ClaudeSuperPower
SubmitLog in

aidp-alh

Skill

Connect from an AIDP notebook to Oracle AI Lakehouse (ALH), Autonomous Data Warehouse (ADW), or Autonomous Transaction Processing (ATP). Prefer the AIDP `aidataplatform` Spark format handler for wallet/password and catalog.id paths (`ORACLE_ALH` / `ORACLE_ATP`), but use raw Spark JDBC for IAM DB-tok

0Databases

Install

git clone https://github.com/oracle-samples/oracle-aidp-samples.git ~/.claude/skills/aidp-alh

What is aidp-alh?

Connect from an AIDP notebook to Oracle AI Lakehouse (ALH), Autonomous Data Warehouse (ADW), or Autonomous Transaction Processing (ATP). Prefer the AIDP `aidataplatform` Spark format handler for wallet/password and catalog.id paths (`ORACLE_ALH` / `ORACLE_ATP`), but use raw Spark JDBC for IAM DB-token because the AIDP connector does not support DB-token auth yet.

What this can do

Capabilities declared in this component's own frontmatter — not inferred.

Run shell commands

Declares Bash

Create and modify files

Declares Write or Edit

~91 tokens of context used while enabled, before you invoke anything

All declared tools (4)
BashEditReadWrite

Documentation

README · ~3 min read

aidp-alh — Oracle AI Lakehouse / ADW / ATP via AIDP aidataplatform

This skill covers the entire Oracle Autonomous Database family using the official AIDP ingestion connectors. Use ORACLE_ALH for Oracle AI Lakehouse / ADW-style connections and ORACLE_ATP when the user specifically wants ATP.

If the user names ATP or ADW specifically, just use this skill — substitute the env-var prefix (ATP_* / ADW_*) for ALH_* and proceed identically.

When to use

  • User wants to read or write an ALH, ADW, or ATP table from an AIDP notebook.
  • User mentions: "ALH", "AI Lakehouse", "ADW", "Autonomous Data Warehouse", "ATP", "Autonomous Transaction Processing", "Autonomous Database", "26ai lakehouse", "lakehouse external catalog".
  • User has wallet content/path, a TNS alias, DB username/password, or an existing AIDP external catalog id.

When NOT to use

Reviews

Log in to leave a review.

No reviews yet — be the first.

Explore related

Other things in this space — across every part of the ecosystem, not just skills.

Skillssimilar to this one

All skills →

claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

88.9K stars

session-report

Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.

32.8K stars

create-atomic-tool

Build a `BaseTool[InSchema, OutSchema]` subclass — input/output schemas, `BaseToolConfig`, `run()` (and optional `run_async()`), env-driven secrets, typed failure outputs. Use when the user asks to "add a tool", "create a tool", "wrap an API as a tool", "build a `BaseTool`", "make a calculator/searc

6.1K stars

Hooks

All hooks →

SessionStart

SessionStart nudge directing the agent to delegate data-engineering tasks to altimate-code via the altimate-code skill. The UserPromptSubmit pre-run hook was removed because it double-invoked altimate-code (once at hook time, once when the model fired the skill), doubling token consumption on the al

PostToolUse (mcp__.*__find_columns|mcp__.*__get_dataset_columns|mcp__.*__get_dataset)

Pre-query column validation via schema caching. Catches unknown column errors before they hit the API by building a per-session schema cache from find_columns / get_dataset_columns / get_dataset results.

PreToolUse (mcp__.*__run_query)

Pre-query column validation via schema caching. Catches unknown column errors before they hit the API by building a per-session schema cache from find_columns / get_dataset_columns / get_dataset results.