pm-07-conformance
Evaluate conformance of the event log to discovered models and generate deviation artefacts.
Evaluate conformance of the event log to discovered models and generate deviation artefacts.
This skill should be used when the user asks to "analyze DBF files", "read DBF data", "query DBF database", "convert DBF to Parquet", "analyze Thai accounting data", "explore legacy database", "run DuckDB queries on DBF", or mentions DBF, Parquet conversion, or Thai legacy accounting systems. Provides comprehensive guidance for reading, converting, and analyzing Thai legacy DBF accounting databases.
Execute chunked historical blockchain data backfills using canonical 1-year pattern. Use when loading multi-year historical data, filling gaps in ClickHouse, or preventing OOM failures on Cloud Run. Keywords chunked_backfill.sh, BigQuery historical, gap filling, memory-safe backfill.
Fetch ClickHouse Cloud service details from API (organization ID, service endpoints, configuration). Use when setting up new ClickHouse Cloud services, discovering endpoints, or validating service metadata for gapless-crypto-clickhouse project.
Phase 3 of Ontology Builder Pipeline. Synthesizes analysis results into complete Domain Requirement Document (DRD). Use after Phase 2 analysis is complete to generate structured DRD.
Flutter + fpdart環境でのDriftデータベース管理の包括的なスキル。以下の場合に使用:(1) 型安全なクエリを持つDriftデータベースのセットアップ、(2) EitherとTaskEitherを使った関数型エラーハンドリングの実装、(3) fpdartの合成を使ったリポジトリパターンの作成、(4) データベースマイグレーションとスキーマ変更の管理、(5) 関数型変換を使ったリアクティブストリームの記述、(6) 関数型ラッパーを使ったトランザクション管理の実装、(7) 例外を使わない関数型データベースエラーハンドリング、(8) 依存性注入を使ったテスト可能なデータベースレイヤーの作成、(9) Driftのクエリビルダーを使った複雑なクエリの構築、(10) リレーションシップ管理の実装、(11) JSONカラムを使った柔軟なデータ構造の保存と取得
Create, alter, and validate Snowflake semantic views using Snowflake CLI (snow). Use when asked to build or troubleshoot semantic views/semantic layer definitions with CREATE/ALTER SEMANTIC VIEW, to validate semantic-view DDL against Snowflake via CLI, or to guide Snowflake CLI installation and connection setup.
Ingest the event log, normalise schema, and generate an initial data profile with notebook and manifest updates.
Implement data I/O with immediate DTO conversion using ILoader/ISaver protocols. Use when: building data loaders, result savers, file handlers, model persistence, or any external I/O operations. Triggers: "loader", "saver", "I/O", "file", "parquet", "json", "csv", "persistence", "データ読込", "保存", "永続化", "読み書き". NOT for: data transformation (use processor-impl), business logic (use domain-impl).
Write robust GAQL queries for last-90-days ads+metrics, and implement field-fallback when Google Ads API rejects fields.
Comprehensive data validation framework for testing schema compliance, data quality, and referential integrity. Validates databases, APIs, data pipelines, and file formats. Generates data quality scorecards with anomaly detection across completeness, accuracy, and consistency.
Run AWS Athena queries against telemetry data. Use when executing SQL against telemetry-parser-db (raw Parquet from telemetry-parser-service) or telemetry_alerts (DBT-transformed tables). Also for Glue catalog exploration, partition debugging, or filtering by $path pseudo-column.
Install, configure, and validate local ClickHouse for gapless-crypto-clickhouse development and backtesting. Use when setting up local development environment, enabling offline mode, improving query performance for backtesting, or running E2E validation. Includes mise/Homebrew/apt installation, mode detection, connection validation, and E2E workflow scripts.
FiftyOne dataset visualization and curation tool via Podman Quadlet. Multi-container architecture with MongoDB sidecar for dataset persistence. GPU-accelerated for ML workflows. Use when users need to configure, start, or manage FiftyOne for dataset analysis.
验证车险CSV数据的完整性和正确性,检查26个必需字段,验证数据类型、枚举值和业务规则。当用户提到"验证数据"、"检查数据"、"数据导入"、"CSV"时使用。
Use when developing BigQuery Dataform transformations, SQLX files, source declarations, or troubleshooting pipelines - enforces TDD workflow (tests first), ALWAYS use ${ref()} never hardcoded table paths, comprehensive columns:{} documentation, safety practices (--schema-suffix dev, --dry-run), proper ref() syntax, .sqlx for new declarations, no schema config in operations/tests, and architecture patterns that prevent technical debt under time pressure
Convert a Nextflow subworkflow to a Galaxy workflow
This skill should be used when moving data between storage locations, changing data structures, renaming fields, or removing deprecated data. Covers schema versioning, safe migration methods, the Foundry unset operator, and idempotent migrations.
Understand the specific data model, entities, and database operations for Project SENTINEL. Use when writing database queries, creating migrations, or explaining the data architecture.
Assists with migrating data from Neo4j Memory to Graphiti temporal knowledge graphs
Investigate ClickHouse query failures, exceptions, crashes, and error patterns. Use for error analysis and failure investigation.