last_write` timestamp and high read\u002Fwrite activity\n- Direct SQL query returns 0 rows or all-NULL timestamp columns\n- Monte Carlo detected freshness anomalies (the table stayed empty longer than expected between loads)\n\n---\n\n## Graceful degradation\n\nHandle missing or unavailable tools gracefully:\n\n| Scenario | Behavior |\n| --- | --- |\n| No use cases defined | Fall back to importance-based discovery |\n| No database MCP available | Skip SQL profiling, rely on MC tools only |\n| `get_unmonitored_tables_with_anomalies` returns empty | Note that no recent anomalies were found; proceed with use-case or importance-based prioritization |\n| `get_use_case_tables` returns no tables | Note the use case has no tables; suggest exploring other use cases |\n| `get_audiences` returns empty | Inform user no audiences are configured; monitors can still be created without notification routing |\n| User has no warehouses | Inform user that no warehouses are accessible; they may need to check their Monte Carlo permissions |\n\nNever error out or stop the conversation because one tool returned empty results. Explain what happened and offer the next best path.\n\n---\n\n## Rules\n\n- **Never expose UUIDs, MCONs, or internal identifiers** to the user -- always use human-readable names for warehouses, audiences, use cases, and tables. Keep internal identifiers for tool calls only.\n- When the user asks about relationships between tables, use `get_asset_lineage` to fetch upstream\u002Fdownstream connections and explain the data flow.\n- Be concise but thorough. Use bullet points and tables for clarity.\n- Always use **ISO 8601** format for datetime values in tool calls.\n- Never reformat YAML values returned by creation tools.\n- When passing `audiences` or `failure_audiences` to monitor creation tools, use the audience **name\u002Flabel** (not UUID). The API accepts audience names.\n\n## Limitations\n\n- Use this skill only when the task clearly matches its upstream source and local project context.\n- Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.\n- Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.\n","# Monte Carlo Monitoring Advisor Skill\n\nThis skill handles all monitoring requests -- coverage analysis, data monitor creation, and AI agent monitoring. It routes to the right reference file based on the user's intent.\n\n> **Monte Carlo tool routing (required):** Always call Monte Carlo MCP tools through this plugin's\n> bundled server, whose fully-qualified tool names are\n> `mcp__plugin_mc-agent-toolkit_monte-carlo-mcp__\u003Ctool>` (e.g.\n> `mcp__plugin_mc-agent-toolkit_monte-carlo-mcp__get_alerts`). Bare tool names used in this skill\n> (`get_alerts`, `search`, `get_table`, …) refer to that bundled server. If the session also has a\n> separately-configured `monte-carlo-mcp` server, do **not** route to it — it may point at a\n> different endpoint or credentials.\n\nReference files live next to this skill file. **Use the Read tool** (not MCP resources) to access them:\n\n- Data monitor creation procedure: `references\u002Fdata-monitor-creation.md` (relative to this file)\n- Agent monitor creation procedure: `references\u002Fagent-monitor-creation.md` (relative to this file)\n- Per-type references: `references\u002Fdata-*.md` and `references\u002Fagent-*.md` (relative to this file)\n\n## When to activate this skill\n\nActivate when the user:\n\n- Asks about monitoring coverage, data coverage, or coverage gaps\n- Wants to understand what's monitored vs. not in their warehouse\n- Asks about use cases, use-case criticality, or use-case analysis\n- Wants to explore their data estate and find what needs monitoring\n- Says things like \"what should I monitor?\", \"where are my coverage gaps?\", \"show me my use cases\"\n- Asks about unmonitored tables with anomalies or importance-based prioritization\n- Asks to create, add, or set up a monitor (e.g. \"add a monitor for...\", \"create a freshness check on...\", \"set up validation for...\")\n- Mentions monitoring a specific table, field, or metric\n- Wants to check data quality rules or enforce data contracts\n- Asks about monitoring options for a table or dataset\n- Requests monitors-as-code YAML generation\n- Wants to add monitoring after new transformation logic (when the prevent skill is not active)\n- Asks about monitoring AI agents, agent latency, agent token usage, or agent quality\n- Wants to set up alerts on agent behavior or execution patterns\n- Asks about investigating agent traces or conversations\n- Says things like \"monitor my agent\", \"track agent latency\", \"alert on agent errors\"\n- Asks about agent evaluation monitors, trajectory monitors, or validation monitors\n- Mentions agent observability or agent monitoring\n\n## When NOT to activate this skill\n\nDo not activate when the user is:\n\n- Just querying data or exploring table contents\n- Triaging or responding to active alerts (use the prevent skill's Workflow 3)\n- Running impact assessments before code changes (use the prevent skill's Workflow 4)\n- Asking about existing monitor configuration (use `get_monitors` directly)\n- Editing or deleting existing monitors\n\n---\n\n## Prerequisites\n\n- **Required:** Monte Carlo MCP server (`monte-carlo-mcp`) must be configured and authenticated\n- **Optional:** A database MCP server (Snowflake, BigQuery, Redshift, Databricks) for SQL profiling of table usage patterns\n\n---\n\n## Available MCP tools\n\nAll tools are available via the `monte-carlo-mcp` MCP server.\n\n### Coverage and discovery tools\n\n| Tool | Purpose |\n| --- | --- |\n| `get_warehouses` | List accessible warehouses (needed first -- `get_use_cases` requires `warehouse_id`) |\n| `get_use_cases` | List use cases with criticality, descriptions, table counts, precomputed tag names |\n| `get_use_case_table_summary` | Criticality distribution (HIGH\u002FMEDIUM\u002FLOW table counts) for a use case |\n| `get_use_case_tables` | Paginated tables with criticality, golden-table status, MCONs |\n| `get_monitors` | Check monitoring status on specific tables via `mcons` filter |\n| `get_asset_lineage` | Upstream\u002Fdownstream dependencies for tables (takes MCONs + direction) |\n| `get_audiences` | List notification audiences |\n| `get_unmonitored_tables_with_anomalies` | Tables with muted OOTB anomalies but no monitors (takes ISO 8601 time range) |\n| `search` | Find tables by name; supports `is_monitored` filter |\n| `get_table` | Table details, fields, stats, domain membership |\n| `get_queries_for_table` | Query logs for a table (source\u002Fdestination) |\n| `get_field_metric_definitions` | Available metrics per field type for a warehouse |\n| `get_domains` | List Monte Carlo domains |\n| `get_validation_predicates` | Available validation rule types |\n\n### Data monitor creation tools\n\nAll five tools follow a **two-call preview-then-confirm pattern**: the first call (with the default `dry_run=True`) returns rendered MaC YAML for review; the second call (`dry_run=False`) deploys the monitor live and returns a deep link to it. Pass `monitor_uuid` on either call to update an existing monitor in place instead of creating a new one. See `references\u002Fdata-monitor-creation.md` for the full flow.\n\n| Tool | Purpose |\n| --- | --- |\n| `create_or_update_table_monitor` | Create or update a table monitor (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_metric_monitor` | Create or update a metric monitor (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_validation_monitor` | Create or update a validation monitor (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_sql_monitor` | Create or update a custom SQL monitor (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_comparison_monitor` | Create or update a comparison monitor (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n\n### Agent monitoring tools\n\n| Tool | Purpose |\n| --- | --- |\n| `get_agent_metadata` | List AI agents -- returns agent names, `agentReference` values (the `agent` arg for monitor creation), trace table MCONs, source types |\n| `get_agent_conversation` | Retrieve recent LLM interactions\u002Fconversations for an agent |\n| `get_agent_trace` | Inspect execution traces and span trees |\n| `create_or_update_agent_metric_monitor` | Create or update monitors for quantitative span-level metrics (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_agent_evaluation_monitor` | Create or update monitors for LLM-evaluated quality metrics (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_agent_trajectory_monitor` | Create or update trajectory monitors for execution pattern alerts (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n| `create_or_update_agent_validation_monitor` | Create or update validation monitors for logical assertions (preview YAML on `dry_run=True`, deploy on `dry_run=False`) |\n\n---\n\n## Routing\n\nWhen the user's request comes in, determine which workflow to follow:\n\n| User intent | Workflow |\n| --- | --- |\n| Coverage analysis, use-case exploration, \"what should I monitor?\" | **Coverage workflow** (below) |\n| Create a specific data monitor for a known table | **Read `references\u002Fdata-monitor-creation.md`** and follow its procedure |\n| Monitor AI agents, agent latency, agent quality, agent traces | **Read `references\u002Fagent-monitor-creation.md`** and follow its procedure |\n| Coverage analysis leads to monitor creation | Complete coverage workflow, then **read `references\u002Fdata-monitor-creation.md`** for creation |\n\nWhen reading reference files, always use the **Read tool** with the path relative to this skill file.\n\n---\n\n## Coverage workflow\n\nThis is the primary flow when the user asks about monitoring coverage, coverage gaps, or what to monitor.\n\n### Step 1: Discover warehouses\n\nCall `get_warehouses` to list all accessible warehouses.\n\n- If **one** warehouse: select it automatically, proceed to Step 2.\n- If **multiple** warehouses: present warehouse **names** (never UUIDs) and ask the user which one to explore.\n\n### Step 2: Discover use cases\n\nCall `get_use_cases(warehouse_id=\u003Cselected>)` to discover use cases for the chosen warehouse.\n\n- If **use cases exist** --> proceed to the **Use-case exploration** (below).\n- If **no use cases** --> proceed to the **Importance-based fallback** (below).\n\n### Step 3: Check for database MCP (optional)\n\nCheck if the user has a database MCP server available by looking for tools containing `snowflake`, `bigquery`, `redshift`, or `databricks` in the tool list. If found, note it for the SQL profiling step later. If not found, skip SQL profiling gracefully.\n\n---\n\n## Use-case exploration\n\nThis is the primary flow when use cases are defined.\n\n### Present use cases\n\n- Sort by criticality: **HIGH** before **MEDIUM** before **LOW**.\n- For each use case, show the **description** and explain the **reasoning for its criticality level** so the user understands why it matters.\n- Call `get_use_case_tables` with `golden_tables_only=true` and mention specific golden-table names as concrete examples. Golden tables are the last layer in the warehouse -- they feed ML models, dashboards, and reports. Explain this when relevant.\n- Use `get_asset_lineage` to explain how tables in a use case are connected and why certain tables are important (e.g. a golden table with many upstream dependencies).\n\n### \"Create a use case\" requests\n\nYou **cannot** create use cases -- they are generated automatically by Monte Carlo (along with their criticality), and there is no tool to author one. When the user asks to \"create\", \"set up\", or \"define\" a use case: briefly say so, and do NOT silently substitute monitor deployment. Then offer what you *can* do for the table(s) they named -- look up the existing use case \u002F criticality, recommend field monitors, generate monitor previews, or analyze coverage gaps -- and act on the do-able part without expanding to sibling tables.\n\n### Analyze coverage\n\n1. Call `get_use_case_table_summary` to show how many tables exist at each criticality level (HIGH \u002F MEDIUM \u002F LOW) for the use case.\n2. Call `get_use_case_tables` to obtain table MCONs, then call `get_monitors(mcons=[...])` to report how many are already monitored vs. not.\n3. **Default to HIGH + MEDIUM criticality scope.** This covers the most important tables without overwhelming the user. Do NOT ask the user which scope to use -- just proceed. If they want LOW-criticality tables included, they'll ask.\n4. You may suggest covering **multiple** use cases in one session.\n5. **Bias toward action, not questions.** When the scope is clear (HIGH + MEDIUM for the selected use case), proceed directly to generating monitor previews for all recommended monitors. Frame it as opt-out, not opt-in: \"I'll generate previews for all N monitors -- tell me if you want to skip any.\" Do NOT ask \"which would you like me to create?\" one at a time -- batch them.\n\n### Identify coverage gaps with anomaly data\n\nUse `get_unmonitored_tables_with_anomalies` to discover tables that are **not monitored** but already have muted out-of-the-box anomalies. This reveals real coverage gaps -- places where Monte Carlo detected data issues but no monitor was configured to alert anyone.\n\n- Call it with a recent time window (e.g. last 7-30 days) using ISO 8601 timestamps.\n- Results are ranked by **importance score** -- the most critical gaps appear first.\n- Each result includes a sample of anomaly events showing what types of issues were detected (freshness, volume, schema changes).\n- Use this to **prioritize** which unmonitored tables to cover first -- a table with recent anomalies is a stronger candidate than one with no activity.\n- Cross-reference with use-case data: if an unmonitored table with anomalies belongs to a critical use case, escalate its priority.\n\n---\n\n## Importance-based fallback\n\nWhen no use cases are defined, fall back to importance-based table discovery.\n\n1. **Find unmonitored tables:** Use `search(query=\"\", is_monitored=false)` to find unmonitored tables sorted by importance.\n2. **Find tables with anomalies:** Use `get_unmonitored_tables_with_anomalies` with a recent time window (last 14-30 days) to find tables with recent anomalies but no monitors.\n3. **Inspect top candidates:** Use `get_table` to check table details, fields, and stats for the most important unmonitored tables.\n4. **Understand criticality via lineage:** Use `get_asset_lineage` with `direction=\"DOWNSTREAM\"` to understand which tables are most connected -- a table with many downstream dependents is a stronger candidate for monitoring.\n5. **Prioritize:** Rank candidates by importance score and anomaly activity. Present the top candidates to the user with reasoning.\n\n### Important\n\n- **Do NOT present importance scores as business criticality.** Always explain that the importance score is a *computed* metric (query frequency, downstream dependencies, usage patterns), not business-defined criticality.\n- Tell the user their account doesn't have use-case data **yet** -- use cases are generated automatically by Monte Carlo from warehouse metadata and exposed as asset tags; they are not manually configured through a UI.\n- You can still create metric, validation, and custom SQL monitors for individual tables in this mode -- you just won't use tag-based table monitors, since there are no use-case tags.\n\n---\n\n## SQL profiling (optional)\n\nIf a database MCP server was detected in Step 3 of the coverage workflow:\n\n1. Call `get_queries_for_table` to see recent query patterns on candidate tables.\n2. Use the database MCP tools (e.g. `snowflake_query`, `bigquery_query`) to profile table usage -- identify which tables are queried most frequently, which columns are used in JOINs and WHERE clauses.\n3. Use this information to refine monitor suggestions -- heavily-queried tables with no monitors are high-priority gaps.\n\nIf no database MCP is available, skip this step entirely. Do not ask the user to configure one.\n\n---\n\n## Pre-creation context (coverage-driven)\n\nWhen coverage analysis leads to monitor creation, gather this context before reading the creation reference file:\n\n1. **Dedup first.** Before generating a use-case tag monitor, call `get_monitors` with the same tag pair (and `monitor_types=[\"TABLE\"]`) you'd put in the monitor's `asset_selection.filters`. If a monitor already covers that `(tag, domain)` scope, surface it (description, uuid) and ask whether to update it (pass its `monitor_uuid`), add one with a distinct scope, or skip -- do NOT silently re-create. The backend upserts a table monitor on its `(description, domain)`, so a same-description definition silently overwrites the prior monitor's settings.\n2. Call `get_audiences` to list notification audiences. Suggest one or more relevant audiences (match by team or use-case context) and ask the user which they want -- they can pick **one or several**. This is the **one** question to ask before generating; do NOT also ask about draft\u002Factive or schedule. Default to **draft** (`is_draft=True`); the user can flip to active after seeing the preview.\n3. When passing `audiences` or `failure_audiences`, use the audience **name\u002Flabel** (not UUID), as a list -- one entry per selected audience.\n4. **Never fabricate credit costs.** Do not give a generic per-monitor or per-field MC credit rate -- cost scales with the specific spec (segmentation, schedule, field count). If a preview response includes a backend estimate (e.g. `estimated_credits.credits_per_day`), report that; otherwise decline and offer to preview a specific monitor or use case to get the real estimate.\n\n### Use-case tag monitors\n\nThe most common output of coverage analysis is a **table monitor scoped by use-case tags** via `create_or_update_table_monitor`. The `asset_selection` parameter uses this structure:\n\n```json\n{\n  \"databases\": [\"\u003Cdatabase_name>\"],\n  \"schemas\": [\"\u003Cschema_name>\"],\n  \"filters\": [\n    {\n      \"type\": \"TABLE_TAG\",\n      \"tableTags\": [\"\u003Ctag_key>:\u003Ccriticality>\"],\n      \"tableTagsOperator\": \"HAS_ANY\"\n    }\n  ]\n}\n```\n\nRules:\n- Filter `type` is **always** `TABLE_TAG` for use-case monitors.\n- `tableTagsOperator` should be `HAS_ANY`.\n- Each entry in `tableTags` is `\"\u003Ctag_key>:\u003Cvalue>\"` where the tag key is the precomputed tag name from `get_use_cases` output and the value is the criticality level in lowercase (`high`, `medium`, `low`).\n- To monitor only HIGH-criticality tables: `[\"tag_name:high\"]`\n- To monitor MEDIUM + HIGH: `[\"tag_name:high\", \"tag_name:medium\"]`\n- To monitor ALL: `[\"tag_name:high\", \"tag_name:medium\", \"tag_name:low\"]`\n\n### Monitor title (`description`) and reasoning (`notes`)\n\nKeep these distinct -- both are accepted by the creation tools. The backend auto-generates the monitor `name` slug; `description` is the title users see.\n\n- **`description` -- the title.** Short and scannable (≤ ~80 chars), plain English, naming the asset\u002Fuse case and criticality scope. Do NOT cram reasoning here.\n- **`notes` -- the reasoning.** 1-3 sentences answering \"why this monitor?\", grounded in criticality, scope, and downstream impact.\n\nExample for a use-case tag monitor:\n\n- **Bad description** (this is reasoning, not a title): `\"Monitor HIGH criticality tables in the Revenue Reporting use case to catch issues before they affect dashboards and financial reports.\"`\n- **Good description:** `\"Revenue Reporting coverage -- HIGH + MEDIUM criticality tables\"`\n- **Good notes** (paired): `\"Covers HIGH\u002FMEDIUM-criticality tables in the Revenue Reporting use case. Catches freshness, volume, and schema issues before they reach dashboards and financial reports.\"`\n\n---\n\n## Transient and truncate-and-reload tables\n\nSome tables show 0 rows when queried directly but have recent write activity in Monte Carlo metadata. These are **transient tables** -- fully replaced on each pipeline run (truncate-and-reload pattern). Recognize this pattern early to avoid wasting time querying empty tables.\n\nSigns of a transient table:\n- `get_table` shows recent `last_write` timestamp and high read\u002Fwrite activity\n- Direct SQL query returns 0 rows or all-NULL timestamp columns\n- Monte Carlo detected freshness anomalies (the table stayed empty longer than expected between loads)\n\n---\n\n## Graceful degradation\n\nHandle missing or unavailable tools gracefully:\n\n| Scenario | Behavior |\n| --- | --- |\n| No use cases defined | Fall back to importance-based discovery |\n| No database MCP available | Skip SQL profiling, rely on MC tools only |\n| `get_unmonitored_tables_with_anomalies` returns empty | Note that no recent anomalies were found; proceed with use-case or importance-based prioritization |\n| `get_use_case_tables` returns no tables | Note the use case has no tables; suggest exploring other use cases |\n| `get_audiences` returns empty | Inform user no audiences are configured; monitors can still be created without notification routing |\n| User has no warehouses | Inform user that no warehouses are accessible; they may need to check their Monte Carlo permissions |\n\nNever error out or stop the conversation because one tool returned empty results. Explain what happened and offer the next best path.\n\n---\n\n## Rules\n\n- **Never expose UUIDs, MCONs, or internal identifiers** to the user -- always use human-readable names for warehouses, audiences, use cases, and tables. Keep internal identifiers for tool calls only.\n- When the user asks about relationships between tables, use `get_asset_lineage` to fetch upstream\u002Fdownstream connections and explain the data flow.\n- Be concise but thorough. Use bullet points and tables for clarity.\n- Always use **ISO 8601** format for datetime values in tool calls.\n- Never reformat YAML values returned by creation tools.\n- When passing `audiences` or `failure_audiences` to monitor creation tools, use the audience **name\u002Flabel** (not UUID). The API accepts audience names.\n\n## Limitations\n\n- Use this skill only when the task clearly matches its upstream source and local project context.\n- Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.\n- Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.\n",{"name":5,"risk":24,"source":25,"license":15,"date_added":26,"description":7,"source_repo":27,"source_type":28,"license_source":29},"unknown","https:\u002F\u002Fgithub.com\u002Fmonte-carlo-data\u002Fmc-agent-toolkit\u002Ftree\u002Fmain\u002Fskills\u002Fmonitoring-advisor",1782864000000,"monte-carlo-data\u002Fmc-agent-toolkit","community","https:\u002F\u002Fgithub.com\u002Fmonte-carlo-data\u002Fmc-agent-toolkit\u002Fblob\u002Fmain\u002FLICENSE","main","b1e4ffadb4f933bbbcaa03a83f8b9929171ac28b",".agents\u002Fskills\u002Fmonte-carlo-monitoring-advisor",0,"https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR","https:\u002F\u002Fgithub.com\u002FHazek-dc","2026-10-22 08:36:44",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Hazek-dc\u002FPresensiGuru_FaceNet_EMAR --skill monte-carlo-monitoring-advisor",{"tool":43,"command":44},"bunx","bunx skills add Hazek-dc\u002FPresensiGuru_FaceNet_EMAR --skill monte-carlo-monitoring-advisor",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Hazek-dc\u002FPresensiGuru_FaceNet_EMAR --skill monte-carlo-monitoring-advisor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmonte-carlo-monitoring-advisor\u002FSKILL.md",true,[],[52,60,67,74,81,88],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":56,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7DS6GGYRZAYD33PFPS8Z2T3","testing-best-practices","Laravel test design and review. Use when selecting coverage, naming or structuring tests, choosing assertions or test data, isolating dependencies, testing HTTP or security boundaries, improving suite performance, or reviewing test value. Use framework guidance or search-docs for Pest and PHPUnit syntax.","MIT","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002Fattendance-web\u002F.claude\u002Fskills\u002Ftesting-best-practices\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":56,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7DS6BC3AW7HTPRHE2TTVKWM","tailwindcss-development","Always invoke when the user's message includes 'tailwind' in any form. Also invoke for: building responsive grid layouts (multi-column card grids, product grids), flex\u002Fgrid page structures (dashboards with sidebars, fixed topbars, mobile-toggle navs), styling UI components (cards, tables, navbars, pricing sections, forms, inputs, badges), adding dark mode variants, fixing spacing or typography, and Tailwind v3\u002Fv4 work. The core use case: writing or fixing Tailwind utility classes in HTML templates (Blade, JSX, Vue). Skip for backend PHP logic, database queries, API routes, JavaScript with no HTML\u002FCSS component, CSS file audits, build tool configuration, and vanilla CSS.","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002Fattendance-web\u002F.claude\u002Fskills\u002Ftailwindcss-development\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":56,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7DS66GE6B11MYJDVC74HXM4","laravel-best-practices","Apply this skill whenever writing, reviewing, or refactoring Laravel PHP code. This includes creating or modifying controllers, models, migrations, form requests, policies, jobs, scheduled commands, service classes, and Eloquent queries. Triggers for N+1 and query performance issues, caching strategies, authorization and security patterns, validation, error handling, queue and job configuration, route definitions, and architectural decisions. Also use for Laravel code reviews and refactoring existing Laravel code to follow best practices. Covers any task involving Laravel backend PHP code patterns.","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002Fattendance-web\u002F.claude\u002Fskills\u002Flaravel-best-practices\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":56,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7DS5ZW717DMS6P1E90AQCKV","infer-conventions","Use this skill to analyze how a Laravel application is actually written and record its conventions as shared rules. Trigger when the user wants to detect, infer, document, or standardize project conventions or coding style, set up or grow `.ai\u002Frules`, resolve mixed or conflicting patterns (e.g. \"are we using Form Requests or inline validation?\"), or onboard agents and teammates to \"how we do things here\". Covers: a systematic sweep of ~49 Laravel convention dimensions (validation, models, architecture, testing, frontend, database, console), open-ended house-pattern discovery, conflict reporting, and recording rules scoped to the right paths via the Boost `record-rule` MCP tool. Only run this skill when the user explicitly asks for it; never start a sweep as part of another task. Do not use for one-off code review, enforcing formatting a linter already handles, or editing `.ai\u002Frules` files by hand.","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002Fattendance-web\u002F.claude\u002Fskills\u002Finfer-conventions\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":56,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7DS5W12RGCVJTFQJ1N0GB8E","inertia-react-development","Develops Inertia.js v2 React client-side applications. Activates when creating React pages, forms, or navigation; using \u003CLink>, \u003CForm>, useForm, or router; working with deferred props, prefetching, or polling; or when user mentions React with Inertia, React pages, React forms, or React navigation.","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002Fattendance-web\u002F.claude\u002Fskills\u002Finertia-react-development\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":56,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7DS5PVDPMPCWSK2RXPDC9BB","deploying-to-cloud","Deploys and manages Laravel applications on Laravel Cloud using the `cloud` CLI. Use when the user wants to deploy an app, ship to Cloud, create or manage applications, environments, databases, caches, object storage, queues, domains, instances, background processes, secrets, compute, scheduled tasks, or Laravel Cloud infrastructure; or check billing, usage, or spend. Triggers on deployment, shipping, Cloud management, environment setup, database provisioning, billing or usage queries, the `cloud` CLI, and Laravel Cloud deployment troubleshooting.","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002Fattendance-web\u002F.claude\u002Fskills\u002Fdeploying-to-cloud\u002FSKILL.md",[],[]]