Menu
Analyze Snowflake AI cost data and generate insights and reports.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Draft on-brand marketing copy – product announcement emails and slide outlines – that follows Peak Outfitters' brand voice and style guidelines. Use whenever the user wants to write marketing content, a launch email, an announcement, or a slide/deck outline, even if they don't mention the brand explicitly. Triggers: brand content, marketing copy, launch email, announcement, deck outline, slide outline, on-brand, style guide.
Detect anomalies in hot food sales data. Use this skill when the user asks about unusual patterns, spikes, drops, outliers, or unexpected changes in revenue, quantity sold, or transaction counts across stores, categories, states, or items.
Generate a comprehensive sales report by store or by state. Use this skill when the user asks for a sales report, performance summary, store report, state report, executive summary, or full analysis of a specific store or state.
**[REQUIRED]** Use for ALL tasks combining Snowflake Cortex AI functions with Ibis (Python dataframe library): AI_COMPLETE, AI_SENTIMENT, AI_CLASSIFY, AI_EXTRACT, AI_FILTER, AI_SUMMARIZE_AGG, SNOWFLAKE.CORTEX.COMPLETE, SNOWFLAKE.CORTEX.EMBED_TEXT_768/1024, vector similarity search, semantic search, EnrichmentPipeline, direct Cortex REST API calls (PAT auth, JWT auth, streaming SSE, tool calling), cortex_ibis, cortex_rest.
Deploy AI Cost Dashboard stored procedures and Streamlit app to Snowflake.
Build and manage a Snowflake AI Cost Dashboard using stored procedures and Streamlit. Use for **ALL** requests involving: AI cost, AI spending, cost dashboard, spending dashboard, Snowflake AI credits, Cortex cost tracking. DO NOT attempt AI cost dashboard work manually - invoke this skill first.
| name | analyze-report |
| description | Analyze Snowflake AI cost data and generate insights and reports. |
| parent_skill | ai-cost-dashboard |
From ai-cost-dashboard SKILL.md when user selects Analyze / Report intent.
ADMIN_DB.AI_COSTS)| Table | Purpose |
|---|---|
ADMIN_DB.AI_COSTS.CORTEX_AI_UNIFIED_COSTS | Aggregated costs by date/service/model |
ADMIN_DB.AI_COSTS.USER_AI_COSTS | Per-user, per-query cost detail |
Service categories in unified table: LLM Functions, Analyst, Document Processing, Fine Tuning, Provisioned Throughput, REST API, Search, Document AI, LLM Functions Query, Cortex Code CLI
Goal: Understand what the user wants to analyze.
Actions:
Ask user for analysis parameters:
What would you like to analyze?
1. Overall AI credit consumption
2. Cost breakdown by service category
3. Cost trends and anomalies
4. Cost attribution by user
5. Model-level token usage
Time range: Last 7 / 30 / 90 / 365 days / Custom
Optionally refresh data first:
CALL ADMIN_DB.AI_COSTS.REFRESH_CORTEX_AI_COSTS(<days>);
CALL ADMIN_DB.AI_COSTS.REFRESH_USER_AI_COSTS(<days>);
Output: Defined analysis scope and time range
Goal: Retrieve AI cost data.
Actions:
Overall consumption:
SELECT SERVICE_CATEGORY, SUM(CREDITS) AS TOTAL_CREDITS, SUM(TOKENS) AS TOTAL_TOKENS, SUM(REQUEST_COUNT) AS TOTAL_REQUESTS
FROM ADMIN_DB.AI_COSTS.CORTEX_AI_UNIFIED_COSTS
WHERE USAGE_DATE >= DATEADD('day', -<days>, CURRENT_DATE())
GROUP BY SERVICE_CATEGORY
ORDER BY TOTAL_CREDITS DESC;
Daily trend:
SELECT USAGE_DATE, SUM(CREDITS) AS DAILY_CREDITS
FROM ADMIN_DB.AI_COSTS.CORTEX_AI_UNIFIED_COSTS
WHERE USAGE_DATE >= DATEADD('day', -<days>, CURRENT_DATE())
GROUP BY USAGE_DATE ORDER BY USAGE_DATE;
Top users:
SELECT FULL_NAME, SUM(CREDITS) AS TOTAL_CREDITS, COUNT(DISTINCT QUERY_ID) AS REQUESTS
FROM ADMIN_DB.AI_COSTS.USER_AI_COSTS
WHERE USAGE_DATE >= DATEADD('day', -<days>, CURRENT_DATE())
GROUP BY FULL_NAME ORDER BY TOTAL_CREDITS DESC LIMIT 20;
Model usage:
SELECT MODEL_NAME, SUM(TOKENS) AS TOTAL_TOKENS, SUM(CREDITS) AS TOTAL_CREDITS
FROM ADMIN_DB.AI_COSTS.CORTEX_AI_UNIFIED_COSTS
WHERE USAGE_DATE >= DATEADD('day', -<days>, CURRENT_DATE())
GROUP BY MODEL_NAME ORDER BY TOTAL_TOKENS DESC;
Output: Raw cost data
Goal: Analyze data and surface key findings.
Actions:
Calculate key metrics:
Identify anomalies:
Compile findings
Output: Analysis summary
Goal: Deliver findings to user.
Actions:
Present structured report:
Cortex AI Cost Analysis Report
Period: <start> to <end>
Summary:
- Total credits: X
- Total tokens: X
- Total requests: X
- Daily average: X credits/day
Top Services:
1. <category> - X credits (Y%)
2. <category> - X credits (Y%)
Top Users:
1. <name> - X credits, N requests
Top Models:
1. <model> - X tokens
Anomalies:
- [Any spikes or unusual patterns]
Recommendations:
- [Actionable suggestions]
STOP: Ask if user wants deeper analysis on any area.
If requested, drill down and repeat from Step 2 with narrower scope.
Output: Delivered report
AI cost analysis report with insights, trends, anomalies, and recommendations.