From upriver-plugin
Invoke this skill for ANY data engineering task — pipeline failures, data quality problems, schema questions, table lineage, incident investigation, warehouse queries, debugging, writing or reviewing SQL, understanding data flow, or exploring system architecture. It provides read-only Upriver context (architecture, data assets, lineage) that must never be written to or referenced in generated code.
How this skill is triggered — by the user, by Claude, or both
Slash command
/upriver-plugin:upriver-contextThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The data and database context is located in a directory called `upriver_context`, which can be downloaded via MCP request.
The data and database context is located in a directory called upriver_context, which can be downloaded via MCP request.
Important Constraints:
${CLAUDE_PLUGIN_ROOT}/upriver_context/. This keeps the user's project directory clean.skills folder exists inside upriver_context, copy its contents into the plugin's skills folder (${CLAUDE_PLUGIN_ROOT}/skills/). This merges client-provided skills with the plugin's built-in skills.A SessionStart hook (check-context-freshness.sh) runs automatically at the beginning of every session. It checks whether the context needs refreshing (never downloaded, or older than 1 week) and writes a signal file.
⚠️ MANDATORY — You MUST complete the freshness check and any required download BEFORE doing anything else. Do NOT proceed to the user's task until the context is confirmed fresh.
${CLAUDE_PLUGIN_ROOT}/.context-needs-refresh exists.Download steps (must all complete before proceeding):
GetContextDownloadUrl MCP tool to get a presigned URL.rm -rf ${CLAUDE_PLUGIN_ROOT}/upriver_context/.${CLAUDE_PLUGIN_ROOT}/upriver_context/.skills folder exists inside upriver_context, copy its contents into ${CLAUDE_PLUGIN_ROOT}/skills/.rm -f ${CLAUDE_PLUGIN_ROOT}/.context-needs-refresh.The file ${CLAUDE_PLUGIN_ROOT}/upriver_context/context-insights-catalog.md is a catalog of all possible insight files that may exist in the upriver_context/ directory. It is bundled with the context download. Use it as a lookup table to find the right file for your task:
upriver_context/<db_type>/assets/ — e.g. Databricks catalog/schema/table/, BigQuery project/dataset/table/. Each table/view has a JSON file with metadata, attributes, and lineage (upstream/downstream).upriver_context/mwaa/ — DAG definitions, run history, task status, error messages. Use to understand pipeline execution and failures.outpost_staging.omop_cdm.person), not directory paths like upriver_context/databricks/assets/.../person.json.upriver_context directory exists. Use natural language: "searching Upriver context", "exploring Upriver context". In task plans: "Explore Upriver context structure" not "List upriver_context directory contents". If access fails, say "I'm unable to access the Upriver context at the moment" not "the upriver_context directory is not accessible".table-comparison.md in Upriver context if present. Do not skip planning (ask about branches/metrics) or logic-aware analysis (understand what changed before comparing). Classify every difference as Expected or Unexpected. See docs/reference.md for full table comparison rules.incident-investigation.md under the Upriver context directory. The file might not exist and that's ok.npx claudepluginhub upriverdata/claude-marketplace --plugin upriver-pluginRoutes users to specialized agents for data pipeline design, schema modeling, data quality, SQL optimization, lakehouse, AI pipelines, and data contracts. Provides access to 23 knowledge domains.
Explores data lineage, traces upstream/downstream dependencies, performs impact analysis, and maps data pipelines using DataHub CLI.
Generates scripts using pycarlo SDK to collect and push metadata, lineage, query logs from any data warehouse to Monte Carlo. Uses templates for warehouses like Snowflake.