Data work often needs clear queries, repeatable transformations, and careful interpretation. This skill guides SQL, pandas, statistics, and data cleaning workflows.

Messaging teams need consistent metrics for volume, deliverability, contacts, and number capabilities. This skill queries Sent analytics and explains trends within defined periods.

Manual web research and scraping can be slow and inconsistent. This skill guides Claude, Codex, and Claude Code through ScrapeGraph CLI workflows.

Agents often lose useful lessons from prior tasks. This skill shows how to store, judge, retrieve, and distill reasoning patterns with AgentDB-backed ReasoningBank.

AgentDB teams need faster vector search and lower memory use as datasets grow. This skill provides tuning guidance for quantization, HNSW indexing, caching, batching, and monitoring.

Recoup data and connected services require precise authentication, identifiers, and endpoint schemas. This skill guides reliable retrieval and approved external actions.

Agents often need spreadsheet logic without controlling Excel. This skill guides MCP and TypeScript workflows for WorkPaper formulas, file-backed edits, and local XLSX formula reports.

Agent teams need repeatable evidence before comparing models. PinchBench runs real-world OpenClaw tasks, grades outcomes, and can publish results to a leaderboard.

DEX research often requires several data sources and command formats. This skill routes read-only market, token, wallet, social, and live signal queries through Onchain OS.

Neon projects require careful choices for connections, migrations, scaling, and recovery. This skill provides focused guidance for dependable Postgres workflows on Neon.

Agent quality is difficult to measure because outputs vary and may have several valid forms. This skill builds repeatable rubrics, tests, gates, and monitoring.

Agent decisions become difficult to explain when beliefs, goals, and commitments lack formal structure. This skill models BDI chains with RDF, SPARQL, provenance, and temporal validity.

AI agents often generate fragile data-fetching and transformation code. This skill uses mloda feature requests, plugins, and lineage to build deterministic data workflows.

Maintaining current A-share market data across several tables is slow and operationally complex. This skill configures, updates, and queries a compatible local DuckDB database through MCP tools.

Large A-share datasets make factor testing and strategy validation slow and inconsistent. QuantAll runs vectorized local analysis and returns measurable backtest, IC, screening, and visualization results.

Azure Data Explorer data can be hard to inspect without the right KQL structure and schema context. This skill helps Claude, Codex, and Claude Code build focused KQL queries, explore schemas, and troubleshoot ADX results.

Azure spending can be difficult to explain and control. This skill queries costs, forecasts spending, and produces evidence-based optimization recommendations.

Prediction market changes can be difficult to track across frequent updates. This skill polls approved feeds and formats alerts for notable events and movements.

WeChat Mac data is encrypted and difficult to search or export. This skill builds a local vault for authorized queries, exports, and summaries.

Technical analysis often requires several methods and consistent data preparation. This skill applies nine structured frameworks to Longbridge OHLCV data and explains each result.