Database schemas are hard to understand when tables, keys, and indexes are scattered across files. This skill turns schema sources into diagrams, documentation, and relationship analysis.

Slow database queries can increase costs and make applications feel unreliable. This skill helps Claude, Codex, and Claude Code review queries, execution plans, and index choices.

Writing correct database queries across SQL, NoSQL, and ORM tools can be slow and error prone. This skill helps Claude, Codex, and Claude Code design, optimize, and explain query patterns.

JSON work often requires validation, reshaping, extraction, and conversion across tools. This skill gives Claude, Codex, and Claude Code practical patterns for common JSON transformations.

Bad records, weak schemas, and unclear rules can slow delivery and hide data quality risks. This skill guides Claude, Codex, and Claude Code through validation checks, reports, and practical fixes.

CSV files often contain inconsistent formats, missing values, duplicates, and large datasets. This skill provides practical workflows for parsing, cleaning, transforming, merging, and analyzing CSV data.

Raw data is hard to interpret without the right chart. This skill helps create clear static and interactive visualizations with practical library examples.

Complex data investigations lose context when questions, evidence, and conclusions remain scattered. This skill maintains them in one evolving analysis tree.

Database code can become slow when queries run inside repeated loops. This skill guides Claude, Codex, and Claude Code toward bulk SQLAlchemy operations, joins, and repository boundaries.

JSON can consume excessive prompt tokens when records repeat the same keys. This skill converts suitable structures into compact TOON and validates format rules.

Data and reporting tasks often need repeatable Python workflows with clear output rules. This skill guides Claude, Codex, and Claude Code through sandboxed analysis, charts, and downloadable document generation.

Image review often needs structured visual reasoning, not only a short caption. This skill guides GLM-4V prompts for descriptions, visual questions, OCR, and detail extraction.

Teams often need web content in clean formats without writing custom scrapers. This skill guides Claude, Codex, and Claude Code through Firecrawl modes for scraping, search, maps, crawling, extraction, and status checks.

Slow database queries harm application reliability and scale. This skill gives practical PostgreSQL patterns for faster queries, safer migrations, and clearer monitoring.

PostgreSQL migrations can pass tests while causing locks, slow scans, or index bloat. This skill gives Claude, Codex, and Claude Code practical patterns for safer schema and query review.

LLM evaluation is hard to make consistent across teams and models. This skill helps design judge prompts, rubrics, metrics, and bias checks for repeatable assessments.

Writing OQL queries requires exact schema names, JSON types, Candid escaping, and careful pagination. This skill provides practical patterns for reliable, read-only canister queries.

Logseq database concepts can be difficult to connect across entities, classes, properties, and validation. This skill explains the Datascript model and provides practical schema templates.

Logseq users often need reliable access to pages, blocks, properties, and relationships without hand-writing every query. This skill gives Claude, Codex, and Claude Code structured helpers for reading local Logseq graph data.

Logseq database queries are difficult to structure and optimize. This skill provides practical Datalog patterns for filters, pulls, rules, aggregations, and plugin queries.