{"id":"200cd965-3df5-43a0-820a-6030456851e2","shortId":"n6cS3H","kind":"skill","title":"monte-carlo-proactive-monitoring","tagline":"Guide users from coverage analysis to monitor creation. USE WHEN user asks what should I monitor, where are my gaps, improve coverage, or wants a systematic approach to monitoring across their data estate.","description":"# Monte Carlo Proactive Monitoring Workflow\n\nThis workflow guides users through improving their monitoring coverage by\nsequencing existing Monte Carlo skills. It does not contain coverage analysis\nor monitor creation logic itself — each step loads the relevant skill's\nSKILL.md which has the actual instructions.\n\n## When to activate this workflow\n\nActivate when:\n\n- Context detection routes here (coverage intent + data project detected)\n- User invokes `/mc-proactive-monitoring`\n- User asks \"what should I monitor?\", \"where are my gaps?\", \"improve coverage\"\n- User wants a systematic approach to monitoring — not just creating one specific monitor\n\n## When NOT to activate this workflow\n\n- User already knows exactly what monitor to create (e.g., \"create a freshness monitor on X\") — route to `monitoring-advisor` directly\n- User is responding to an active incident — use incident response workflow\n- User is editing a dbt model — defer to `prevent` skill (auto-activates via hooks)\n- A skill is already active and handling the user's request\n\n---\n\n## Workflow Steps\n\n```\nStep 1 (conditional): Assess current state — when user has specific tables in mind\nStep 2: Identify gaps — the core of this workflow\nStep 3: Create monitors — act on identified gaps\n```\n\n### Determine entry point\n\nBefore starting, determine which step to enter based on the user's context:\n\n- **User mentions specific tables** (\"what monitoring do I have on stg_payments?\", \"check my orders tables\") → Start at **Step 1: Assess Current State**\n- **User has a model file open** with a specific table → Start at **Step 1: Assess Current State**\n- **User wants estate-wide coverage** (\"where are my gaps?\", \"what should I monitor?\") → Skip to **Step 2: Identify Gaps**\n- **Ambiguous** → Ask: \"Would you like to check specific tables first, or look at coverage across your estate?\"\n\n---\n\n### Step 1: Assess Current State (conditional)\n\n**Skill:** Read and follow `../asset-health/SKILL.md`\n\n**Goal:** Check health of the specific tables the user cares about — freshness, alerts, existing monitoring coverage, importance score, upstream dependencies.\n\n**When to run:** Only when the user has specific tables in mind or a model file open. Provides table-level context before the broader coverage analysis.\n\n**Transition to Step 2:** After the health report, offer the broader view:\n\n> \"[Table] has [summary of health and existing monitors]. Want me to analyze monitoring coverage more broadly — across your warehouse or use cases — to find where the gaps are?\"\n\nIf the user says yes, proceed to Step 2. If they're satisfied with the table-level view, stop.\n\n---\n\n### Step 2: Identify Gaps\n\n**Skill:** Read and follow `../monitoring-advisor/SKILL.md`\n\nWhen loading monitoring-advisor for this step, frame the request as **coverage analysis** — not direct monitor creation. The monitoring-advisor skill has two flows; this step uses the coverage analysis flow:\n- Warehouse discovery → use-case exploration → coverage analysis → gap identification\n\n**Goal:** Analyze coverage across warehouses and use cases, identify unmonitored tables, prioritize by importance and anomaly activity.\n\n**This is the core step.** Most workflow entries start here.\n\n**Transition to Step 3:** When gaps are identified and the user wants to act:\n\n> \"I've identified [N] monitoring gaps, prioritized by importance. Ready to create monitors for the top priorities?\"\n\nIf yes, proceed to Step 3 (which stays within monitoring-advisor). If no, stop.\n\n---\n\n### Step 3: Create Monitors\n\n**Skill:** Continues within `../monitoring-advisor/SKILL.md` — transitions from coverage analysis flow to direct monitor creation flow.\n\nThis step does NOT load a separate skill. The monitoring-advisor skill handles both gap identification (Step 2) and monitor creation (Step 3). The workflow just signals the transition from \"analysis\" to \"creation.\"\n\n**Goal:** Create monitors-as-code YAML for the identified gaps. For each gap:\n1. Determine the appropriate monitor type (freshness, volume, validation, custom SQL, comparison)\n2. Generate the monitor configuration\n3. Output as monitors-as-code YAML\n\n**The user can create monitors for all identified gaps or select specific ones.**\n\n---\n\n## Orchestration Rules\n\n- **Users can enter at any step.** The entry point section above determines where to start.\n- **Each step loads the actual skill's SKILL.md** via relative path. This workflow does not replicate skill logic — it sequences it.\n- **Context carries forward** through conversation naturally.\n- **No state tracking or hooks.** This is purely prompt-driven sequencing.\n- **User can exit anytime.**\n- **If the user already knows what monitor to create** (skipping Steps 1 and 2), they should not be in this workflow — context detection routes them to monitoring-advisor directly.","tags":["proactive","monitoring","agent","toolkit","monte-carlo-data","agent-observability","agent-skills","ai-agents","claude-code","codex-skills","cursor","data-observability"],"capabilities":["skill","source-monte-carlo-data","skill-proactive-monitoring","topic-agent-observability","topic-agent-skills","topic-ai-agents","topic-claude-code","topic-codex-skills","topic-cursor","topic-data-observability","topic-data-quality","topic-mcp","topic-monte-carlo","topic-opencode","topic-skill-md"],"categories":["mc-agent-toolkit"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/monte-carlo-data/mc-agent-toolkit/proactive-monitoring","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add monte-carlo-data/mc-agent-toolkit","source_repo":"https://github.com/monte-carlo-data/mc-agent-toolkit","install_from":"skills.sh"}},"qualityScore":"0.488","qualityRationale":"deterministic score 0.49 from registry signals: · indexed on github topic:agent-skills · 76 github stars · SKILL.md body (4,811 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-04-22T06:55:42.490Z","embedding":null,"createdAt":"2026-04-20T19:31:48.034Z","updatedAt":"2026-04-22T06:55:42.490Z","lastSeenAt":"2026-04-22T06:55:42.490Z","tsv":"'/asset-health/skill.md':326 '/mc-proactive-monitoring':101 '/monitoring-advisor/skill.md':442,566 '1':194,258,275,317,625,734 '2':207,296,377,422,435,595,637,736 '3':216,516,549,560,600,642 'across':35,313,402,489 'act':219,526 'activ':85,88,130,159,177,184,502 'actual':81,684 'advisor':152,447,464,555,588,751 'alert':339 'alreadi':134,183,726 'ambigu':299 'analysi':10,64,373,456,474,483,570,608 'analyz':397,487 'anomali':501 'anytim':722 'approach':32,118 'appropri':628 'ask':17,103,300 'assess':196,259,276,318 'auto':176 'auto-activ':175 'base':233 'broad':401 'broader':371,384 'care':336 'carlo':3,40,57 'carri':702 'case':407,480,493 'check':251,305,328 'code':616,648 'comparison':636 'condit':195,321 'configur':641 'contain':62 'context':90,238,368,701,744 'continu':564 'convers':705 'core':211,506 'coverag':9,27,52,63,94,113,284,312,342,372,399,455,473,482,488,569 'creat':123,140,142,217,538,561,612,653,731 'creation':13,67,460,575,598,610 'current':197,260,277,319 'custom':634 'data':37,96 'dbt':169 'defer':171 'depend':346 'detect':91,98,745 'determin':223,228,626,676 'direct':153,458,573,752 'discoveri':477 'driven':717 'e.g':141 'edit':167 'enter':232,667 'entri':224,510,672 'estat':38,282,315 'estate-wid':281 'exact':136 'exist':55,340,392 'exit':721 'explor':481 'file':266,362 'find':409 'first':308 'flow':468,475,571,576 'follow':325,441 'forward':703 'frame':451 'fresh':144,338,631 'gap':25,111,209,222,288,298,412,437,484,518,532,592,621,624,658 'generat':638 'goal':327,486,611 'guid':6,46 'handl':186,590 'health':329,380,390 'hook':179,711 'identif':485,593 'identifi':208,221,297,436,494,520,529,620,657 'import':343,499,535 'improv':26,49,112 'incid':160,162 'instruct':82 'intent':95 'invok':100 'know':135,727 'level':367,431 'like':303 'load':72,444,581,682 'logic':68,697 'look':310 'mention':240 'mind':205,358 'model':170,265,361 'monitor':5,12,21,34,42,51,66,107,120,126,138,145,151,218,244,292,341,393,398,446,459,463,531,539,554,562,574,587,597,614,629,640,646,654,729,750 'monitoring-advisor':150,445,462,553,586,749 'monitors-as-cod':613,645 'mont':2,39,56 'monte-carlo-proactive-monitor':1 'n':530 'natur':706 'offer':382 'one':124,662 'open':267,363 'orchestr':663 'order':253 'output':643 'path':690 'payment':250 'point':225,673 'prevent':173 'priorit':497,533 'prioriti':543 'proactiv':4,41 'proceed':419,546 'project':97 'prompt':716 'prompt-driven':715 'provid':364 'pure':714 're':425 'read':323,439 'readi':536 'relat':689 'relev':74 'replic':695 'report':381 'request':190,453 'respond':156 'respons':163 'rout':92,148,746 'rule':664 'run':349 'satisfi':426 'say':417 'score':344 'section':674 'select':660 'separ':583 'sequenc':54,699,718 'signal':604 'skill':58,75,174,181,322,438,465,563,584,589,685,696 'skill-proactive-monitoring' 'skill.md':77,687 'skip':293,732 'source-monte-carlo-data' 'specif':125,202,241,270,306,332,355,661 'sql':635 'start':227,255,272,511,679 'state':198,261,278,320,708 'stay':551 'step':71,192,193,206,215,230,257,274,295,316,376,421,434,450,470,507,515,548,559,578,594,599,670,681,733 'stg':249 'stop':433,558 'summari':388 'systemat':31,117 'tabl':203,242,254,271,307,333,356,366,386,430,496 'table-level':365,429 'top':542 'topic-agent-observability' 'topic-agent-skills' 'topic-ai-agents' 'topic-claude-code' 'topic-codex-skills' 'topic-cursor' 'topic-data-observability' 'topic-data-quality' 'topic-mcp' 'topic-monte-carlo' 'topic-opencode' 'topic-skill-md' 'track':709 'transit':374,513,567,606 'two':467 'type':630 'unmonitor':495 'upstream':345 'use':14,161,406,471,479,492 'use-cas':478 'user':7,16,47,99,102,114,133,154,165,188,200,236,239,262,279,335,353,416,523,651,665,719,725 'valid':633 've':528 'via':178,688 'view':385,432 'volum':632 'want':29,115,280,394,524 'warehous':404,476,490 'wide':283 'within':552,565 'workflow':43,45,87,132,164,191,214,509,602,692,743 'would':301 'x':147 'yaml':617,649 'yes':418,545","prices":[{"id":"ad6bc4bd-2ba4-413a-a36c-59a4c1ee545a","listingId":"200cd965-3df5-43a0-820a-6030456851e2","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"monte-carlo-data","category":"mc-agent-toolkit","install_from":"skills.sh"},"createdAt":"2026-04-20T19:31:48.034Z"}],"sources":[{"listingId":"200cd965-3df5-43a0-820a-6030456851e2","source":"github","sourceId":"monte-carlo-data/mc-agent-toolkit/proactive-monitoring","sourceUrl":"https://github.com/monte-carlo-data/mc-agent-toolkit/tree/main/skills/proactive-monitoring","isPrimary":false,"firstSeenAt":"2026-04-20T19:31:48.034Z","lastSeenAt":"2026-04-22T06:55:42.490Z"}],"details":{"listingId":"200cd965-3df5-43a0-820a-6030456851e2","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"monte-carlo-data","slug":"proactive-monitoring","github":{"repo":"monte-carlo-data/mc-agent-toolkit","stars":76,"topics":["agent-observability","agent-skills","ai-agents","claude-code","codex-skills","cursor","data-observability","data-quality","mcp","monte-carlo","opencode","skill-md","skillsmp","vscode"],"license":"apache-2.0","html_url":"https://github.com/monte-carlo-data/mc-agent-toolkit","pushed_at":"2026-04-22T00:57:31Z","description":"Official Monte Carlo toolkit for AI coding agents. Skills and plugins that bring data and agent observability — monitoring, triaging, troubleshooting, health checks  — into Claude Code, Cursor, and more.","skill_md_sha":"cca5aaa68808f94c70dc312133cfe6354edf2216","skill_md_path":"skills/proactive-monitoring/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/monte-carlo-data/mc-agent-toolkit/tree/main/skills/proactive-monitoring"},"layout":"multi","source":"github","category":"mc-agent-toolkit","frontmatter":{"name":"monte-carlo-proactive-monitoring","description":"Guide users from coverage analysis to monitor creation. USE WHEN user asks what should I monitor, where are my gaps, improve coverage, or wants a systematic approach to monitoring across their data estate."},"skills_sh_url":"https://skills.sh/monte-carlo-data/mc-agent-toolkit/proactive-monitoring"},"updatedAt":"2026-04-22T06:55:42.490Z"}}