Menu
Guided workflow for SQL data analysis using db_tools
Build the project's vector-indexed knowledge base from files plus database metadata — optionally scoped to specific files / tables / datasources / domains. Scan the in-scope material, classify it into business domains, explore each domain in parallel with explore subagents, then (after the user confirms a generation manifest) route every artifact to its store via storage-classify, generating semantic_models / metrics / reference_sql (and mining any extra knowledge), and refresh AGENTS.md's KB index. The lightweight /init handles the AGENTS.md inventory plus file-based knowledge/memory; this skill owns the heavy vector-store generation.
Lightweight project initialization — infer the project goal and in-scope datasources, scan the file tree and database metadata (db/table/desc/sample), classify into business domains, then write an AGENTS.md inventory skeleton plus the cheap file-based stores (atomic facts to ./knowledge/*.md via lite extract-knowledge, durable preferences to memory). Stops short of the expensive vector-indexed stores (semantic_models / metrics / reference_sql). Single confirmation-free pass, low token cost.
Decide where a produced artifact must be persisted before writing it, then route it the prescribed way — semantic_models / metrics / reference_sql via the matching task() subagent, knowledge via extract-knowledge (lite), memory via add_memory, skills via create-skill, and AGENTS.md edited directly. Load before persisting any business fact, validated SQL, metric/model definition, session preference, project convention, or reusable workflow.
Mine shortest atomic facts from (question + gold_sql) pairs into ./knowledge/*.md; either by simulating SQL drafting (lite) or by driving the gen_sql subagent in blind iteration (deep)
Audit and reorganize every persistent store — semantic_models, metrics, reference_sql, knowledge, memory, AGENTS.md, skills — verifying each item sits in the correct store per storage-classify, and surfacing duplicates, misclassifications, conflicts, and stale/erroneous entries. Produce a Remediation Plan, STOP for confirmation, then execute. Use ask_user only for genuine decisions during analysis. If nothing needs fixing, report it and stop.
Review the current chat session and persist its valuable takeaways — business facts/rules, validated SQL, metric/model definitions, durable preferences, project conventions, reusable workflows — by classifying each via storage-classify and routing it to the right store. Present a Summary Manifest and STOP for confirmation before any heavy generation. Use at the end of a working session or when the user asks to capture what was learned.
| name | sql-analysis |
| description | Guided workflow for SQL data analysis using db_tools |
| tags | ["sql","analysis","workflow"] |
| version | 1.0.0 |
This skill guides you through a structured data analysis workflow using database tools.
First, understand the database schema:
Use db_tools.list_tables() to see available tables
Use db_tools.describe_table(table_name) for each relevant table
Explore the data with sample queries:
Use db_tools.execute_sql("SELECT * FROM {table} LIMIT 10")
Based on the user's question, construct and execute the analysis query.
Analyze the results and provide insights.